CN111683229B

CN111683229B - Cruise monitoring method, device, equipment and storage medium

Info

Publication number: CN111683229B
Application number: CN202010574159.XA
Authority: CN
Inventors: 郑伟
Original assignee: Hangzhou Hikvision System Technology Co Ltd
Current assignee: Hangzhou Hikvision System Technology Co Ltd
Priority date: 2020-06-22
Filing date: 2020-06-22
Publication date: 2021-10-26
Anticipated expiration: 2040-06-22
Also published as: CN111683229A

Abstract

The embodiment of the invention provides a cruise monitoring method, a cruise monitoring device, cruise monitoring equipment and a storage medium, wherein the method comprises the following steps: determining each monitored object in the monitoring range of the monitoring equipment and the sequence of monitoring each monitored object; then controlling the monitoring equipment to respectively carry out image acquisition on each monitored object according to the sequence and according to acquisition parameters corresponding to the monitored objects; therefore, the scheme can be used for carrying out image acquisition on each monitored object, meets the monitoring requirements of users on the monitored objects, and carries out image acquisition on the acquisition parameters adaptive to the monitored objects respectively aiming at each monitored object, so that the acquisition effect is better.

Description

Cruise monitoring method, device, equipment and storage medium

Technical Field

The present invention relates to the field of monitoring technologies, and in particular, to a cruise monitoring method, apparatus, device, and storage medium.

Background

In some scenarios, for example, in a security scenario or a scenario in which natural resources are supervised, some monitoring devices with a large monitoring range, such as a high altitude dome camera, are generally required to be arranged to perform cruise monitoring on the scenario. Cruise monitoring can be understood as: the various regions of the scene are monitored in turn.

In some cruise monitoring schemes at present, a plurality of preset positions are configured for a monitoring device, and the field of view ranges corresponding to the preset positions can cover a monitoring scene. Taking cruise monitoring of the dome camera as an example, the dome camera rotates to each preset position in sequence to monitor, and thus images of each area in a monitoring scene are obtained.

However, in this scheme, the monitoring device can only monitor according to the sequence of the preset bits, but cannot monitor a certain monitored object or some monitored objects in the monitoring scene, and cannot meet the monitoring requirements of the user for the monitored objects.

Disclosure of Invention

The embodiment of the invention aims to provide a cruise monitoring method, a cruise monitoring device, cruise monitoring equipment and a cruise monitoring storage medium, so as to meet monitoring requirements of a user for a monitored object.

In order to achieve the above object, an embodiment of the present invention provides a cruise monitoring method, including:

determining each monitored object in the monitoring range of the monitoring equipment;

determining the sequence of monitoring the monitored objects;

determining the current monitored object in each monitored object in sequence according to the sequence;

and controlling the monitoring equipment to acquire images of the current monitored object based on the acquisition parameters corresponding to the current monitored object, and then returning to execute the step of determining the current monitored object in each monitored object in sequence according to the sequence.

Optionally, the determining each monitored object within the monitoring range of the monitoring device includes:

determining each block target located in the monitoring range of the monitoring equipment;

and determining the block target of a preset type as a monitoring object in the monitoring range of the monitoring equipment.

Optionally, after determining each monitored object within the monitoring range of the monitoring device, the method further includes:

judging whether the monitored object meets a preset segmentation condition or not aiming at each monitored object; the preset segmentation conditions are as follows: the area is larger than a first preset threshold value, and/or the geometrical shape formed by the boundary line is irregular;

and if so, segmenting the monitoring object into a plurality of monitoring objects which do not meet the preset segmentation condition.

Optionally, the boundary line forms an irregular geometric shape, including:

in the boundary line of the monitored object, the difference value between at least two side lengths is larger than a second preset threshold value;

and/or the ratio of the area of the monitored object to the area of the reference graph of the monitored object is smaller than a third preset threshold; the reference graph is a regular graph with a preset shape, at least one vertex of the monitoring object is located on the edge of the reference graph, and other vertices of the monitoring object are located inside the reference graph.

Optionally, the determining the sequence of monitoring the monitoring objects includes:

and determining the sequence of monitoring the monitoring objects according to the distances between the monitoring objects and the monitoring equipment.

Optionally, after determining the current monitored object in the monitored objects in sequence according to the sequence, the method further includes:

and determining acquisition parameters of the monitoring equipment for acquiring images of the current monitored object based on the position relation between the current monitored object and the monitoring equipment, wherein the acquisition parameters are used as acquisition parameters corresponding to the current monitored object.

In order to achieve the above object, an embodiment of the present invention further provides a cruise monitoring apparatus, including:

the first determining module is used for determining each monitored object in the monitoring range of the monitoring equipment;

the second determining module is used for determining the sequence of monitoring the monitoring objects;

a third determining module, configured to determine, in sequence according to the sequence, a current monitored object among the monitored objects;

and the control module is used for controlling the monitoring equipment to acquire images for the current monitored object based on the acquisition parameters corresponding to the current monitored object and then triggering the third determination module.

Optionally, the first determining module is specifically configured to:

Optionally, the apparatus further comprises:

the judging module is used for judging whether the monitored object meets a preset segmentation condition or not aiming at each monitored object; the preset segmentation conditions are as follows: the area is larger than a first preset threshold value, and/or the geometrical shape formed by the boundary line is irregular; if yes, triggering a segmentation module;

and the segmentation module is used for segmenting the monitoring object into a plurality of monitoring objects which do not meet the preset segmentation condition.

Optionally, the boundary line forms an irregular geometric shape, including:

Optionally, the second determining module is specifically configured to:

Optionally, the apparatus further comprises:

and the fourth determining module is used for determining acquisition parameters of the monitoring equipment for acquiring images of the current monitored object based on the position relation between the current monitored object and the monitoring equipment, and the acquisition parameters are used as acquisition parameters corresponding to the current monitored object.

