CN110969743A - Person retention detection method and device, electronic device and readable storage medium - Google Patents
Person retention detection method and device, electronic device and readable storage medium Download PDFInfo
- Publication number
- CN110969743A CN110969743A CN201811125902.2A CN201811125902A CN110969743A CN 110969743 A CN110969743 A CN 110969743A CN 201811125902 A CN201811125902 A CN 201811125902A CN 110969743 A CN110969743 A CN 110969743A
- Authority
- CN
- China
- Prior art keywords
- target
- detained
- monitoring point
- personnel
- face model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Time Recorders, Dirve Recorders, Access Control (AREA)
- Image Analysis (AREA)
Abstract
The application provides a method and a device for detecting the retention of people, an electronic device and a readable storage medium, wherein the method comprises the following steps: modeling a target face picture captured by a target capturing machine to obtain a target face model; inquiring information of detained personnel according to the target face model; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is reduced; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, determining that the number of the detained personnel is unchanged; and determining that the number of retained people is increased when no target retained people matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an entrance monitoring point. The method can improve the statistical accuracy of the detained personnel.
Description
Technical Field
The present disclosure relates to video surveillance technologies, and in particular, to a method and an apparatus for detecting people staying in a room, an electronic device and a readable storage medium.
Background
With the development of video monitoring technology, the application of the video monitoring technology is more and more extensive.
The detection of the retention of people in dangerous areas (such as complex mountainous areas) belongs to a typical application of video monitoring technology, and the implementation scheme mainly comprises the following steps: the method comprises the steps that a snapshot machine (which can be respectively called an entrance snapshot machine and an exit snapshot machine) is respectively arranged at an entrance and an exit of a dangerous area, and the pictures of people snapshot by the entrance snapshot machine and the exit snapshot machine are compared to determine the staying people in the dangerous area.
However, practice shows that in the existing personnel retention detection scheme, for personnel pictures captured by a capturing machine, an effective means is lacked to determine whether a plurality of personnel pictures correspond to the same personnel, so that the statistical accuracy of the number of retained personnel is poor.
Disclosure of Invention
In view of the above, the present application provides a method and an apparatus for detecting people staying in a room, an electronic device and a readable storage medium.
Specifically, the method is realized through the following technical scheme:
according to a first aspect of embodiments of the present application, there is provided a person retention detection method, including:
modeling a target face picture captured by a target capturing machine to obtain a target face model;
inquiring information of detained personnel according to the target face model;
when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is reduced;
when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, determining that the number of the detained personnel is unchanged;
and determining that the number of retained people is increased when no target retained people matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an entrance monitoring point.
According to a second aspect of embodiments of the present application, there is provided a people retention detection apparatus comprising:
the receiving unit is used for receiving a target face picture captured by the target capturing machine;
the modeling unit is used for modeling a target face picture captured by the target capturing machine to obtain a target face model;
the query unit is used for querying the information of the detained personnel according to the target face model;
the acquisition unit is used for acquiring the type of the monitoring point of the snapshot machine;
the control unit is used for determining that the number of the detained personnel is reduced when target detained personnel matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an exit monitoring point;
the control unit is also used for determining that the number of the detained personnel is not changed when target detained personnel matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an entrance monitoring point;
the control unit is further used for determining that the number of the detained people is increased when no target detained people of which the face models are matched with the target face models exist and the types of the monitoring points of the target snapshot machine are inlet monitoring points.
According to a third aspect of the embodiments of the present application, there is provided an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;
a memory for storing a computer program;
and the processor is used for realizing the personnel detention detection method when executing the program stored in the memory.
According to a fourth aspect of embodiments of the present application, there is provided a machine-readable storage medium having stored therein a computer program which, when executed by a processor, implements the above-described person stagnation detection method.
According to the personnel retention detection method, a target face picture captured by a target capture machine is modeled to obtain a target face model, and information of retained personnel is inquired according to the target face model; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is reduced; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, determining that the number of the detained personnel is unchanged; when no target retention personnel matched with the human face model exists and the monitoring point type of the target snapshot machine is an entrance monitoring point, the retention personnel is determined to be increased, and the statistical accuracy of the retention personnel is improved.
Drawings
FIG. 1 is a flow chart illustrating a method of people retention detection in accordance with an exemplary embodiment of the present application;
FIG. 2 is a schematic diagram of a people retention detection device according to an exemplary embodiment of the present disclosure;
FIG. 3 is a schematic diagram of a people retention detection device according to yet another exemplary embodiment of the present application;
FIG. 4 is a schematic diagram of a people retention detection device according to yet another exemplary embodiment of the present application;
fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an exemplary embodiment of the present application.
