CN105744232A - Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology - Google Patents
Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology Download PDFInfo
- Publication number
- CN105744232A CN105744232A CN201610174705.4A CN201610174705A CN105744232A CN 105744232 A CN105744232 A CN 105744232A CN 201610174705 A CN201610174705 A CN 201610174705A CN 105744232 A CN105744232 A CN 105744232A
- Authority
- CN
- China
- Prior art keywords
- target
- behavior
- transmission line
- external force
- damage prevention
- 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.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B13/00—Burglar, theft or intruder alarms
- G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
- G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
- G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
- G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
- G08B13/19602—Image analysis to detect motion of the intruder, e.g. by frame subtraction
- G08B13/19608—Tracking movement of a target, e.g. by detecting an object predefined as a target, using target direction and or velocity to predict its new position
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method for preventing a power transmission line from being externally broken, and in particular relates to a method for preventing the power transmission line from being externally broken through a video. The method for preventing the power transmission line from being externally broken through the video based on a behaviour analysis technology comprises the following steps of: (1), acquiring an image; (2), detecting motion; (3), detecting a block; (4), tracking a target; (5), filtering the target; (6), identifying the target; (7), analyzing a target behaviour; and (8), giving an alarm to prevent the power transmission line from being externally broken. According to the invention, the intelligent analysis method for preventing the power transmission line from being externally broken based on the behaviour analysis technology is provided for requirements for preventing the power transmission line of a power system from being externally broken; therefore, detecting, tracking and identifying of a motion target can be realized; and in addition, the type of the target behaviour can be accurately judged.
Description
Technical field
The method that the present invention relates to the external force damage prevention of a kind of transmission line of electricity, particularly to the method for transmission line of electricity video external force damage prevention.
Background technology
Electric power facility external force damage prevention intelligent analysis system combines the correlation techniques such as Digital Image Processing, computer vision and machine learning, the moving target in camera supervised video carries out detection in real time, follows the tracks of and identify, and is analyzed judging to the behavior of target.Difference according to target behavior classification, pushes different grades of early warning report automatically.
Electric power facility external force damage prevention can be divided into indoor and outdoor two kinds of application scenarios.The situation that wherein Migrant women and toy are mainly invaded power distribution station by indoor scene is identified analysis, and outdoor scene is then need to be identified the kinestate of the Large Construction vehicle such as crane, excavator, behavior and the Harm to transmission line of electricity thereof analyzing.Traditional electric power facility external force damage prevention mainly adopts the method such as manual inspection and camera supervised video recording, and it major downside is that needs to expend bigger human resources, and cannot accomplish that real-time response is reported to the police for event broken outside electric power facility.
In intelligent video analysis algorithm, existing universal video tracking recognizer is capable of the detection to moving target, follows the tracks of and identify.And in target behavior analysis, universal video tracking recognizer cannot judge the specific objective behavior type being likely to transmission line of electricity is worked the mischief, for instance arm raised by crane.
Summary of the invention
1, technical problem to be solved:
Existing electric power facility external force damage prevention adopts the method such as manual inspection and camera supervised video recording, and it major downside is that needs to expend bigger human resources, and cannot accomplish that real-time response is reported to the police for event broken outside electric power facility.The specific objective behavior being likely to transmission line of electricity is worked the mischief cannot be judged in goal analysis, it is impossible to target behavior type is judged accurately at intelligent video analysis algorithm.