In order to achieve the above object, an embodiment of the present invention further provides an electronic device, including a processor and a memory;

a memory for storing a computer program;

and the processor is used for realizing any cruise monitoring method when executing the program stored in the memory.

To achieve the above object, an embodiment of the present invention further provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements any one of the above cruise monitoring methods.

By applying the embodiment of the invention, all the monitored objects in the monitoring range of the monitoring equipment and the sequence of monitoring all the monitored objects are determined; then controlling the monitoring equipment to respectively carry out image acquisition on each monitored object according to the sequence and according to acquisition parameters corresponding to the monitored objects; therefore, the scheme can be used for carrying out image acquisition on each monitored object, meets the monitoring requirements of users on the monitored objects, and carries out image acquisition on the acquisition parameters adaptive to the monitored objects respectively aiming at each monitored object, so that the acquisition effect is better.

Of course, not all of the advantages described above need to be achieved at the same time in the practice of any one product or method of the invention.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.

FIG. 1 is a first schematic flow chart of a cruise monitoring method according to an embodiment of the present invention;

FIG. 2 is a schematic view of a parcel with irregular boundary line geometry according to an embodiment of the present invention;

FIG. 3 is a schematic diagram illustrating a segmentation of a large-area parcel according to an embodiment of the present invention;

FIG. 4a is a schematic diagram of a segmentation of a parcel with irregular boundary line geometry according to an embodiment of the present invention;

FIG. 4b is a schematic diagram of another example of the segmentation of a parcel with irregular boundary line geometry according to the present invention;

fig. 5a is a schematic diagram of determining a monitoring sequence of a ball machine according to an embodiment of the present invention;

FIG. 5b is a schematic diagram of another method for determining a monitoring sequence of a ball machine according to an embodiment of the present invention;

fig. 6 is a schematic diagram of determining a P value of a ball machine according to an embodiment of the present invention;

fig. 7 is a schematic diagram of determining a T value of a ball machine according to an embodiment of the present invention;

FIG. 8 is a second flowchart of a cruise monitoring method according to an embodiment of the present invention;

fig. 9 is a schematic structural diagram of a cruise monitoring apparatus according to an embodiment of the present invention;

fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to achieve the above object, embodiments of the present invention provide a cruise monitoring method, apparatus, device and storage medium, where the method and apparatus may be applied to various electronic devices, such as monitoring devices like a ball machine and a snapshot machine, or data processing devices connected to the monitoring devices, such as a server, and the specific type of the electronic devices is not limited.

Fig. 1 is a first flowchart of a cruise monitoring method according to an embodiment of the present invention, including:

s101: and determining each monitored object in the monitoring range of the monitoring equipment.

For example, if the execution subject is a monitoring device, the monitoring device in this embodiment may be the execution subject itself. If the execution main body is a data processing device connected to the monitoring device, the monitoring device in this embodiment refers to: the same monitoring device is connected with the data processing device.

In one embodiment, the position information of each block target in the monitoring scene and the position information of the monitoring device may be obtained; in this embodiment, S101 may include: calculating the monitoring range of the monitoring equipment according to the position information of the monitoring equipment; and determining the block target positioned in the monitoring range according to the position information of each block target, and using the block target as each monitoring object in the monitoring range of the monitoring equipment.

For example, the position information in the present embodiment may be geographic coordinates, such as GPS (Global Positioning System) coordinates, or may also be projection coordinates, and the specific coordinate type is not limited. However, when comparing the position information of both the block target and the monitoring device, it is necessary to convert both into the same coordinate System, such as WGS-84(World Geodetic System-1984, World Geodetic System 1984) geographic coordinate System and WGS-84 projection coordinate System (e.g., 900913 google coordinate System), and the specific coordinate System is not limited.

For example, assuming that the monitoring scene is a scene for monitoring natural resources, the block target may be a parcel, and the position information of each parcel in the scene may be collected through some public data or through calibration, and the position information of the monitoring device may be obtained through calibration. For example, a remote sensing image acquired by a national resource department or a vector geographic information data set obtained by calibration aiming at a region, a plot and the like can be acquired.

As another example, assuming that the monitoring scene is a security scene, the block targets may be residential areas, squares, parks, office buildings, and the like, the position information of each block target in the scene may be collected through some public data or through calibration, and the position information of the monitoring device may be obtained through calibration.

In one case, the monitoring range may be a circular area. Assuming that the monitoring radius of the monitoring device is R, a circular area can be determined by taking the position of the monitoring device as the center of a circle and taking R as the radius, and the circular area can be used as the monitoring range of the monitoring device. The specific R value may be determined according to hardware parameters of the monitoring device. The shape of the monitoring range is not limited, and may be rectangular, oval, or the like. Alternatively, in other cases, the monitoring range of the monitoring device may be manually defined.

In this embodiment, the comparison of the position information determines whether the tile target is located in the monitoring range. Therefore, the monitored object can be determined only by simple comparison of the position coordinates, and the process is simple, convenient and efficient. Or in another embodiment, whether the block target is located in the monitoring range can be judged through image recognition. For example, an image of a monitored scene may be acquired, a monitoring range of a monitoring device may be determined in the image, and a block object located in the monitoring range may be identified. The image may be acquired by the monitoring device in the embodiment of the present invention, or may be acquired by other monitoring devices, which is not limited specifically. The embodiment has better intuition of the monitored object, the image can truly reflect the actual situation of the monitored scene, and the accuracy of the monitored object is higher.