Detailed Description
Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present application, as detailed in the appended claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a", "an", and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
In order to make the technical solutions provided in the embodiments of the present application better understood and make the above objects, features and advantages of the embodiments of the present application more comprehensible, the technical solutions in the embodiments of the present application are described in further detail below with reference to the accompanying drawings.
Referring to fig. 1, a schematic flow chart of a method for detecting people staying in a Video surveillance system deployed in an embodiment of the present application is shown, where the method for detecting people staying in a Video surveillance system deployed in a specific scene (such as a mall, a company, a school, or a park) may be applied to a monitoring device with an intelligent analysis function, such as an NVR (Network Video Recorder), as shown in fig. 1, the method for detecting people staying in a Video surveillance system may include the following steps:
for ease of understanding and description, the following description will be given taking NVR as an example of the main execution of steps S100 to S140.
And S100, modeling a target face picture captured by the target capturing machine to obtain a target face model.
In the embodiment of the application, the target snapshot machine does not refer to a fixed snapshot machine, but refers to any snapshot machine deployed in any monitoring point (including an entrance monitoring point or an exit monitoring point) in a specified scene; the target face picture is not particularly specified to a certain fixed face picture, but can refer to any face picture captured by the target capturing machine, and the embodiment of the application is not repeated in the following.
In the embodiment of the application, when the target snapshot machine takes a snapshot of the target face picture, the target face picture can be transmitted to the NVR. When the NVR receives the target face picture transmitted by the target snapshot machine, modeling may be performed on the target face picture to obtain a face model of the target face picture (referred to herein as a target face model).
The specific implementation of modeling the face image to obtain the face model may refer to related descriptions in the prior art, and details of the embodiment of the present application are not repeated herein.
And S110, inquiring information of the detained personnel according to the target face model.
In the embodiment of the application, when the NVR obtains the target face model, the information of the staying person may be queried according to the target face model to determine whether the staying person (referred to as the target staying person) whose face model matches the target face model exists.
The face model matched with the target face model may be a face model whose similarity with the target face model exceeds a preset similarity threshold (which may be set according to an actual scene, such as 80% or 90%).
In one example, the information of the detained people may include a picture of the face of the detained people. When the NVR obtains the target face model, modeling can be carried out on the face pictures of each detained person to obtain the face model of the detained person, and the target face model and the face model of the detained person are compared to determine the target detained person matched with the face model of the target face model.
In another example, the information of the detained person may include a face model of the detained person. When the NVR obtains the target face model, the target face model and the face model of the detained people can be compared to determine the target detained people of which the face model is matched with the target face model.
And S120, determining that the number of detained people is reduced when target detained people exist, the face model of which is matched with the target face model, and the type of the monitoring point of the target snapshot machine is an exit monitoring point.
And S130, determining that the number of the detained personnel is unchanged when the target detained personnel matched with the face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point.
In the embodiment of the application, when the NVR determines that the target detained people matched with the face model exist, the type of the monitoring point (the entrance monitoring point or the exit monitoring point) of the target snapshot machine can be further obtained.
In one example, when the target snapshot machine transmits the snapshot to the NVR, the monitoring point type of the target snapshot machine may be carried, so that the NVR may directly acquire the monitoring point type of the target snapshot machine.
In another example, the target snapshot machine may carry an identifier of the target snapshot machine when transmitting the snapshot to the NVR; the NVR can pre-store the corresponding relation between the identification of the snapshot machine and the monitoring point type of the snapshot machine, so that the monitoring point type of the target snapshot machine can be determined according to the identification of the target snapshot machine.
In the embodiment of the application, when the NVR determines that there is a target detained person whose face model matches the target face model and the type of the monitoring point of the target snapshot machine is an exit monitoring point (that is, the target snapshot machine is a snapshot machine deployed at an exit monitoring point of a specified scene), the NVR may determine that the target detained person leaves the specified scene, and at this time, the NVR may determine that the number of detained persons is reduced, for example, the counted number of detained persons is reduced by 1.
When the NVR determines that the target detained people of which the face models are matched with the target face models exist, and the monitoring point type of the target snapshot machine is an entrance monitoring point (namely the target snapshot machine is a snapshot machine deployed at the entrance monitoring point of the specified scene), the NVR can determine that the target face picture is the face picture of the detained people in the specified scene, and at the moment, the NVR can keep the number of the detained people unchanged.
And S140, determining that the number of retained people is increased when no target retained people matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is the entrance snapshot machine.
In the embodiment of the application, when the NVR determines that no target detained people with the face models matched with the target face models exist, the NVR can further acquire the types of monitoring points (entrance monitoring points or exit monitoring points) of the target snapshot machine.
In the embodiment of the application, when the NVR determines that there is no target detained person whose face model matches the target face model and the type of the monitoring point of the target snapshot machine is the entrance snapshot machine, it is determined that the target face picture is a face picture of a person who newly enters the designated scene, and at this time, the NVR may determine that the number of detained persons is increased, for example, the counted number of detained persons is increased by 1.