2, technical scheme:
In order to solve problem above, the method that the invention provides the transmission line of electricity video external force damage prevention of a kind of Behavior-based control analytical technology, comprise the following steps: step one, image acquisition, the original image of camera acquisition is carried out pretreatment by image acquisition, strengthens and noise reduction process including the convergent-divergent of image, contrast；Step 2, motion detection, the region having target to occur, by increasing Rule of judgment in the more New Policy in background modeling, is carried out locking background process by motion detection；Step 3, block detect, and are detected the block structure body array representation of the motion block in foreground image by block；Step 4, target following, in the tracking process of target, the generation selection foreground blocks that the target occurred in former frame is extracted in the current frame is mated, choose suitable foreground blocks matched, determine certain moving target in certain foreground blocks correspondence former frame of present frame in the process of constantly coupling, then constantly clarification of objective parameter is updated；Step 5, goal filtering, goal filtering is filtered according to the size of target, color, shape, movement velocity, direction and movement locus；Step 6, target recognition, target recognition is for carry out Classification and Identification to target；Step 7, target behavior analysis, after determining target type, carry out target behavior analysis targetedly, described target behavior is divided into general objectives behavior and specific objective behavior two class, described general objectives behavior refers to the behavior type that moving target all has, swarming into first including target, leave, repeat to swarm into, hover and stopping situation, described specific objective behavior is the target behavior of certain types of target；Step 8, external force damage prevention are reported to the police, after determining target type and target behavior, according to whether rule judgment set in advance there is broken event outside electric power facility, when judging that determining that generation is outer breaks event, intelligent analysis system will push alarming short message, picture and warning video by wireless network, it is to avoid causes serious electric power facility damage accident.
Further, complete on the basis of described motion detection, target following, target recognition, target behavior analysis, electric power facility scene modeling can be carried out, model of place includes static layer, dynamic layer and three parts of statistics layer, wherein static layer is for representing the fixing object in electric power facility scene, dynamic layer is for representing the moving target in scene, and statistics layer, by analyzing the target frequency of occurrence in each region in scene, calculates and obtains goal activities hot spot region figure.
3, beneficial effect:
The present invention is directed to the transmission line of electricity external force damage prevention demand of power system, it is proposed to the external force damage prevention intelligent analysis method of a kind of Behavior-based control analytical technology, the detection of moving target can not only be realized, follow the tracks of and identify, additionally it is possible to target behavior type is judged accurately.
Accompanying drawing explanation
Fig. 1 is transmission line of electricity video external force damage prevention algorithm flow chart.
Detailed description of the invention
The present invention is described in detail below.
Step one, image acquisition
The original image of camera acquisition is carried out pretreatment by image acquisition, processes including the convergent-divergent of image, contrast enhancing and noise reduction etc..It it is high-resolution situation such as 720P, 1080P for original image, it is possible to original image is contracted to relatively low resolution, to reduce the amount of calculation of subsequent motion detection algorithm, it is ensured that the real-time process that moving object detection is followed the tracks of.
Step 2, motion detection
Described motion detection is the situation of change by pixel each in analysis video image, the pixel wherein changed greatly is judged as motor image vegetarian refreshments, change less pixel and be judged as background pixel point, motion detection have employed the VIBE algorithm of a kind of improvement, by the more New Policy in background modeling increases Rule of judgment, the region having target to occur is carried out locking background process.
Adopting the VIBE algorithm improved is the detection in order to realize static target, and basic motion detection algorithm is only used for detection moving target, can fade away when target transfers to static from kinestate.
The input of motion detection block is colored or gray level image, is output as the binary image of foreground moving object.
Step 3, block detect
The detection of described block method particularly includes: analyze all connected domains in foreground image, then by the position of each connected domain, size parameter block array representation.
Step 4, target following
Described target following adopts the track algorithm based on Kalman filtering.Moving target generally at least has three kinds of states in video monitoring scene: target first time enters monitoring scene, target and moves in the scene and tracked, target exits from scene.In the tracking process of target, need the generation selection foreground blocks that the target occurred in former frame is extracted in the current frame is mated, choose suitable foreground blocks matched, certain moving target in certain foreground blocks correspondence former frame of present frame is determined in the process of constantly coupling, then constantly clarification of objective parameter is updated, it is achieved thereby that the tracking of target between frame and frame.
Step 5, goal filtering
Goal filtering is filtered according to the size of target, color, shape, movement velocity, direction and movement locus.Size characteristic for target, it is necessary to calculate target projection size in original image according to camera parameters.If the target size followed the tracks of is less than minimum size threshold, or more than full-size threshold value, is then regarded as noise and filters.In outdoor scene, can by the interference filtering such as pedestrian and bicycle by minimum size threshold.Color characteristic for target, it is possible to target image is converted to hsv color space and processes.In the HSV image of target, according to panel tone set in advance, saturation and luminance threshold scope, the pixel number that statistics satisfies condition.If pixel number is less than the percentage ratio parameter set, then it is regarded as noise and filters.
