CN104754296A - Time sequence tracking-based target judging and filtering method applied to transformer substation operation security control - Google Patents
Time sequence tracking-based target judging and filtering method applied to transformer substation operation security control Download PDFInfo
- Publication number
- CN104754296A CN104754296A CN201410347251.7A CN201410347251A CN104754296A CN 104754296 A CN104754296 A CN 104754296A CN 201410347251 A CN201410347251 A CN 201410347251A CN 104754296 A CN104754296 A CN 104754296A
- Authority
- CN
- China
- Prior art keywords
- target
- time
- coordinate
- transformer substation
- substation operation
- 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
Landscapes
- Image Analysis (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention discloses a time sequence tracking-based target judging and filtering method applied to transformer substation operation security control. The method comprises, firstly, obtaining the coordinate of a target to be judged for N times, and recording the coordinate of the target every time and the time of generating the target every time; secondly, according to the recorded coordinate of the target every time and the time of generating the target every time, calculating the moving distance and the moving time of the target every time; lastly, calculating the moving speed of the target in the N times and the average speed of the target, and according to the average time, determining whether the target is interference. By judging the target through time sequence tracking, the time sequence tracking-based target judging and filtering method applied to transformer substation operation security control can effectively improve the accuracy of target judgement, and meanwhile through filtering, can eliminate most of interference.
Description
Technical field
The present invention relates to transformer substation operation safety management and control technology, be specifically related to the video dynamic target capture technology in transformer substation operation safety management and control.
Background technology
Traditional video dynamic target capture is generally applied in indoor, and its intensity of illumination is generally constant or changes inviolent.In the video dynamic target capture system of transformer substation operation safety management and control, the judgement of dynamic object in transformer station is relied on completely and catches pixel size to be judged to be real captured target or external interference.For making system worked well, prerequisite must be that Video capture system must be able to catch very accurately, if when system cloud gray model, ambient light is larger according to Strength Changes, at this moment various interference is by showed increased, is at this moment also difficult to ensure that interference and target are not different sizes.
Summary of the invention
Video dynamic target capture technology for existing transformer substation operation safety management and control is subject to external environmental interference, affects the problem of accuracy rate, the object of the present invention is to provide a kind of object judgement filter method followed the trail of based on sequential.The method is followed the trail of object judgement by sequential, will effectively improve the accuracy rate to object judgement, can get rid of overwhelming majority interference by filtering simultaneously.
In order to achieve the above object, the present invention adopts following technical scheme:
Be applied to the object judgement filter method followed the trail of based on sequential of transformer substation operation safety management and control, first described method, obtains the coordinate waiting for N time to judge target, and records the coordinate of each target and each time generating target;
Then, displacement and the traveling time of each target is gone out according to the coordinate of each target of record and the Time Calculation of each generation target;
Finally, calculate speed and the average speed of N target movement, and judge whether this target is interference according to this average speed.
In the preferred version of this method, target is in action in process, and elementary area gathers target image, and calculates coordinates of targets (X by dynamic object algorithm
n, Y
n), record obtains the time T of coordinates of targets simultaneously
n.
Scheme provided by the invention is followed the trail of object judgement, at the time T of this coordinates of targets by sequential
nwith coordinates of targets last time time T
n-1time difference be T=T
n-T
n-1.To effectively improve the accuracy rate to object judgement, overwhelming majority interference can be got rid of, if when T is less by filtering simultaneously, displacement is larger again, be greater than the distance that normal pedestrian walks in time T, the target filtering that we are then generated, be considered as interference.
Accompanying drawing explanation
The present invention is further illustrated below in conjunction with the drawings and specific embodiments.
Fig. 1 is process principle figure of the invention process.
Embodiment
The technological means realized to make the present invention, creation characteristic, reaching object and effect is easy to understand, below in conjunction with concrete diagram, setting forth the present invention further.
The present invention is followed the trail of by sequential and judges the true and false of target, removes overwhelming majority interference, greatly improves the accuracy rate to object judgement, then will improve transformer substation operation safety managing and control system to video dynamic target capture
See Fig. 1, be depicted as the flow chart that the present invention is based on sequential tracking and carry out target judging to filter.As seen from the figure, whole handling process is divided into following three key steps:
First, obtain and wait for N time to judge coordinates of targets, and record the coordinate (X1, Y1) of each target, (X2, Y2) ..., (Xn, Yn) and each the time T1 generating target, T2 ..., Tn.
During specific implementation, in target in action process, gather target image by elementary area, and calculate coordinates of targets (X by dynamic object algorithm
n, Y
n), record obtains the time T of coordinates of targets simultaneously
n.
The degree of depth of target filtering is to the value of N, in actual application in substations, as more in run into interference source, the corresponding increase of value of N.N value is larger, filter effect is better, but also bring the time delay of object judgement, elementary area is when carrying out coordinates of targets and gathering thus, first interference source quantity is judged, the number of times waiting to judge coordinates of targets is calculated again, i.e. the numerical value of N, with the balance of the precision and efficiency that ensure object judgement according to interference source quantity.
Then, computing unit obtains the data of its record from elementary area, goes out displacement and the traveling time of each target according to the coordinate of each target of record and the Time Calculation of each generation target.
During for each record object coordinate, computing unit, by according to the coordinate of this record object and the coordinate of last registration target, calculates the displacement S of this record object relative to last registration target
n:
S
n＝(Xn，Yn)-(Xn-1，Yn-1)；
Moreover during for each record object coordinate, computing unit, by according to the time of this record object and the time of last registration target, calculates the traveling time T of this record object relative to last registration target
n:
T
n＝(Tn)-(Tn-1)。
Finally, computing unit calculates speed and the average speed of N target movement again, then by judging that comparing unit determines whether interference according to this average speed.
By two steps above, when obtaining and record N coordinates of targets, the displacement S of target relative to last target of current record can be obtained
nwith traveling time T
n, each target can be calculated thus at this segment distance mobile or speed V during this period of time
n:
V
n＝S
n/T
n；
Owing to having got N coordinates of targets and time before, therefore the average translational speed V ' of this N time target can be obtained:
V′＝(∑V
n)/N。
After the average translational speed V ' obtaining N target, judge that this speed V ' and the actual translational speed V 〞 of predetermined target are before compared judgement by comparing unit, if average speed V ' approximates the actual translational speed V 〞 of target, i.e. V ' ≈ V 〞, then judge that this target is actual moving target, two speed differences are comparatively large else if, namely judge that this target is as interference.
At the time T of this coordinates of targets
nwith coordinates of targets last time time T
n-1time difference be T=T
n-T
n-1.To effectively improve the accuracy rate to object judgement, overwhelming majority interference can be got rid of, if when T is less by filtering simultaneously, displacement is larger again, be greater than the distance that normal pedestrian walks in time T, the target filtering that we are then generated, be considered as interference.
This programme is further illustrated below by way of an embody rule:
In whole transformer station, multiple camera and the elementary area to camera video process are installed, the size of the number Yao Shi transformer station of camera are installed and determine.Camera institute illumination range must the whole transformer station of all standing.
When moving target moves under certain camera, the elementary area of corresponding camera can capture the relevant information of moving target, as moving target pixel coordinate in the picture, and record the time forming pixel coordinate, the physical coordinates of pixel coordinate equal corresponding transformer station electronic chart, now physical coordinates represents with (X1, Y1), and the time recorded represents with T1.
Because the moving target under camera is that the moment is all in motion, when moving target moves to another place, elementary area can capture the pixel coordinate of moving target equally, and record the time forming pixel coordinate, now physical coordinates (the X2 of pixel coordinate corresponding transformer station electronic chart, Y2) represent, and the time now forming physical coordinates represents with T2.
Moving target continues mobile, and the physical coordinates that corresponding elementary area is formed represents with (Xn, Yn), and the time represents with Tn.Distance S=(Xn, Yn)-(X1, the Y1) of moving target movement within the time of T=(Tn-T1), the average speed V=S/T that moving target is interior at this moment.
If moving target is a normal pedestrian, the normal translational speed of pedestrian is 1.5m/s-2m/s.So velocity estimated is here predisposed to 2m/s.Determination methods is, is judged to be interference, otherwise is judged as normal pedestrian when average speed V is greater than 2m/s.
More than show and describe general principle of the present invention, principal character and advantage of the present invention.The technical staff of the industry should understand; the present invention is not restricted to the described embodiments; what describe in above-described embodiment and specification just illustrates principle of the present invention; without departing from the spirit and scope of the present invention; the present invention also has various changes and modifications, and these changes and improvements all fall in the claimed scope of the invention.Application claims protection range is defined by appending claims and equivalent thereof.
Claims (2)
1. be applied to the object judgement filter method followed the trail of based on sequential of transformer substation operation safety management and control, it is characterized in that, first described method, obtains the coordinate waiting for N time to judge target, and records the coordinate of each target and each time generating target;
Then, displacement and the traveling time of each target is gone out according to the coordinate of each target of record and the Time Calculation of each generation target;
Finally, calculate speed and the average speed of N target movement, and judge whether this target is interference according to this average speed.
2. a kind of object judgement filter method followed the trail of based on sequential being applied to transformer substation operation safety management and control according to claim 1, it is characterized in that, target is in action in process, elementary area gathers target image, and calculating coordinates of targets by dynamic object algorithm, record obtains the time of coordinates of targets simultaneously.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410347251.7A CN104754296A (en) | 2014-07-21 | 2014-07-21 | Time sequence tracking-based target judging and filtering method applied to transformer substation operation security control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410347251.7A CN104754296A (en) | 2014-07-21 | 2014-07-21 | Time sequence tracking-based target judging and filtering method applied to transformer substation operation security control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104754296A true CN104754296A (en) | 2015-07-01 |
Family
ID=53593325
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410347251.7A Pending CN104754296A (en) | 2014-07-21 | 2014-07-21 | Time sequence tracking-based target judging and filtering method applied to transformer substation operation security control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104754296A (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5947413A (en) * | 1996-11-12 | 1999-09-07 | Raytheon Company | Correlation filters for target reacquisition in trackers |
| US6590999B1 (en) * | 2000-02-14 | 2003-07-08 | Siemens Corporate Research, Inc. | Real-time tracking of non-rigid objects using mean shift |
| US6980685B2 (en) * | 2001-01-22 | 2005-12-27 | Siemens Corporate Research, Inc. | Model-based localization and measurement of miniature surface mount components |
| US20060120590A1 (en) * | 2004-12-07 | 2006-06-08 | Lockheed Martin Corporation | Automatic scene correlation and identification |
| CN101344966A (en) * | 2008-08-18 | 2009-01-14 | 浙江大学 | Method for detecting exception target behavior in intelligent vision monitoring |
| CN101739686A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Moving object tracking method and system thereof |
| CN101764923A (en) * | 2008-12-23 | 2010-06-30 | 北京中星微电子有限公司 | Method and device for eliminating noise in motion detection |
| CN102096829A (en) * | 2011-01-06 | 2011-06-15 | 西北工业大学 | Iterative optimization distance categorization-based space weak and small target detection method |
-
2014
- 2014-07-21 CN CN201410347251.7A patent/CN104754296A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5947413A (en) * | 1996-11-12 | 1999-09-07 | Raytheon Company | Correlation filters for target reacquisition in trackers |
| US6590999B1 (en) * | 2000-02-14 | 2003-07-08 | Siemens Corporate Research, Inc. | Real-time tracking of non-rigid objects using mean shift |
| US6980685B2 (en) * | 2001-01-22 | 2005-12-27 | Siemens Corporate Research, Inc. | Model-based localization and measurement of miniature surface mount components |
| US20060120590A1 (en) * | 2004-12-07 | 2006-06-08 | Lockheed Martin Corporation | Automatic scene correlation and identification |
| CN101344966A (en) * | 2008-08-18 | 2009-01-14 | 浙江大学 | Method for detecting exception target behavior in intelligent vision monitoring |
| CN101764923A (en) * | 2008-12-23 | 2010-06-30 | 北京中星微电子有限公司 | Method and device for eliminating noise in motion detection |
| CN101739686A (en) * | 2009-02-11 | 2010-06-16 | 北京智安邦科技有限公司 | Moving object tracking method and system thereof |
| CN102096829A (en) * | 2011-01-06 | 2011-06-15 | 西北工业大学 | Iterative optimization distance categorization-based space weak and small target detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6571274B2 (en) | System and method for laser depth map sampling | |
| CN111126152A (en) | Video-based multi-target pedestrian detection and tracking method | |
| WO2016149938A1 (en) | Video monitoring method, video monitoring system and computer program product | |
| CN101344965A (en) | Tracking system based on binocular camera shooting | |
| CN108665541B (en) | A kind of ground drawing generating method and device and robot based on laser sensor | |
| CN103530874A (en) | People flow counting method on basis of Kinect | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| CN105913454A (en) | Pixel coordinate locus prediction method of motion object in video image | |
| CN103150559A (en) | Kinect three-dimensional depth image-based head identification and tracking method | |
| JP2013196684A (en) | Object counting method and object counting device | |
| CN106355604A (en) | Target image tracking method and system | |
| CN104063885A (en) | Improved movement target detecting and tracking method | |
| CN105513342A (en) | Video-tracking-based vehicle queuing length calculating method | |
| CN105261034A (en) | Method and device for calculating traffic flow on highway | |
| WO2022095514A1 (en) | Image detection method and apparatus, electronic device, and storage medium | |
| JP7306766B2 (en) | Target motion information detection method, apparatus, equipment and medium | |
| CN102930524A (en) | Method for detecting heads based on vertically-placed depth cameras | |
| CN106228570A (en) | A kind of Truth data determines method and apparatus | |
| CN110222579B (en) | Video object counting method combining motion law and target detection | |
| CN204305213U (en) | The interactive sighting device of multi-cam human body tracking | |
| Rao et al. | Real-time speed estimation of vehicles from uncalibrated view-independent traffic cameras | |
| Prokaj et al. | Using 3d scene structure to improve tracking | |
| CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
| CN111062971A (en) | Cross-camera mud head vehicle tracking method based on deep learning multi-mode | |
| CN105469427A (en) | Target tracking method applied to videos |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150701 |
|
| WD01 | Invention patent application deemed withdrawn after publication |