Wherein, when the NVR determines that the number of the detained personnel is increased, the information of the newly increased detained personnel can be saved.
Therefore, in the method flow shown in fig. 1, whether the face picture captured by the capturing machine belongs to the face picture of the newly-added detained person is determined by the face picture capturing, the face picture modeling and the face model comparison, thereby effectively avoiding the number statistics error of the detained persons caused by capturing a plurality of pictures of the same person by the capturing machine, and improving the accuracy of the number statistics of the detained persons.
In one embodiment of the present application, after querying information of remaining people according to the target face model, the method may further include:
and when no target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is increased.
In this embodiment, for the case that there is no target detained person whose face model matches the target face model and the monitoring point type of the target snapshot machine is the exit snapshot machine, it is determined that there is a person entering a specified scene from the exit, at this time, NVR may determine that newly added detained person, and accordingly, the detained person counted by NVR is added.
In another embodiment of the present application, after querying information of the detained people according to the target face model, the method may further include:
and when no target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the detained personnel are unchanged.
In this embodiment, taking the case that there is no staying person at the target entering the designated scene from the exit as an example, and for the case that there is no staying person at the target matching the face model with the target face model and the monitoring point type of the target snapshot machine is the exit snapshot machine, it is determined that the missing situation occurs in the entrance snapshot machine, that is, when the staying person enters the designated scene from the entrance, the entrance snapshot machine does not take a snapshot of the staying person, at this time, the NVR may determine that the missing staying person has left the designated scene from the exit, and accordingly, the NVR may keep the counted staying person unchanged.
Further, in the embodiment of the application, when the NVR determines that there is a target detained person whose face model matches the target face model and the type of the monitoring point of the target snapshot machine is an exit monitoring point, the NVR may determine that the target detained person leaves a specified scene, and at this time, the NVR may directly delete information of the target detained person.
However, if the NVR directly deletes the information of the remaining people leaving the designated scene, when people entering the designated scene need to be queried, the monitoring video of the designated scene needs to be analyzed and determined, and the implementation efficiency is low.
In one embodiment of the present application, the information of the detained person may include a flag for identifying whether the detained person is in a detained state or a non-detained state;
the target detained personnel are in a detained state;
when there is a target detained person whose face model matches the target face model and the type of the monitoring point of the target snapshot machine is an exit monitoring point, the method may further include:
and updating the state of the target detained personnel to the state of no detaining.
In this embodiment, in order to improve the efficiency of querying information of persons who have entered a specific scene in the subsequent flow, the information of the detained persons recorded by the NVR may include a flag for identifying whether the detained persons are in the detained state or in the non-detained state.
Here, a flag for identifying that the staying person is in a staying state (i.e., the staying person is in the designated scene) may be referred to as a first flag, and a flag for identifying that the staying person is in a non-staying state (i.e., the staying person leaves the designated scene) may be referred to as a second flag.
For a detained person leaving a specified scene, the NVR no longer directly deletes the information of the detained person, but updates the state of the detained person to an unreserved state.
In one example, the NVR may update the retention status flag of the retained person from a first flag to a second flag.
In another example, the NVR may add a second flag to the detaining person's information and sequence the second flag and the first flag included in the detaining person's information. For example, the actual retention state of the retained person is determined in chronological order from first to last (or from last to first) and based on the retention state flag ranked last (or foremost).
Taking the order from first to last according to the time as an example, the NVR may add a second flag after the first flag in the information of the detained people, and further, when the NVR needs to determine the detained state of the detained people, it may be determined that the detained people are in a non-detained state, that is, the detained people have left the designated scene, according to the detained state flag (the second flag in this example) ranked last.
Accordingly, in this embodiment, when querying information of detained people according to the target face model, the NVR may query information of detained people whose detained status is marked as the first mark to determine whether there is a target detained person whose face model matches the target face model.
Further, in one embodiment of the present application, the information of the staying personnel may include an entry time and/or snapshot monitoring point information;
when there is a target detained person whose face model matches the target face model and the monitoring point type of the target snapshot machine is an entrance monitoring point, the detained person detection method may further include:
and updating the entering time of the target detained personnel and/or the snapshot monitoring point information.
In this embodiment, the information of the detained people recorded by the NVR may include entry time of the detained people (time when the detained people enter the specified scene or/and time when the detained people are captured by the entrance monitoring capturing machine within the specified scene) and/or capture monitoring point information.
In order to improve the accuracy of the recorded information of the detained personnel, when the NVR determines that the target detained personnel with the face model matched with the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, the NVR can update the entry time of the target detained personnel and/or the information of the snapshot monitoring point.