Step 6, target recognition
Target recognition is for carry out Classification and Identification to target.Described target recognition includes single frames target recognition and multiple frame cumulation identification, described single frames target recognition is that the target in single frame video image is carried out Classification and Identification, described multiple frame cumulation is identified as on the basis of single frames target recognition, by the recognition result of multiple frame cumulation, target is carried out Classification and Identification.
Described single frames target recognition adopts degree of deep learning method that the target in single frame video image is carried out Classification and Identification.The method needs to gather substantial amounts of sample data, then passes through sample data and deep neural network is trained, it is possible to realize higher recognition accuracy.Difference according to application scenarios, it is necessary to gather corresponding target recognition sample respectively.For indoor scene, mainly personnel and toy are carried out Classification and Identification.For outdoor scene, Large Construction vehicle such as crane, excavator etc. and other types vehicle such as car, truck, Bus Carriage etc. that mainly road pavement travels carry out Classification and Identification.Using self-built vehicle classification Sample Storehouse that single frames target recognition module is trained, this Sample Storehouse comprises the type of vehicle such as crane, car, truck at the sample image of different angles, is mainly used in the Classification and Identification of crane and other types vehicle.
On the basis of single frames target recognition, by the recognition result of multiple frame cumulation, target is carried out Classification and Identification, thus realizing higher recognition accuracy.
When described multiple frame cumulation identification is divided into k kind type for target, the computing formula of multiple frame cumulation identification is:
In formula, N is target type sum,For the probability that target is kth class,For the target migration index in kth class,For the target multiple frame cumulation identification number of times in kth class,For target in all types of accumulation identification number of times summations.
By changingRate of false alarm and the rate of failing to report of target recognition can be adjusted.Such as by increasing, it is possible to reduce the target rate of failing to report in kth class, but the rate of false alarm of target can be increased simultaneously.By multiple frame cumulation identification module being tested in the mode of actual scene video recording, sectional drawing, the time of 4 tests is 7:00 to 17:00 in afternoon in the morning, and the vehicle fleet that statistics is passed by is 9748, and wherein crane wrong report number is 233, and average rate of false alarm is 2.5%.
Step 7, target behavior analysis
Described target behavior is divided into general objectives behavior and specific objective behavior two class, described general objectives behavior refers to the behavior type that moving target all has, swarming into first including target, leave, repeat to swarm into, hover and stopping situation, described specific objective behavior is the target behavior of certain types of target.
The target behavior analysis of described general objectives behavior is: start target is tracked after target enters monitoring scene, monitoring scene is arranged as required to one or more detection region, each detection region can be arranged corresponding target behavior analytical parameters, with the application demand of satisfied reality.General objectives behavior is by the position of combining target, kinestate and movement time parameter, the method adopting rule judgment, the method of rule judgment is: be identified, and when target first time enters in detection region from detection region exterior, definition target behavior type is for swarm into first；When target leaves detection region, definition target behavior type is for leaving；When being again introduced into after target is left in detection region, definition target behavior type, for repeating to swarm into, starts timing after target enters detection region, arranges threshold speed Vth1、Vth2For judging the kinestate of target, if target speed average Vmean<Vth1Then judge that target is resting state, Vmean>Vth2Then judge that target is kinestate, Vth1<Vmean<Vth2Then judge that target is as the criterion resting state, arranges time threshold Tth1、Tth2For judging the behavior type of target.If the time T that target is kept in motion in detection regionM>Tth1, then judge that target behavior type is as hovering.If the time T that target remains static in detection regionS>Tth2, then judge that target behavior type is as stopping.