In one embodiment, the type of each tile object in the monitoring scene may be predetermined. In the embodiment, each block target located in the monitoring range of the monitoring device is determined; and determining the block target of a preset type as a monitoring object in the monitoring range of the monitoring equipment.

For example, assuming that the monitoring scenario is a scenario for supervising natural resources, the tile target may be a parcel, and the type of the tile target may include: urban planning land, hospital land, farmland, woodland, etc., are not listed. In one case, the type of the block target may refer to the classification of national land by the national resource department, such as farmland, forest land, civil building land, and the like. As another example, assuming the monitoring scenario is a security scenario, the type of the tile object may include: residential areas, squares, parks, office buildings, etc., to name but a few.

In the embodiment, the type of the monitoring object needing to be subjected to cruise monitoring can be predetermined and used as the type to be matched; and judging whether the type of the candidate monitoring object is matched with the type to be matched or not aiming at each candidate monitoring object, and if so, determining the candidate monitoring object as the monitoring object. In this way, the cruise monitoring can be performed only for one or more specific types of block targets, that is, block targets of other types (types that are not important or do not need attention) can be filtered out, in other words, cruise monitoring is not performed for block targets of other types (types that are not important or do not need attention), so that monitoring resources, computing resources, storage resources and the like are saved.

In one embodiment, after S101, for each monitored object, whether the monitored object meets a preset segmentation condition may be determined; the preset segmentation conditions are as follows: the area is larger than a first preset threshold value, and/or the geometrical shape formed by the boundary line is irregular; and if so, segmenting the monitoring object into a plurality of monitoring objects which do not meet the preset segmentation condition.

For example, in one case, if a certain monitored object has a large area, the monitored object may be divided into a plurality of monitored objects, and each of the divided monitored objects is subjected to image acquisition. A threshold may be set for the area of the monitored object, and for distinguishing descriptions, the threshold is referred to as a first preset threshold, and the first preset threshold may be set according to an actual situation, and is not limited specifically. And if the area of a certain monitoring object is larger than a first preset threshold value, the monitoring object is segmented, and the area of each segmented monitoring object is smaller than the first preset threshold value. The specific segmentation method is not limited, for example, the new monitoring objects with the area not greater than the first preset threshold may be equally divided, or may be sequentially intercepted from the original monitoring objects (the monitoring objects to be segmented) until the remaining area of the original monitoring objects is not greater than the first preset threshold. Under the condition, the monitoring object with a large area is divided into a plurality of monitoring objects to be respectively subjected to image acquisition, so that the whole and the details can be considered, and the acquisition effect is good.

Alternatively, if the boundary line of a monitoring object has an irregular geometric shape, the monitoring object may be divided into a plurality of monitoring objects, and the geometric shape formed by the boundary line of each divided monitoring object is regular.

For example, various common geometric shapes such as rectangles, parallelograms, circles, ellipses, sectors, triangles, equilateral hexagons, pentagons, and the like can be understood as regular geometric shapes.

Each vertex in the boundary of the monitored object can be identified, and the adjacent vertexes are sequentially connected according to a preset sequence to obtain the boundary line of the monitored object. In one case, the vertices with the shorter distance may be clustered, and then the vertices after each cluster are connected in sequence according to a preset sequence to obtain the boundary line of the monitored object, so that the obtained boundary line is more regular. Alternatively, after the boundary line of the monitored object is obtained, the boundary line may be subjected to regular fitting, and the boundary line after regular fitting is also more regular. For example, the boundary line of the monitored object is shaped like a rectangle, and the boundary line is subjected to regular fitting, so that the boundary line after regular fitting is a rectangle. For another example, the boundary line of the monitored object is shaped like a circle, and the boundary line is subjected to regular fitting, so that the boundary line after the regular fitting is a circle.

For example, the boundary line may form an irregular geometric shape, which may include: in the boundary line of the monitored object, the difference value between at least two side lengths is larger than a second preset threshold value; and/or the ratio of the area of the monitored object to the area of the reference graph of the monitored object is smaller than a third preset threshold; the reference graph is a regular graph with a preset shape, at least one vertex of the monitoring object is positioned on the edge of the reference graph, and other vertices of the monitoring object are positioned in the reference graph, in other words, the monitoring object is positioned in the reference graph of the monitoring object.

The two cases of geometric irregularities are described below:

if the side lengths of the boundary lines of the monitored objects have more difference, the geometric shape formed by the boundary lines of the monitored objects can be considered to be irregular, the monitored objects can be divided into a plurality of monitored objects, and image acquisition is carried out on each of the monitored objects obtained by dividing the monitored objects. A threshold may be set for a difference between side lengths in a boundary line of the monitored object, and for distinguishing descriptions, the threshold is referred to as a second preset threshold, and the second preset threshold may be set according to an actual situation, and is not limited specifically. And if the length difference value of two sides in the boundary line of the monitored object is greater than a second preset threshold value, the monitored object is divided, and the difference value between the side lengths of the boundary line of the divided monitored object is smaller than the second preset threshold value. The specific division method is not limited, and for example, the side with the largest length may be divided.

If the ratio of the area of the monitored object to the area of the reference pattern of the monitored object is smaller than a third preset threshold, the geometric shape formed by the boundary line of the monitored object can be considered to be irregular, the monitored object can be divided into a plurality of monitored objects, and image acquisition is performed on each of the monitored objects obtained by dividing the monitored object.