The snapshot monitoring point information may include information such as an identifier (e.g., name) and a location of the snapshot monitoring point.
In one example, the NVR may directly update the entry time and/or the snapshot monitoring point information recorded in the information of the target detained people to the snapshot time of the target face picture and the snapshot monitoring point information corresponding to the target snapshot machine, that is, for the detained people in the specified scene, the time that the entrance snapshot machine last shoots the detained people and/or the snapshot monitoring point information corresponding to the snapshot machine is used as the criterion.
In another example, the NVR may newly add the snapshot time of the target face picture (as the entry time corresponding to the target face picture) and/or the snapshot monitoring point information corresponding to the target snapshot machine to the information of the target detained people, that is, the information of the detained people may include a plurality of entry times and/or snapshot monitoring point information, and further, it may be convenient to determine at which times the detained people have been snapshot by the entry snapshot machine and/or which snapshot machines have been snapshot.
Further, in one embodiment of the present application, the information of the detainer may include an entry time;
the remaining person detection method may further include:
receiving a first detained person retrieval request, wherein the first detained person retrieval request carries an entry time range;
information on the staying person whose entry time is within the entry time range is retrieved.
In this embodiment, the information of the detained people recorded by the NVR may include the entry time of the detained people, and may provide information retrieval of the detained people for the time.
Accordingly, when the NVR receives a detainer retrieval request (referred to herein as a first detainer retrieval request) carrying an entry time range, the NVR may search the recorded information of detainers according to the entry time range to determine information of detainers whose entry time is within the entry time range.
In one example, when the information of the detained people recorded by the NVR includes a plurality of entry times, any of which is within the entry time range, the NVR may determine the information of the detained people as the information of the detained people whose entry time is within the entry time range.
In another example, when the information of the staying personnel recorded by the NVR includes a plurality of entry times, the NVR may determine whether the latest entry time included in the information of the staying personnel is within an entry time range, and if so, determine that the information of the staying personnel is the information of the staying personnel whose entry time is within the entry time range; otherwise, the information of the detained person is determined not to be the information of the detained person whose entry time is within the entry time range.
Therefore, in the embodiment, the NVR can perform statistics on the retention personnel entering the time range, and controllability of the statistics on the retention personnel is improved.
Further, in one embodiment of the present application, the information of the staying person may include face attribute information of the staying person;
the remaining person detection method may further include:
receiving a second detained person retrieval request, wherein the second detained person retrieval request carries face retrieval filtering conditions;
and inquiring information of the detained personnel according to the face retrieval filtering condition, and determining the information of the detained personnel matched with the face retrieval filtering condition.
In this embodiment, the information of the detained people recorded by the NVR may include face attribute information of the detained people, and may provide information retrieval of the detained people for the face attributes.
The face attribute information may include, but is not limited to, one or more of gender, age group, whether to wear a mask, whether to wear glasses, and the like.
Accordingly, when the NVR receives a detained person retrieval request (referred to as a second detained person retrieval request herein) carrying the face retrieval filtering condition, the NVR may query information of detained persons according to the face retrieval filtering condition, and determine information of detained persons matching the face retrieval filtering condition.
The face retrieval filtering condition is attribute information of the face to be retrieved, which may include but is not limited to one or more of facial expression of the face to be retrieved, whether glasses are worn, gender, age and the like.
Therefore, in the embodiment, the NVR can perform statistics of the staying personnel aiming at the face attributes, and the controllability of the statistics of the staying personnel is improved.
Further, in one embodiment of the present application, the information of the detained person may include an entry time;
when there is a target detained person whose face model matches the target face model and the monitoring point type of the target snapshot machine is an exit monitoring point, the detained person detection method may further include:
increasing the departure time in the information of the target detained person;
and determining the detention time of the target detention personnel according to the entering time and the leaving time of the target detention personnel.
In this embodiment, the NVR may record the entry time and the exit time of the detained person, and determine the detained person's detention time (detention time within the specified scenario) from the entry time and the exit time of the detained person.
Correspondingly, when the NVR determines that the target detained people with the face models matched with the target face models exist and the monitoring point type of the target snapshot machine is an exit monitoring point, the NVR can increase leaving time (namely the snapshot time of the target face pictures) in the information of the target detained people and determine the staying time of the target detained people according to the entering time and the leaving time of the target detained people.
In one example, when the information recorded by the NVR for the detained people includes multiple times of entry, the NVR may determine the detained people's time of residence based on the earliest time of entry and the time of departure that the information for the detained people includes.
In another example, when the information recorded by the NVR for the detained personnel includes multiple entry times, the NVR may determine the detained personnel's detention time based on the last entry time and the exit time included in the information for the detained personnel.
In order to enable those skilled in the art to better understand the technical solutions provided by the embodiments of the present application, the technical solutions provided by the embodiments of the present application are described below with reference to specific examples.