Described specific objective behavior is that arm raised by crane, when judging the behavior type of this target as stopping, then runs and raises arm detection algorithm and determine whether to raise arm behavior, raise arm detection algorithm as follows: set the target position coordinates in halted state as (x0,y0), the height and the width of target respectively h0,w0, then raise arm and detect first to target stop position (x0,y0) rectangular area, top carry out motion detection, the position coordinates in this region is (x0,y0+h0), the height and the width respectively a*h in detection region0,b*h0, wherein a, b are that detection region height, width are relative to the proportionality coefficient of object height, it is possible to statistics is determined by experiment.After raising above target finds moving object in arm detection region, it is possible to the movement locus at this moving object top is analyzed.If the starting point of movement locus is (xt0,yt0), trail termination point is (xt1,yt1), path length.If path length L is more than the threshold value L setth, and the direction of movement locus is from the bottom up, then be judged as that arm raised by crane.
Step 8, external force damage prevention are reported to the police
After determining target type and target behavior, it is possible to according to whether rule judgment set in advance broken event outside electric power facility occurs.When judging that determining that generation is outer breaks event, intelligent analysis system will push alarming short message, picture and warning video by wireless network, it is to avoid causes serious electric power facility damage accident.
Step 9, electric power facility scene modeling
Complete on the basis that motion detection, target following, identification and target behavior are analyzed, it is possible to carry out electric power facility scene modeling.Model of place includes static layer, dynamic layer and three parts of statistics layer.Wherein static layer is for representing the fixing object in electric power facility scene, for instance the instrument cabinet in indoor scene and the steel tower in outdoor scene, building etc..Fixing object can adopt human configuration parameter or automatically identify location algorithm be really sized, shape and position.Dynamic layer is then for representing moving target in scene, for instance personnel in indoor scene and toy, and the Large Construction vehicle in outdoor scene and other types vehicle.The parameter of moving target can be determined by target following and Target Recognition Algorithms.Statistics layer is then by analyzing the target frequency of occurrence in each region in scene, calculating and obtain goal activities hot spot region figure.
Compared with prior art, provide the benefit that produced by electric power facility external force damage prevention intelligent analysis system provided by the invention: by adjusting systematic parameter, it is possible to adapt to the electric power facility external force damage prevention demand of several scenes.At indoor scene, it is achieved personnel's intrusion detection and Activity recognition analysis.At outdoor scene, it is achieved the Real time identification analysis that the Large Construction vehicle such as kinestate such as crane, excavator and behavior type (are swarmed into, hover, stop, being raised arm etc.).When detecting region and broken event outside electric power facility occurring, it is possible to accurately identify and respond rapidly to report to the police, push alarming short message, picture and warning video by wireless network, it is to avoid cause serious electric power facility damage accident.
Claims (10)
1. a method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology, comprises the following steps: step one, image acquisition, and the original image of camera acquisition is carried out pretreatment by image acquisition, strengthens and noise reduction process including the convergent-divergent of image, contrast；Step 2, motion detection, the region having target to occur, by increasing Rule of judgment in the more New Policy in background modeling, is carried out locking background process by motion detection；Step 3, block detect, and are detected the block structure body array representation of the motion block in foreground image by block；Step 4, target following, in the tracking process of target, the generation selection foreground blocks that the target occurred in former frame is extracted in the current frame is mated, choose suitable foreground blocks matched, determine certain moving target in certain foreground blocks correspondence former frame of present frame in the process of constantly coupling, then constantly clarification of objective parameter is updated；Step 5, goal filtering, goal filtering is filtered according to the size of target, color, shape, movement velocity, direction and movement locus；Step 6, target recognition, target recognition is for carry out Classification and Identification to target；Step 7, target behavior analysis, after determining target type, carry out target behavior analysis targetedly, described target behavior is divided into general objectives behavior and specific objective behavior two class, described general objectives behavior refers to the behavior type that moving target all has, swarming into first including target, leave, repeat to swarm into, hover and stopping situation, described specific objective behavior is the target behavior of certain types of target；Step 8, external force damage prevention are reported to the police, after determining target type and target behavior, according to whether rule judgment set in advance there is broken event outside electric power facility, when judging that determining that generation is outer breaks event, intelligent analysis system will push alarming short message, picture and warning video by wireless network, it is to avoid causes serious electric power facility damage accident.
2. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1, it is characterized in that: complete described motion detection, target following, target recognition, on the basis that target behavior is analyzed, electric power facility scene modeling can be carried out, model of place includes static layer, dynamic layer and three parts of statistics layer, wherein static layer is for representing the fixing object in electric power facility scene, dynamic layer is for representing the moving target in scene, statistics layer is by analyzing the target frequency of occurrence in each region in scene, calculating obtains goal activities hot spot region figure.
3. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterized in that: described motion detection is the situation of change by pixel each in analysis video image, the pixel wherein changed greatly is judged as motor image vegetarian refreshments, change less pixel and be judged as background pixel point, motion detection have employed the VIBE algorithm of a kind of improvement, by the more New Policy in background modeling increases Rule of judgment, the region having target to occur is carried out locking background process.
4. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterized in that: the detection of described block method particularly includes: analyze all connected domains in foreground image, then by the position of each connected domain, size parameter block array representation.
5. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterised in that: described target following adopts the track algorithm based on Kalman filtering.
6. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterized in that: described target recognition includes single frames target recognition and multiple frame cumulation identification, described single frames target recognition is that the target in single frame video image is carried out Classification and Identification, described multiple frame cumulation is identified as on the basis of single frames target recognition, by the recognition result of multiple frame cumulation, target is carried out Classification and Identification.
7. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 6, it is characterised in that: described single frames target recognition adopts degree of deep learning method that the target in single frame video image is carried out Classification and Identification.
8. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 6, it is characterised in that: when described multiple frame cumulation identification is divided into k kind type for target, the computing formula of multiple frame cumulation identification is:
In formula, N is target type sum,For the probability that target is kth class,For the target migration index in kth class,For the target multiple frame cumulation identification number of times in kth class,For target in all types of accumulation identification number of times summations.
9. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterized in that: the target behavior analysis of described general objectives behavior is: start target is tracked after target enters monitoring scene, monitoring scene is arranged as required to one or more detection region, each detection region can be arranged corresponding target behavior analytical parameters, application demand with satisfied reality, the general objectives behavior position by combining target, kinestate and movement time parameter, the method adopting rule judgment is identified, when target first time enters in detection region from detection region exterior, definition target behavior type is for swarm into first；When target leaves detection region, definition target behavior type is for leaving；When being again introduced into after target is left in detection region, definition target behavior type, for repeating to swarm into, starts timing after target enters detection region, arranges threshold speed Vth1、Vth2For judging the kinestate of target, if target speed average Vmean<Vth1Then judge that target is resting state, Vmean>Vth2Then judge that target is kinestate, Vth1<Vmean<Vth2Then judge that target is as the criterion resting state, arranges time threshold Tth1、Tth2For judging the behavior type of target, if the time T that target is kept in motion in detection regionM>Tth1, then judge that target behavior type is as hovering, if the time T that target remains static in detection regionS>Tth2, then judge that target behavior type is as stopping.