The reference graph of the monitored object is a regular graph with a preset shape, such as a circumscribed rectangle of the monitored object, a circumscribed circle of the monitored object, a circumscribed ellipse of the monitored object, and the like, and the specific shape can be set according to the actual situation. Alternatively, in one case, the reference pattern may be the same as the shape of the monitoring screen of the monitoring device, the shape of the monitoring screen is usually a rectangle with a fixed aspect ratio, the shape of some panoramic monitoring screens is an ellipse, and the like, which are not listed. In this case, the ratio of the area of the monitoring object to the area of the reference pattern of the monitoring object can be analogized as: and when the monitoring picture just contains the whole monitoring object, the effective picture proportion of the monitoring object in the monitoring picture.

If the effective picture proportion is smaller, when the monitored object is subjected to image acquisition, the whole and the details are not easily considered. Referring to fig. 2, it is assumed that the monitored image is a rectangle with a fixed aspect ratio, the reference image is a rectangle with a fixed aspect ratio, the aspect ratio of the reference image is the same as the aspect ratio of the monitored image, some vertices of the monitored object are located on the side of the reference image, and other vertices of the monitored object are all located inside the reference image, in fig. 2, the ratio of the area of the monitored object to the area of the reference image is small, or the monitored object occupies a small part of the reference image. This means that when the image of the monitored object is collected, if the whole appearance of the monitored object needs to be collected, the monitored image is filled with more invalid information and cannot reflect the details of the monitored object; and if the details of the monitored object need to be reflected, the monitoring picture cannot contain the full picture of the monitored object. In this case, the monitoring object is divided into a plurality of monitoring objects, and each divided monitoring object is subjected to image acquisition, so that the whole and the details can be considered, and the acquisition effect is good.

Alternatively, in still another case, the division condition includes: and under the condition I, the area is larger than a first preset threshold, and under the condition II, the geometric shape formed by the boundary line is irregular. If a certain monitored object meets the two segmentation conditions at the same time, the monitored object is segmented, and each monitored object obtained after segmentation does not meet the two segmentation conditions at the same time.

For example, taking the monitored object as a land parcel, the area and boundary line of each land parcel in the scene can be determined through some public data or through calibration. Alternatively, in some cases, a conversion relationship between the image coordinate system and the geographic coordinate system or the projection coordinate system may be obtained by calibration, and based on the conversion relationship, the area and the boundary line of each land may be determined in the image. For example, the image coordinate system may be a visible pixel coordinate system, that is, a coordinate system constructed for imaging pixels in the visible range of the dome camera.

Referring to fig. 3, assuming that the area of the plot a is greater than a first preset threshold, the plot a is divided into a plot a1, a plot a2 and a plot A3, and the areas of the plot a1, the plot a2 and the plot A3 are not greater than the first preset threshold. The plot a1, the plot a2 and the plot A3 are used as three different monitoring objects, and then the three plots are respectively subjected to image acquisition. Compared with the whole image of the plot A, the image acquisition method and the image acquisition device have the advantages that the images of the plot A1, the plot A2 and the plot A3 are acquired respectively, the images can reflect more details of the plot, and the acquisition effect is better.

Referring to fig. 4a, the shape of the parcel B is irregular, each vertex in the boundary line of the parcel B is identified, and each adjacent vertex is sequentially connected according to a preset sequence (such as a clockwise sequence or a counterclockwise sequence), so as to obtain the boundary line of the monitored object. The vertex W and the vertex X form a side length 1, the vertex Y and the vertex Z form a side length 2, and the length difference value between the side length 1 and the side length 2 is larger than a second preset threshold value. The land parcel B is divided, and can be divided according to the side length 1 to obtain two land parcels B1 and B2. And subsequently, respectively carrying out image acquisition on the two land parcels. Compared with the method for acquiring the whole image of the land parcel B, the method for acquiring the image of the land parcel B1 and the image of the land parcel B2 are acquired respectively, the images can reflect more details of the land parcel, and the acquisition effect is better.

Referring to fig. 4b, the shape of the parcel C is irregular, identifying the respective vertices in the boundary lines of the parcel C: the vertex K1, the vertex K2, the vertex K3, the vertex K4, the vertex K5, the vertex K6, and the vertex K7 are sequentially connected with each other according to a preset sequence (such as a clockwise sequence or a counterclockwise sequence), so as to obtain a boundary line of the monitored object. The ratio of the area of the plot C to the area of the reference pattern (rectangle with preset aspect ratio) of the plot C is smaller than a third preset threshold, and the ratio of the area of the plot C into the plots C1, C2, C3, C1, C2, C3 and the area of the reference pattern (rectangle with preset aspect ratio) is smaller than the third preset threshold. And subsequently, respectively carrying out image acquisition on the three plots. Compared with the whole image of the collected plot C, the image collection method has the advantages that the images of the plots C1 and the plots C2 and the images of the plots C3 are collected respectively, the images can reflect more details of the plots, and the collection effect is better.

The positions of the monitoring devices in fig. 3, 4a and 4b are merely illustrative and are not limited, for example, the monitoring device may be located at the center of the monitoring range, and the specific position is not limited.

S102: and determining the sequence of monitoring each monitored object.

For example, in one embodiment, the monitored objects may be randomly ordered.

Or, in another embodiment, the order of monitoring the monitoring objects may be determined according to the distances between the monitoring objects and the monitoring device. For example, the distance is the smallest, the higher the ranking, or the distance is the larger, the higher the ranking, and the specific ranking is not limited.

Or, in another embodiment, the monitoring device is a ball machine, and the initial field range and the rotation direction of the ball machine can be determined; and determining the sequence of monitoring the monitored objects based on the initial field range and the rotation direction.

Referring to fig. 5a, assuming that a monitoring object C exists in an initial field range of the dome camera, assuming that the dome camera rotates clockwise, and a monitoring object D, a monitoring object E, and the like are sequentially collected, the order of monitoring each monitoring object is determined as follows: monitored object C, monitored object D and monitored object E. Therefore, the purpose of cruise monitoring of all monitored objects can be achieved under the condition that the rotation of the ball machine is the least.