In this embodiment, the information of the detained people recorded in the detained people library includes the ID of the detained people, the face model, the entry time, the exit time, the snapshot monitoring point information, the face attribute, and the detained state flag (the first flag corresponds to the detained state, and the second flag corresponds to the non-detained state) as an example.
Wherein, the ID of the detention personnel is used for uniquely identifying the detention personnel, the ID of different detention personnel is different, and the ID of the same detention personnel is the same.
In this embodiment, when receiving a target face picture transmitted by a target snapshot machine, the NVR may model the target face picture to obtain a target face model, and query, according to the target face model, a face model included in information of retained persons including a first marker recorded in a retained person library for comparison.
If the NVR finds that the target detained people with the similarity between the face model and the target face model being more than 80% exist, the NVR can acquire the type of the monitoring point of the target snapshot machine so as to determine that the type of the monitoring point of the target snapshot machine is an entrance monitoring point or an exit monitoring point.
If the type of the monitoring point of the target snapshot machine is an entrance monitoring point, the NVR can determine that the face captured this time appears and maintain the face in the detained personnel library, at this time, the NVR can add a record to the information corresponding to the ID of the target detained personnel recorded in the detained personnel library, and the record comprises the entry time (the snapshot time of the target face picture) and the snapshot monitoring point information (the name and the position of the monitoring point of the target snapshot machine).
If the type of the monitoring point of the target snapshot machine is an exit monitoring point, the NVR can determine that the target detained people leave the designated scene, at this time, the NVR can add a record to the information corresponding to the ID of the target detained people recorded in the detained people library, the record comprises leaving time (snapshot time of the target face picture) and snapshot monitoring point information (the name and the position of the monitoring point of the target snapshot machine), and the detaining mark in the information corresponding to the ID of the target detained people recorded in the detained people library is updated to the second mark from the first mark.
If the NVR finds that no target detained people with the similarity between the face model and the target face model being more than 80% exists, the NVR can allocate an ID to the target face model, and adds information of the detained people corresponding to the ID to a detained people library, wherein the information comprises the target face model, the entering time (the snapshot time of the target face picture), snapshot monitoring point information (the name and the position of a monitoring point of a target snapshot machine), face attributes and a second mark.
In this embodiment, the NVR may count the number of detained persons in the specified scene (determined by the number of different IDs in the information of detained persons including the first identification) and specific information of detained persons (including but not limited to face attributes (such as gender, age, etc.), entry time, etc.) in real time according to the information of detained persons including the first marker in the detained person repository.
In this embodiment, NVR may support information retrieval for detained people for a range of entry times and/or facial attributes.
When the NVR receives a detained person retrieval request carrying the entry time range and/or the face retrieval filtering condition, the NVR can retrieve the information of the matched detained person from the detained person library according to the entry time range and/or the face retrieval filtering condition carried in the request.
In this embodiment, for any detained person information including the second flag, the NVR may determine the detention time of the corresponding detained person in the specified scenario from the entry time and the exit time recorded therein.
In the embodiment of the application, a target face image captured by a target capturing machine is modeled to obtain a target face model, and information of detained people is inquired according to the target face model; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is reduced; when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, determining that the number of the detained personnel is unchanged; when no target retention personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, the retention personnel is determined to be increased, and the statistical accuracy of the retention personnel is improved.
The methods provided herein are described above. The following describes the apparatus provided in the present application:
please refer to fig. 2, which is a schematic structural diagram of a people staying detection apparatus provided in an embodiment of the present application, wherein the people staying detection apparatus may be applied to a monitoring device (such as NVR) in the foregoing method embodiment, and as shown in fig. 2, the people staying detection apparatus may include:
the receiving unit 210 is configured to receive a target face picture captured by a target capturing machine;
the modeling unit 220 is configured to model a target face picture captured by the target capture machine to obtain a target face model;
the query unit 230 is configured to query information of remaining people according to the target face model;
an obtaining unit 240, configured to obtain a monitoring point type of the snapshot machine;
the control unit 250 is used for determining that the number of the detained people is reduced when target detained people exist, the face models of which are matched with the target face models, and the types of the monitoring points of the target snapshot machine are outlet monitoring points;
the control unit 250 is further configured to determine that the number of retained people is not changed when there are target retained people whose face models match the target face model and the types of the monitoring points of the target snapshot machine are entrance monitoring points;
the control unit 250 is further configured to determine that the number of retained people is increased when there is no target retained person whose face model matches the target face model and the type of the monitoring point of the target snapshot machine is an entrance monitoring point.