10. the method for the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology as claimed in claim 1 or 2, it is characterized in that: described specific objective behavior is that arm raised by crane, when judging the behavior type of this target as stopping, then run and raise arm detection algorithm and determine whether to raise arm behavior, raise arm detection algorithm as follows: set the target position coordinates in halted state as (x0,y0), the height and the width of target respectively h0,w0, then raise arm and detect first to target stop position (x0,y0) rectangular area, top carry out motion detection, the position coordinates in this region is (x0,y0+h0), the height and the width respectively a*h in detection region0,b*h0, wherein a, b are that detection region height, width are relative to the proportionality coefficient of object height, statistics is determined by experiment, the movement locus at this moving object top is analyzed, if the starting point of movement locus is (x after finding moving object in arm detection region by raising above targett0,yt0), trail termination point is (xt1,yt1), path lengthIf path length L is more than the threshold value L setth, and the direction of movement locus is from the bottom up, then be judged as that arm raised by crane.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610174705.4A CN105744232B (en) | 2016-03-25 | 2016-03-25 | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610174705.4A CN105744232B (en) | 2016-03-25 | 2016-03-25 | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105744232A true CN105744232A (en) | 2016-07-06 |
| CN105744232B CN105744232B (en) | 2017-12-12 |
Family
ID=56251441
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610174705.4A Active CN105744232B (en) | 2016-03-25 | 2016-03-25 | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105744232B (en) |
Cited By (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056821A (en) * | 2016-08-13 | 2016-10-26 | 哈尔滨理工大学 | Power-transmission-line foreign-matter-invasion intelligent-video on-line monitoring evaluation system |
| CN106339723A (en) * | 2016-08-30 | 2017-01-18 | 天津天地伟业数码科技有限公司 | Video based river illegal dredging detection method |
| CN106778472A (en) * | 2016-11-17 | 2017-05-31 | 成都通甲优博科技有限责任公司 | The common invader object detection and recognition method in transmission of electricity corridor based on deep learning |
| CN107679495A (en) * | 2017-10-09 | 2018-02-09 | 济南大学 | A kind of detection method of transmission line of electricity periphery activity engineering truck |
| CN107820051A (en) * | 2017-11-07 | 2018-03-20 | 北京京电电网维护集团有限公司 | Monitoring system and its monitoring method and device |
| CN108109385A (en) * | 2018-01-18 | 2018-06-01 | 南京杰迈视讯科技有限公司 | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method |
| CN108307146A (en) * | 2017-12-12 | 2018-07-20 | 张宝泽 | A kind of ultra-high-tension power transmission line Security Vulnerability Detecting System and method |
| CN108805207A (en) * | 2018-06-13 | 2018-11-13 | 江苏电力信息技术有限公司 | A kind of Large Construction vehicle raises arm detection algorithm |
| CN108875535A (en) * | 2018-02-06 | 2018-11-23 | 北京旷视科技有限公司 | image detecting method, device and system and storage medium |
| CN109040604A (en) * | 2018-10-23 | 2018-12-18 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109167893A (en) * | 2018-10-23 | 2019-01-08 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109460719A (en) * | 2018-10-24 | 2019-03-12 | 四川阿泰因机器人智能装备有限公司 | A kind of electric operating safety recognizing method |
| CN109785361A (en) * | 2018-12-22 | 2019-05-21 | 国网内蒙古东部电力有限公司 | Substation's foreign body intrusion detection system based on CNN and MOG |
| CN110097723A (en) * | 2019-04-17 | 2019-08-06 | 南京砺剑光电技术研究院有限公司 | Outer broken Activity recognition and alarm method based on computer vision |
| CN110414375A (en) * | 2019-07-08 | 2019-11-05 | 北京国卫星通科技有限公司 | Recognition methods, device, storage medium and the electronic equipment of low target |
| CN110490121A (en) * | 2019-08-14 | 2019-11-22 | 北京国网信通埃森哲信息技术有限公司 | A kind of transmission line of electricity external force damage prevention method and system for clapping image recognition based on more prisons |
| CN110689706A (en) * | 2019-10-11 | 2020-01-14 | 广东电网有限责任公司 | Method, device and system for monitoring large construction vehicle under overhead line |
| CN110837079A (en) * | 2018-08-16 | 2020-02-25 | 杭州海康威视数字技术股份有限公司 | Target detection method and device based on radar |
| CN111461010A (en) * | 2020-04-01 | 2020-07-28 | 贵州电网有限责任公司 | Power equipment identification efficiency optimization method based on template tracking |
| CN112584095A (en) * | 2020-11-25 | 2021-03-30 | 国家电网有限公司 | Intelligent pole tower external damage prevention monitoring method based on 3D convolution technology |