As another example, assume that, as shown in fig. 5b, a monitoring object C and a monitoring object D exist in the initial field range of the dome camera, assume that the dome camera rotates clockwise, a monitoring object E and a monitoring object F exist in the field range of one rotation, a monitoring object G and a monitoring object H exist in the field range of two rotations, and so on. In this case, a plurality of monitoring objects exist in the same field range, and for each monitoring object in the same field range, the sequence of monitoring the monitoring objects can be randomly determined, or the sequence of monitoring the monitoring objects can be determined according to the distance between the monitoring object and the ball machine. For example, the smaller the distance, the earlier the sequence, or the larger the distance, the earlier the sequence, and the specific sequence is not limited. If the distance is smaller and the sequence is closer to the front, the sequence of monitoring each monitored object is determined as follows: monitoring object C, monitoring object D, monitoring object E, monitoring object F, monitoring object G and monitoring object H.

Therefore, by the aid of the method and the device, the rotating path of the dome camera is reasonable, and cruise monitoring of each monitored object can be achieved through small rotation.

In one case, a monitoring object list may be generated, where the list includes information of each monitoring object determined in S101 and a sequence of monitoring the monitoring objects. The information of the monitoring object may include: the identifier of the monitored object, the location information of the monitored object, and the like, which are not limited specifically. Cruise monitoring can then be performed based on the list. In this case, the monitored object list may also be displayed to the user, and the user further screens the monitored objects that need to be subjected to cruise monitoring, or the user may also adjust the monitoring order (the order of monitoring the monitored objects), so that the user experience is better.

S103: and determining the current monitored object in each monitored object in sequence according to the sequence.

In this embodiment, image acquisition is performed on each monitored object in turn according to the sequence determined in S102, that is, cruise monitoring is performed. And the targeted monitoring object is the current monitoring object when image acquisition is carried out each time.

In one case, a cruise monitoring scheme can be triggered at intervals, image acquisition is sequentially carried out on each monitored object in the cruise monitoring scheme, and cruise monitoring is stopped after the image acquisition is finished. And triggering the cruise monitoring scheme again until the next time period is reached. The specific time interval is not limited, for example, it may be one hour, one day, etc., and is not limited specifically.

Or, in another case, the sequence determined in S102 may be understood as a cyclic sequence, and the next monitoring object of the last monitoring object is the first monitoring object, so that the cruise monitoring can be performed continuously and uninterruptedly.

Or, in another case, a more complex cruising period may be set, for example, cruising N times per day, where N represents a positive integer, and each monitored object is sequentially subjected to image acquisition once each time cruising. The cruise cycle may be set according to actual conditions, and is not particularly limited.

If the monitoring device is a ball machine or other movable image acquisition devices, the initial positions of the monitoring device in each cruise monitoring scheme execution can be the same or different, and are not limited specifically.

For example, the monitoring object in the present embodiment may be a fixed monitoring object, such as a land, a park, a residential area, and the like in the above example.

S104: and controlling the monitoring equipment to acquire images of the current monitored object based on the acquisition parameters corresponding to the current monitored object, and then returning to execute S103.

As described above, in one case, the cruise monitoring scheme may be triggered at intervals. In this case, if image acquisition is performed on each monitored object in sequence, the step is no longer executed to return to step S103, or after the step is executed to step S103, the current monitored object cannot be determined in sequence, and the execution of the flowchart shown in fig. 1 is finished. Until the next time period is reached, when the cruise monitoring scheme is triggered again, the flowchart shown in fig. 1 may be executed again, or if the monitored object is not changed, the cruise monitoring scheme may be executed from S103. In another case, the sequence determined in S102 may be understood as a loop sequence, and the next monitored object of the last monitored object is the first monitored object, in which case, the flowchart shown in fig. 1 may loop all the time, and cruise monitoring may be performed continuously and uninterruptedly.

In one case, the current monitored object is subjected to image acquisition, a plurality of images can be captured, the number of captured images can be preset, or the number of captured images can be random, and the specific number is not limited. And after the snapshot is finished, returning to the step S103, and re-determining the current monitored object. Or in another case, the image of the current monitored object is acquired, or a video image of a certain time period is recorded, the recording time length can be preset, and the specific time length is not limited. And after the recording is finished, returning to the step S103, and re-determining the current monitoring object.

The acquisition parameters corresponding to the current monitored object can be understood as follows: adapted to the acquisition parameters of the currently monitored object. As described above, the monitoring object in this embodiment may be a fixed monitoring object, and thus, the acquisition parameter corresponding to the monitoring object may also be fixed, and therefore, in an implementation, the acquisition parameter corresponding to each monitoring object may be preset.

Or, in another embodiment, after S103, based on the position relationship between the current monitored object and the monitoring device, an acquisition parameter for the monitoring device to acquire an image of the current monitored object is determined, and the acquisition parameter is used as the acquisition parameter corresponding to the current monitored object.

For example, the position information of the monitoring object may be collected through some public data or through calibration, and the position information of the monitoring device may be obtained through calibration. Thus, the position relation between the current monitoring object and the monitoring equipment can be determined. The positional relationship may include: horizontal distance (projected distance to horizontal ground), vertical distance (height difference), and the like.

In one embodiment, the monitoring device is a dome camera, the collecting parameters may include a PTZ value (Pan/Tilt/Zoom, PT represents Pan/Tilt/Zoom, and Z represents Zoom, Zoom control) of the dome camera, and S104 may include: calculating the PT value of the dome camera according to the position information of the current monitored object and the position information of the dome camera; and determining the Z value of the ball machine meeting the preset focusing condition under the condition that the ball machine aims at the current monitored object based on the PT value.