In an optional embodiment, the control unit 250 is further configured to determine that the number of detained people is increased when there is no target detained people with a face model matching the target face model and the monitoring point type of the target snapshot machine is an exit monitoring point; or the like, or, alternatively,
the control unit 250 is further configured to determine that the detained people are not changed when there is no target detained people with the face models matched with the target face models and the types of the monitoring points of the target snapshot machine are exit monitoring points.
In an alternative embodiment, the detaining person's information includes indicia identifying the detaining person as being in a detained state or a non-detained state; the target detained personnel are in a detained state;
the control unit 250 is further configured to update the state of the target detained people to be in an unreleased state when the target detained people exist whose face models are matched with the target face models and the monitoring point types of the target snapshot machine are exit monitoring points.
In an alternative embodiment, the information of the detained people comprises the entering time and/or the snapshot monitoring point information;
the control unit 250 is further configured to update the entry time and/or snapshot monitoring point information of the target detained people when there are target detained people with the face models matched with the target face models and the monitoring point types of the target snapshot machine are entry monitoring points.
In an alternative embodiment, the information of the detained person comprises the time of entry;
the receiving unit 210 is further configured to receive a first detained person retrieval request, where the first detained person retrieval request carries an entry time range;
as shown in fig. 3, the people staying detection apparatus further includes:
a first search unit 260 for searching information of the staying person whose entering time is within the entering time range.
In an optional embodiment, the information of the detained people comprises face attribute information of the detained people;
the receiving unit 210 is further configured to receive a second detained person retrieval request, where the second detained person retrieval request carries a face retrieval filtering condition;
as shown in fig. 4, the people staying detection apparatus further includes:
the second retrieving unit 270 is configured to query information of remaining people according to the face retrieval filtering condition, and determine information of remaining people matching the face retrieval filtering condition.
It should be noted that, in practical applications, the first retrieving unit 260 and the second retrieving unit 270 may be implemented by the same retrieving unit, and specific implementation thereof is not described herein again.
In an optional embodiment, the control unit 250 is further configured to, when there is a target detained person whose face model matches the target face model and the monitoring point type of the target snapshot machine is an exit monitoring point, increase departure time in the information of the target detained person;
the control unit 250 is further configured to determine the staying time of the target staying person according to the entering time and the leaving time of the target staying person
Fig. 5 is a schematic diagram of a hardware structure of an electronic device according to an embodiment of the present disclosure. The electronic device may include a processor 501, a communication interface 502, a memory 503, and a communication bus 504. The processor 501, the communication interface 502 and the memory 503 are in communication with each other via a communication bus 504. Wherein, the memory 503 stores a computer program; the processor 501 may execute the person remaining detection method described above by executing a program stored on the memory 503.
The memory 503 referred to herein may be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, and the like. For example, the memory 502 may be: RAM (random access memory), volatile memory, non-volatile memory, flash memory, a storage drive (e.g., a hard drive), a solid state drive, any type of storage disk (e.g., an optical disk, dvd, etc.), or similar storage medium, or a combination thereof.
Embodiments of the present application also provide a machine-readable storage medium, such as the memory 503 in fig. 5, storing a computer program, which can be executed by the processor 501 in the electronic device shown in fig. 5 to implement the people-retention detection method described above.
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.
The above description is only exemplary of the present application and should not be taken as limiting the present application, as any modification, equivalent replacement, or improvement made within the spirit and principle of the present application should be included in the scope of protection of the present application.
Claims (16)
1. A method of detecting a person staying in a room, comprising:
modeling a target face picture captured by a target capturing machine to obtain a target face model;
inquiring information of detained personnel according to the target face model;
when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is reduced;
when target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point, determining that the number of the detained personnel is unchanged;
and determining that the number of retained people is increased when no target retained people matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an entrance monitoring point.
2. The method according to claim 1, wherein after querying information of detained people according to the target face model, the method further comprises:
when target detained personnel matched with the face model and the target face model do not exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the number of detained personnel is increased; or the like, or, alternatively,
and when no target detained personnel matched with the face model and the target face model exist and the monitoring point type of the target snapshot machine is an exit monitoring point, determining that the detained personnel are unchanged.
3. The method of claim 1, wherein the detaining person's information includes indicia identifying the detaining person as being in a detained state or a non-detained state;
the target detained personnel are in a detained state;
when a target detained person exists, the face model of which is matched with the target face model, and the monitoring point type of the target snapshot machine is an exit monitoring point, the method further comprises the following steps:
and updating the state of the target detained personnel to be an unreserved state.
4. The method according to claim 1, characterized in that the information of the detained people comprises the time of entry and/or snapshot monitoring point information;
when a target detained person exists, the face model of which is matched with the target face model, and the monitoring point type of the target snapshot machine is an entrance monitoring point, the method further comprises the following steps:
and updating the entering time and/or snapshot monitoring point information of the target detained personnel.
5. The method of claim 1, wherein the information of the detained personnel comprises an entry time;
the method further comprises the following steps:
receiving a first detained person retrieval request, wherein the first detained person retrieval request carries an entry time range;
and retrieving information of the detained people with the entry time within the entry time range.
6. The method according to claim 1, wherein the information of the detained people comprises face attribute information of the detained people;
the method further comprises the following steps:
receiving a second detained person retrieval request, wherein the second detained person retrieval request carries face retrieval filtering conditions;
and inquiring information of the detained personnel according to the face retrieval filtering condition, and determining the information of the detained personnel matched with the face retrieval filtering condition.
7. The method of claim 1, wherein the information of the detained personnel comprises an entry time;
when a target detained person exists, the face model of which is matched with the target face model, and the monitoring point type of the target snapshot machine is an exit monitoring point, the method further comprises the following steps:
increasing the departure time in the information of the target detained person;
and determining the detention time of the target detention personnel according to the entering time and the leaving time of the target detention personnel.
8. A people retention detection device, comprising:
the receiving unit is used for receiving a target face picture captured by the target capturing machine;
the modeling unit is used for modeling a target face picture captured by the target capturing machine to obtain a target face model;
the query unit is used for querying the information of the detained personnel according to the target face model;
the acquisition unit is used for acquiring the type of the monitoring point of the snapshot machine;
the control unit is used for determining that the number of the detained personnel is reduced when target detained personnel matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an exit monitoring point;
the control unit is also used for determining that the number of the detained personnel is not changed when target detained personnel matched with the face model and the target face model exist and the type of the monitoring point of the target snapshot machine is an entrance monitoring point;
the control unit is further used for determining that the number of the detained people is increased when no target detained people of which the face models are matched with the target face models exist and the types of the monitoring points of the target snapshot machine are inlet monitoring points.
9. The apparatus of claim 8,
the control unit is also used for determining that the number of the detained people is increased when no target detained people with the face models matched with the target face models exist and the types of the monitoring points of the target snapshot machine are outlet monitoring points; or the like, or, alternatively,
the control unit is further used for determining that the detained personnel are not changed when the target detained personnel matched with the face model do not exist and the type of the monitoring point of the target snapshot machine is an exit monitoring point.
10. The apparatus of claim 8, wherein the detained person's information comprises indicia identifying the detained person as being in a detained state or a non-detained state; the target detained personnel are in a detained state;
and the control unit is also used for updating the state of the target detained personnel to be in an unreleased state when the target detained personnel matched with the human face model exist and the type of the monitoring point of the target snapshot machine is an outlet monitoring point.
11. The device according to claim 8, wherein the information of the detained people comprises entry time and/or snapshot monitoring point information;
the control unit is further used for updating the entering time and/or the snapshot monitoring point information of the target detained personnel when the target detained personnel matched with the human face model exist and the monitoring point type of the target snapshot machine is an entrance monitoring point.
12. The apparatus of claim 8, wherein the information of the detained personnel comprises an entry time;
the receiving unit is further configured to receive a first detained person retrieval request, where the first detained person retrieval request carries an entry time range;
the device further comprises:
and the first retrieval unit is used for retrieving the information of the detained personnel with the entry time within the entry time range.
13. The apparatus according to claim 8, wherein the information of the detained person includes face attribute information of the detained person;
the receiving unit is further configured to receive a second detained person retrieval request, where the second detained person retrieval request carries a face retrieval filtering condition;
the device further comprises:
and the second retrieval unit is used for querying the information of the detained personnel according to the face retrieval filtering condition and determining the information of the detained personnel matched with the face retrieval filtering condition.
14. The apparatus of claim 8,
the control unit is further used for increasing leaving time in information of target detained people when the target detained people exist, the face models of which are matched with the target face models, and the types of the monitoring points of the target snapshot machine are outlet monitoring points;
the control unit is also used for determining the detention time of the target detention personnel according to the entering time and the leaving time of the target detention personnel.
15. An electronic device is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor and the communication interface are used for realizing mutual communication by the memory through the communication bus;
a memory for storing a computer program;
a processor for implementing the method of any one of claims 1 to 7 when executing a program stored in the memory.
16. 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 claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811125902.2A CN110969743A (en) | 2018-09-26 | 2018-09-26 | Person retention detection method and device, electronic device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811125902.2A CN110969743A (en) | 2018-09-26 | 2018-09-26 | Person retention detection method and device, electronic device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110969743A true CN110969743A (en) | 2020-04-07 |
Family
ID=70026537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811125902.2A Pending CN110969743A (en) | 2018-09-26 | 2018-09-26 | Person retention detection method and device, electronic device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110969743A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112885013A (en) * | 2021-01-13 | 2021-06-01 | 三一专用汽车有限责任公司 | Monitoring and early warning method and device and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008057655A2 (en) * | 2006-11-02 | 2008-05-15 | Ram Pattikonda | System and method for counting people |
| US20090116700A1 (en) * | 2007-11-06 | 2009-05-07 | Mitsubishi Electric Corporation | Entering and leaving management system |
| CN101763667A (en) * | 2008-12-26 | 2010-06-30 | 上海三有日用科技有限公司 | Passenger flow management method of large-scale multi-venue activity based on radio frequency identification technology |
| CN102542292A (en) * | 2011-12-26 | 2012-07-04 | 湖北莲花山计算机视觉和信息科学研究院 | Method for determining roles of staffs on basis of behaviors |
| CN104574437A (en) * | 2013-10-29 | 2015-04-29 | 松下电器产业株式会社 | Staying state analysis device, staying state analysis system and staying state analysis method |
| CN107992786A (en) * | 2016-10-27 | 2018-05-04 | 中国科学院沈阳自动化研究所 | A kind of people streams in public places amount statistical method and system based on face |
| CN108090452A (en) * | 2017-12-20 | 2018-05-29 | 贵阳宏益房地产开发有限公司 | Personnel statistical method and device |
-
2018
- 2018-09-26 CN CN201811125902.2A patent/CN110969743A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2008057655A2 (en) * | 2006-11-02 | 2008-05-15 | Ram Pattikonda | System and method for counting people |
| US20090116700A1 (en) * | 2007-11-06 | 2009-05-07 | Mitsubishi Electric Corporation | Entering and leaving management system |
| CN101763667A (en) * | 2008-12-26 | 2010-06-30 | 上海三有日用科技有限公司 | Passenger flow management method of large-scale multi-venue activity based on radio frequency identification technology |
| CN102542292A (en) * | 2011-12-26 | 2012-07-04 | 湖北莲花山计算机视觉和信息科学研究院 | Method for determining roles of staffs on basis of behaviors |
| CN104574437A (en) * | 2013-10-29 | 2015-04-29 | 松下电器产业株式会社 | Staying state analysis device, staying state analysis system and staying state analysis method |
| CN107992786A (en) * | 2016-10-27 | 2018-05-04 | 中国科学院沈阳自动化研究所 | A kind of people streams in public places amount statistical method and system based on face |
| CN108090452A (en) * | 2017-12-20 | 2018-05-29 | 贵阳宏益房地产开发有限公司 | Personnel statistical method and device |
Non-Patent Citations (1)
| Title |
|---|
| 晨月: "国外先进监控技术最新发展情况", 《中国安防》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112885013A (en) * | 2021-01-13 | 2021-06-01 | 三一专用汽车有限责任公司 | Monitoring and early warning method and device and readable storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TWI743987B (en) | Behavioral analysis methods, electronic devices and computer storage medium | |
| CN110139075B (en) | Video data processing method, video data processing device, computer equipment and storage medium | |
| CN110598551B (en) | Method, device, equipment and medium for improving pedestrian identity recognition efficiency | |
| CN109858354B (en) | Face identity library, track table establishment method and face track query method and system | |
| WO2022156234A1 (en) | Target re-identification method and apparatus, and computer-readable storage medium | |
| CN109784231B (en) | Security information management method, device and storage medium | |
| CN111368619B (en) | Suspicious person detection method, suspicious person detection device and suspicious person detection equipment | |
| CN112579593A (en) | Population database sorting method and device | |
| CN111291596B (en) | Early warning method and device based on face recognition | |
| CN115083004B (en) | Identity recognition method and device and computer readable storage medium | |
| CN110399525A (en) | A kind of people based on image recognition technology, object motion profile method for quickly retrieving | |
| CN109963113B (en) | Method and device for monitoring interested target | |
| CN110543584A (en) | method, device, processing server and storage medium for establishing face index | |
| CN111435435A (en) | Method, device, server and system for identifying pedestrians | |
| CN111367956B (en) | Data statistics method and device | |
| CN110969743A (en) | Person retention detection method and device, electronic device and readable storage medium | |
| CN110876090B (en) | Video abstract playback method and device, electronic equipment and readable storage medium | |
| CN111784742B (en) | Pedestrian cross-lens tracking method and device | |
| CN116189086A (en) | Loitering personnel detection method based on AI model, edge equipment and storage medium | |
| CN114863364A (en) | Security detection method and system based on intelligent video monitoring | |
| CN112559583B (en) | Method and device for identifying pedestrians | |
| CN111818296B (en) | Monitoring target identification method and distributed monitoring system | |
| JP5618628B2 (en) | Person information automatic collection system, person information automatic collection method and program thereof | |
| CN111369791B (en) | Method and device for determining landing points, electronic equipment and storage medium | |
| CN110929095A (en) | Video abstract playback method and device, electronic equipment and readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200407 |