| CN114973571A (en) * | 2022-05-23 | 2022-08-30 | 贵州天然气管网有限责任公司 | Natural gas unattended station target object invasion and residence monitoring system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110016342A1 (en) * | 2009-07-20 | 2011-01-20 | Viridity Software, Inc. | Techniques for power analysis |
| CN102096977A (en) * | 2010-11-26 | 2011-06-15 | 上海电力带电作业技术开发有限公司 | Method for video monitoring and prewarning of intrusive external force |
| CN102547244A (en) * | 2012-01-17 | 2012-07-04 | 深圳辉锐天眼科技有限公司 | Video monitoring method and system |
| CN102968802A (en) * | 2012-11-28 | 2013-03-13 | 无锡港湾网络科技有限公司 | Moving target analyzing and tracking method and system based on video monitoring |
| CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
| CN105184258A (en) * | 2015-09-09 | 2015-12-23 | 苏州科达科技股份有限公司 | Target tracking method and system and staff behavior analyzing method and system |
-
2016
- 2016-03-25 CN CN201610174705.4A patent/CN105744232B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110016342A1 (en) * | 2009-07-20 | 2011-01-20 | Viridity Software, Inc. | Techniques for power analysis |
| CN102096977A (en) * | 2010-11-26 | 2011-06-15 | 上海电力带电作业技术开发有限公司 | Method for video monitoring and prewarning of intrusive external force |
| CN102547244A (en) * | 2012-01-17 | 2012-07-04 | 深圳辉锐天眼科技有限公司 | Video monitoring method and system |
| CN102968802A (en) * | 2012-11-28 | 2013-03-13 | 无锡港湾网络科技有限公司 | Moving target analyzing and tracking method and system based on video monitoring |
| CN104915655A (en) * | 2015-06-15 | 2015-09-16 | 西安电子科技大学 | Multi-path monitor video management method and device |
| CN105184258A (en) * | 2015-09-09 | 2015-12-23 | 苏州科达科技股份有限公司 | Target tracking method and system and staff behavior analyzing method and system |
Cited By (29)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106056821A (en) * | 2016-08-13 | 2016-10-26 | 哈尔滨理工大学 | Power-transmission-line foreign-matter-invasion intelligent-video on-line monitoring evaluation system |
| CN106056821B (en) * | 2016-08-13 | 2018-04-24 | 哈尔滨理工大学 | Electric line foreign matter intrusion intelligent video monitors assessment system on-line |
| CN106339723A (en) * | 2016-08-30 | 2017-01-18 | 天津天地伟业数码科技有限公司 | Video based river illegal dredging detection method |
| CN106778472A (en) * | 2016-11-17 | 2017-05-31 | 成都通甲优博科技有限责任公司 | The common invader object detection and recognition method in transmission of electricity corridor based on deep learning |
| CN107679495A (en) * | 2017-10-09 | 2018-02-09 | 济南大学 | A kind of detection method of transmission line of electricity periphery activity engineering truck |
| CN107679495B (en) * | 2017-10-09 | 2020-08-07 | 济南大学 | Detection method for movable engineering vehicles around power transmission line |
| CN107820051A (en) * | 2017-11-07 | 2018-03-20 | 北京京电电网维护集团有限公司 | Monitoring system and its monitoring method and device |
| CN108307146A (en) * | 2017-12-12 | 2018-07-20 | 张宝泽 | A kind of ultra-high-tension power transmission line Security Vulnerability Detecting System and method |
| CN108109385A (en) * | 2018-01-18 | 2018-06-01 | 南京杰迈视讯科技有限公司 | A kind of vehicle identification of power transmission line external force damage prevention and hazardous act judgement system and method |
| CN108875535A (en) * | 2018-02-06 | 2018-11-23 | 北京旷视科技有限公司 | image detecting method, device and system and storage medium |
| CN108875535B (en) * | 2018-02-06 | 2023-01-10 | 北京旷视科技有限公司 | Image detection method, device and system and storage medium |
| CN108805207B (en) * | 2018-06-13 | 2020-08-04 | 江苏电力信息技术有限公司 | Method for detecting large construction vehicle lifting arm |
| CN108805207A (en) * | 2018-06-13 | 2018-11-13 | 江苏电力信息技术有限公司 | A kind of Large Construction vehicle raises arm detection algorithm |
| CN110837079B (en) * | 2018-08-16 | 2021-10-19 | 杭州海康威视数字技术股份有限公司 | Target detection method and device based on radar |
| CN110837079A (en) * | 2018-08-16 | 2020-02-25 | 杭州海康威视数字技术股份有限公司 | Target detection method and device based on radar |
| CN109040604A (en) * | 2018-10-23 | 2018-12-18 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109167893A (en) * | 2018-10-23 | 2019-01-08 | Oppo广东移动通信有限公司 | Shoot processing method, device, storage medium and the mobile terminal of image |
| CN109167893B (en) * | 2018-10-23 | 2021-04-27 | Oppo广东移动通信有限公司 | Shot image processing method and device, storage medium and mobile terminal |