The P-value of the ball machine can be understood as the angle of the ball machine in the horizontal direction, or as the azimuth angle. Referring to fig. 6, fig. 6 is a top view of a dome camera, and according to a horizontal included angle between a connection line between the dome camera and a current monitored object and a designated direction (such as due north), an angle of the dome camera in the horizontal direction can be determined, and a P value of the dome camera is obtained.

The T value of a ball machine can be understood as the angle of the ball machine in the vertical direction (height direction), or as the pitch angle. Referring to fig. 7, according to the horizontal distance and the vertical distance between the current monitored object and the dome camera, the T value of the dome camera can be calculated: tan ═ horizontal distance/vertical distance.

The Z value of the ball machine can be understood as the focal length parameter of the ball machine, and in one embodiment, the preset focusing condition is: and the picture proportion of the monitored object in the image collected by the ball machine reaches a third preset threshold value. The third preset threshold may be set according to practical situations, such as 1/5, 1/3, etc., and the specific value is not limited. Assuming that the third preset threshold is 1/5, when the image of the current monitored object is acquired by using the calculated PT value, the Z value of the dome camera is adjusted until the focusing condition is reached when the current monitored object occupies 1/5 of the screen, and the image is acquired.

In another embodiment, the preset focusing condition is: and the picture proportion of the monitored object in the image acquired by the ball machine reaches a third preset threshold, and the monitored object is positioned in the picture center of the image.

When the ball machine is aligned with the current monitoring object based on the calculated PT value, the current monitoring object is generally located at the center of the picture of the ball machine, under some conditions, if the current monitoring object is not located at the center of the picture of the ball machine due to some errors, the PT value can be finely adjusted, so that the current monitoring object is located at the center of the picture of the ball machine.

For example, the null degree of the azimuth angle (P value) and the null degree of the pitch angle (T value) of the dome camera may be corrected in advance to improve the acquisition accuracy.

After acquiring the image of the current monitored object, AI (Artificial Intelligence) recognition may be performed on the image, for example, to recognize an abnormal event or an abnormal object in the image, or to recognize a desired event or a desired object in the image, where a specific AI recognition algorithm is not limited. The identified event or object can be archived and archive managed, the archive can include the attribute information of the event or object, and the specific archive content is not limited.

In the embodiment of the invention, the image acquisition is carried out on each monitored object by the acquisition parameters adapted to the monitored object, so as to obtain the image with higher quality, and the AI identification is carried out on the image, so that the identification effect is better.

By applying the embodiment shown in fig. 1 of the present invention, each monitored object in the monitoring range of the monitoring device and the sequence of monitoring each monitored object are determined; then controlling the monitoring equipment to respectively carry out image acquisition on each monitored object according to the sequence and according to acquisition parameters corresponding to the monitored objects; therefore, on the first aspect, the scheme can be used for carrying out image acquisition on each monitored object, the monitoring requirements of users on the monitored objects are met, and image acquisition is carried out on the acquisition parameters which are adapted to the monitored objects respectively on each monitored object, so that the acquisition effect is better.

In the second aspect, in the related cruise monitoring scheme, a plurality of preset positions are configured for the dome camera, and the dome camera rotates to each preset position in sequence to monitor, so that images of each area in a monitored scene are obtained. In some cases, the field ranges corresponding to the preset positions may overlap, and in this case, some monitored objects may be repeatedly monitored, which wastes monitoring resources. Or in other cases, the field of view ranges corresponding to the preset bits cannot completely cover the monitored scene, in which case, some monitored objects may be omitted, and the monitoring effect is poor.

In the embodiment of the invention, the monitoring objects in the monitoring range are sequentially monitored in sequence, so that the situations of repeated monitoring and monitoring object omission are reduced, the monitoring resources are saved, and the monitoring effect is better.

In a third aspect, in the above related solution, a plurality of monitored objects may exist in the field of view corresponding to each preset position, so that the acquired image includes a plurality of monitored objects at the same time, and the monitored objects may interfere with each other. In the embodiment of the invention, the image acquisition is respectively carried out on each monitored object, and the acquired image only comprises one monitored object, so that the interference of other monitored objects is reduced.

In a fourth aspect, in some monitoring scenes with a large area, if the above-mentioned related scheme is adopted, dozens or even hundreds of preset bits need to be manually configured, which consumes much labor. In the embodiment of the invention, manual configuration and manual control of monitoring equipment are not needed, so that automatic cruise monitoring is realized, and labor is saved.

Fig. 8 is a schematic flowchart of a cruise monitoring method according to an embodiment of the present invention, including:

s801: acquiring position information of each block target in a monitoring scene and position information of a dome camera; and determines the type of each tile object.

For example, the position information in the present embodiment may be geographic coordinates, such as GPS (Global Positioning System) coordinates, or may also be projection coordinates, and the specific coordinate type is not limited. However, when comparing the position information of both the tile target and the dome camera, it is necessary to convert the two into the same coordinate System, such as WGS-84(World Geodetic System-1984, World Geodetic System 1984) geographic coordinate System and WGS-84 projection coordinate System (e.g., 900913 google coordinate System), and the specific coordinate System is not limited.

For example, assuming that the monitoring scenario is a scenario for supervising natural resources, the tile target may be a parcel, and the type of the tile target may include: urban planning land, hospital land, farmland, woodland, etc., are not listed. In one case, the type of the block target may refer to the classification of national land by the national resource department, such as farmland, forest land, civil building land, and the like. The position information and the type of each land in the scene can be collected through some public data or through calibration, and the position information of the dome camera can be obtained through calibration. For example, a remote sensing image acquired by a national resource department or a vector geographic information data set obtained by calibration for a region, a plot or the like can be acquired.

As another example, assuming the monitoring scenario is a security scenario, the type of the tile object may include: the position information and the type of each block target in the scene can be collected through some public data or calibration, and the position information of the dome camera can be obtained through calibration.

S802: and calculating the monitoring range of the ball machine according to the position information of the ball machine.

In one case, the monitoring range may be a circular area. Assuming that the monitoring radius of the ball machine is R, a circular area can be determined by taking the position of the ball machine as the center of a circle and taking R as the radius, and the circular area can be used as the monitoring range of the ball machine. The specific R value can be determined according to the hardware parameters of the dome camera. The shape of the monitoring range is not limited, and may be rectangular, oval, or the like.

S803: and determining the block target positioned in the monitoring range as a candidate monitoring object according to the position information of each block target.

S804: and determining the candidate monitoring object of the preset type as the monitoring object in the monitoring range of the monitoring equipment.

In the embodiment shown in fig. 8, the type of the monitoring object that needs to be subjected to cruise monitoring may be determined in advance as the type to be matched; and judging whether the type of the candidate monitoring object is matched with the type to be matched or not aiming at each candidate monitoring object, and if so, determining the candidate monitoring object as the monitoring object. In this way, the cruise monitoring can be performed only for one or more specific types of block targets, that is, block targets of other types (types that are not important or do not need attention) can be filtered out, in other words, cruise monitoring is not performed for block targets of other types (types that are not important or do not need attention), so that monitoring resources, computing resources, storage resources and the like are saved.

S805: judging whether the monitored object meets a preset segmentation condition or not aiming at each monitored object; if yes, S806 is executed, and if none is satisfied, S807 is directly executed.

S806: and dividing the monitoring object into a plurality of monitoring objects which do not meet preset dividing conditions.

The preset segmentation conditions are as follows: the area is greater than a first predetermined threshold and/or the boundary line forms an irregular geometry.

The two cases of geometric irregularities are described below:

For example, taking the monitored object as a land parcel, the area and boundary line of each land parcel in the scene can be determined through some public data or through calibration. Alternatively, in some cases, a conversion relationship between the image coordinate system and the geographic coordinate system or the projection coordinate system may be obtained by calibration, and based on the conversion relationship, the area and the boundary line of each land may be determined in the image.

S807: and determining the sequence of monitoring each monitored object based on the initial field range and the rotation direction of the dome camera.

As another example, assume that, as shown in fig. 5b, a monitoring object C and a monitoring object D exist in the initial field range of the dome camera, assume that the dome camera rotates clockwise, a monitoring object E and a monitoring object F exist in the field range of one rotation, a monitoring object G and a monitoring object H exist in the field range of two rotations, and so on. In this case, a plurality of monitoring objects exist in the same field range, and for each monitoring object in the same field range, the sequence of monitoring the monitoring objects can be randomly determined, or the sequence of monitoring the monitoring objects can be determined according to the distance between the monitoring object and the ball machine. For example, the distance is the smallest, the higher the ranking, or the distance is the larger, the higher the ranking, and the specific ranking is not limited. If the distance is the smallest and the sequencing is more advanced, the sequence of monitoring each monitored object is determined as follows: monitoring object C, monitoring object D, monitoring object E, monitoring object F, monitoring object G and monitoring object H.

Therefore, by applying the embodiment, the rotation path of the ball machine is reasonable, and cruise monitoring of each monitored object can be realized through smaller rotation.

S808: and determining the current monitored object in each monitored object in sequence according to the sequence.

In this embodiment, image acquisition is performed on each monitored object in turn according to the sequence determined in S807, that is, cruise monitoring is performed. And the targeted monitoring object is the current monitoring object when image acquisition is carried out each time.

Alternatively, the sequence determined in S807 may be understood as a cyclic sequence, and the monitoring object next to the last monitoring object is the first monitoring object, so that the cruise monitoring may be performed continuously and uninterruptedly.

The initial positions of the dome camera each time the cruise monitoring scheme is executed may be the same or may be different, and are not particularly limited.

S809: and calculating the PT value of the dome camera according to the position information of the current monitored object and the position information of the dome camera.

S810: and determining the Z value of the ball machine meeting the preset focusing condition under the condition that the ball machine aims at the current monitored object based on the PT value.

For example, the position information of the monitored object may be collected through some public data or through calibration, and the position information of the ball machine may be obtained through calibration. Thus, the position relation between the current monitoring object and the ball machine can be determined. The positional relationship may include: horizontal distance (projected distance to horizontal ground), vertical distance (height difference), and the like. The zero degree of the azimuth angle (P value) and the zero degree of the pitch angle (T value) of the dome camera can be corrected in advance to improve the acquisition precision.

S811: based on the PTZ value, the control ball machine performs image acquisition for the current monitored object, and then returns to S808.

In one case, the cruise monitoring scheme may be triggered at intervals. In this case, if image acquisition is performed on each monitored object in sequence, the step is not performed again in S808, or after the step is performed in S808, the current monitored object cannot be determined according to the sequence, and the execution of the flowchart shown in fig. 8 is finished. Until the next time period is reached, when the cruise monitoring scheme is triggered again, the flowchart shown in fig. 8 may be executed again, or if the monitored object is not changed, the cruise monitoring scheme may be executed from S808. In another case, the sequence determined in S807 may be understood as a loop sequence, and the monitored object next to the last monitored object is the first monitored object, in which case, the flowchart shown in fig. 8 may loop all the time, and cruise monitoring may be performed continuously and uninterruptedly.

In one case, the current monitored object is subjected to image acquisition, a plurality of images can be captured, the number of captured images can be preset, or the number of captured images can be random, and the specific number is not limited. And after the snapshot is finished, returning to the step S808, and re-determining the current monitored object. Or in another case, the image of the current monitored object is acquired, or a video image of a certain time period is recorded, the recording time length can be preset, and the specific time length is not limited. And after the recording is finished, returning to the step S808, and re-determining the current monitoring object.

By applying the embodiment shown in fig. 8 of the present invention, each monitored object in the monitoring range of the monitoring device and the sequence of monitoring each monitored object are determined; then controlling the monitoring equipment to respectively carry out image acquisition on each monitored object according to the sequence and according to acquisition parameters corresponding to the monitored objects; therefore, on the first aspect, the scheme can be used for carrying out image acquisition on each monitored object, the monitoring requirements of users on the monitored objects are met, and image acquisition is carried out on the acquisition parameters which are adapted to the monitored objects respectively on each monitored object, so that the acquisition effect is better.

The steps in the above method embodiments may be executed in a logical order, and the step numbers or the order of the steps are not limited to the execution order of the steps.

Corresponding to the above method embodiment, an embodiment of the present invention further provides a cruise monitoring apparatus, as shown in fig. 9, including:

a first determining module 901, configured to determine each monitored object in a monitoring range of a monitoring device;

a second determining module 902, configured to determine a sequence of monitoring the monitoring objects;

a third determining module 903, configured to determine, in sequence according to the sequence, a current monitored object in the monitored objects;

a control module 904, configured to control the monitoring device to perform image acquisition on the current monitored object based on the acquisition parameter corresponding to the current monitored object, and then trigger the third determining module 903.

In one embodiment, the first determining module 901 is specifically configured to: determining each block target located in the monitoring range of the monitoring equipment; and determining the block target of a preset type as a monitoring object in the monitoring range of the monitoring equipment.

In one embodiment, the apparatus further comprises: a decision module and a segmentation module (not shown), wherein,

the judging module is used for judging whether each monitored object meets a preset segmentation condition or not; the preset segmentation conditions are as follows: the area is larger than a first preset threshold value, and/or the geometrical shape formed by the boundary line is irregular; if yes, triggering a segmentation module;

In one embodiment, the boundary line forms an irregular geometric shape, comprising:

In an embodiment, the second determining module 902 is specifically configured to:

In one embodiment, the apparatus further comprises: a fourth determining module (not shown in the figure), configured to determine, based on a position relationship between the current monitored object and the monitoring device, an acquisition parameter for the monitoring device to perform image acquisition on the current monitored object, where the acquisition parameter is used as an acquisition parameter corresponding to the current monitored object.

By applying the embodiment shown in fig. 9 of the present invention, each monitored object in the monitoring range of the monitoring device and the sequence of monitoring each monitored object are determined; then controlling the monitoring equipment to respectively carry out image acquisition on each monitored object according to the sequence and according to acquisition parameters corresponding to the monitored objects; therefore, on the first aspect, the scheme can be used for carrying out image acquisition on each monitored object, the monitoring requirements of users on the monitored objects are met, and image acquisition is carried out on the acquisition parameters which are adapted to the monitored objects respectively on each monitored object, so that the acquisition effect is better.

An embodiment of the present invention further provides an electronic device, as shown in fig. 10, including a processor 1001 and a memory 1002,

a memory 1002 for storing a computer program;

the processor 1001 is configured to implement any one of the cruise monitoring methods described above when executing the program stored in the memory 1002.

The electronic device may be a monitoring device such as a dome camera or a snapshot machine, or a data processing device connected to the monitoring device, such as a server, and the specific type of the electronic device is not limited.

The Memory mentioned in the above electronic device may include a Random Access Memory (RAM) or a Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the processor.

The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), and the like; but also Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components.

In yet another embodiment of the present invention, a computer-readable storage medium is further provided, in which a computer program is stored, and the computer program, when executed by a processor, implements any one of the cruise monitoring methods described above.

In yet another embodiment, a computer program product containing instructions is provided, which when run on a computer, causes the computer to perform any one of the cruise monitoring methods described in the previous embodiments.

In the above embodiments, the implementation may be wholly or partially realized by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the invention to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored in a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website site, computer, server, or data center to another website site, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., floppy Disk, hard Disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., Solid State Disk (SSD)), among others.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.

All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, apparatus embodiments, device embodiments, computer-readable storage medium embodiments, and computer program product embodiments are described for simplicity as they are substantially similar to method embodiments, where relevant, reference may be made to some descriptions of method embodiments.

The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.

Claims

1. A cruise monitoring method, comprising:

if yes, the monitoring object is divided into a plurality of monitoring objects which do not meet the preset dividing conditions;

determining the sequence of monitoring the monitored objects;

2. The method of claim 1, wherein the determining each monitored object within the monitoring range of the monitoring device comprises:

3. The method according to claim 1, wherein the determining the monitoring sequence of the monitoring objects comprises:

4. A cruise monitoring device, comprising:

the segmentation module is used for segmenting the monitoring object into a plurality of monitoring objects which do not meet the preset segmentation condition;

5. The apparatus of claim 4, wherein the first determining module is specifically configured to:

6. The apparatus of claim 4, wherein the second determining module is specifically configured to:

7. An electronic device comprising a processor and a memory;

a memory for storing a computer program;

a processor for implementing the method steps of any of claims 1 to 3 when executing a program stored in the memory.

8. A computer-readable storage medium, characterized in that a computer program is stored in the computer-readable storage medium, which computer program, when being executed by a processor, carries out the method steps of any one of the claims 1-3.