| CN109040604B (en) * | 2018-10-23 | 2020-09-15 | Oppo广东移动通信有限公司 | Shot image processing method and device, storage medium and mobile terminal |
| CN109460719A (en) * | 2018-10-24 | 2019-03-12 | 四川阿泰因机器人智能装备有限公司 | A kind of electric operating safety recognizing method |
| CN109785361A (en) * | 2018-12-22 | 2019-05-21 | 国网内蒙古东部电力有限公司 | Substation's foreign body intrusion detection system based on CNN and MOG |
| CN110097723A (en) * | 2019-04-17 | 2019-08-06 | 南京砺剑光电技术研究院有限公司 | Outer broken Activity recognition and alarm method based on computer vision |
| CN110414375A (en) * | 2019-07-08 | 2019-11-05 | 北京国卫星通科技有限公司 | Recognition methods, device, storage medium and the electronic equipment of low target |
| CN110490121A (en) * | 2019-08-14 | 2019-11-22 | 北京国网信通埃森哲信息技术有限公司 | A kind of transmission line of electricity external force damage prevention method and system for clapping image recognition based on more prisons |
| CN110689706A (en) * | 2019-10-11 | 2020-01-14 | 广东电网有限责任公司 | Method, device and system for monitoring large construction vehicle under overhead line |
| CN111461010A (en) * | 2020-04-01 | 2020-07-28 | 贵州电网有限责任公司 | Power equipment identification efficiency optimization method based on template tracking |
| CN111461010B (en) * | 2020-04-01 | 2022-08-12 | 贵州电网有限责任公司 | Power equipment identification efficiency optimization method based on template tracking |
| CN112584095A (en) * | 2020-11-25 | 2021-03-30 | 国家电网有限公司 | Intelligent pole tower external damage prevention monitoring method based on 3D convolution technology |
| CN114973571A (en) * | 2022-05-23 | 2022-08-30 | 贵州天然气管网有限责任公司 | Natural gas unattended station target object invasion and residence monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105744232B (en) | 2017-12-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105744232A (en) | Method for preventing power transmission line from being externally broken through video based on behaviour analysis technology | |
| CN106652465B (en) | Method and system for identifying abnormal driving behaviors on road | |
| CN111860274B (en) | Traffic police command gesture recognition method based on head orientation and upper half skeleton characteristics | |
| CN101458871B (en) | Intelligent traffic analysis system and application system thereof | |
| CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
| CN103456024B (en) | A kind of moving target gets over line determination methods | |
| CN102426785B (en) | Traffic flow information perception method based on contour and local characteristic point and system thereof | |
| CN105513349A (en) | Double-perspective learning-based mountainous area highway vehicle event detection method | |
| CN100454355C (en) | Video method for collecting information of vehicle flowrate on road in real time | |
| CN102164270A (en) | Intelligent video monitoring method and system capable of exploring abnormal events | |
| CN104601965A (en) | Camera shielding detection method | |
| CN103400111A (en) | Method for detecting fire accident on expressway or in tunnel based on video detection technology | |
| CN103605967A (en) | Subway fare evasion prevention system and working method thereof based on image recognition | |
| CN104966304A (en) | Kalman filtering and nonparametric background model-based multi-target detection tracking method | |
| CN107886055A (en) | A kind of retrograde detection method judged for direction of vehicle movement | |
| CN101727748A (en) | Method, system and equipment for monitoring vehicles based on vehicle taillight detection | |
| CN111553214B (en) | Method and system for detecting smoking behavior of driver | |
| CN103345842A (en) | Road vehicle classification system and method | |
| CN103530640A (en) | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) | |
| CN114781479A (en) | Traffic incident detection method and device | |
| CN112084928A (en) | Road traffic accident detection method based on visual attention mechanism and ConvLSTM network | |
| CN110097571B (en) | Quick high-precision vehicle collision prediction method | |
| CN111985295A (en) | Electric bicycle behavior recognition method and system, industrial personal computer and camera | |
| CN103455997A (en) | Derelict detection method and system | |
| CN100546380C (en) | Target detection and tracking at night based on visual characteristic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |