CN110691224A - Transformer substation perimeter video intelligent detection system - Google Patents
Transformer substation perimeter video intelligent detection system Download PDFInfo
- Publication number
- CN110691224A CN110691224A CN201911062983.0A CN201911062983A CN110691224A CN 110691224 A CN110691224 A CN 110691224A CN 201911062983 A CN201911062983 A CN 201911062983A CN 110691224 A CN110691224 A CN 110691224A
- Authority
- CN
- China
- Prior art keywords
- video
- unit
- alarm
- processing
- target
- 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
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- G08B13/19606—Discriminating between target movement or movement in an area of interest and other non-signicative movements, e.g. target movements induced by camera shake or movements of pets, falling leaves, rotating fan
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a transformer substation perimeter video intelligent detection system, which comprises: the front-end video acquisition processing module comprises a video acquisition unit and a video processing unit, acquires and preprocesses field video data in real time, and extracts a dynamic target in the current scene; the data transmission pushing module is used for data transmission and instruction issuing among the modules; the back-end server identification processing module is used for identifying the type of the foreign matters, dividing alarm grades and generating processing instructions; and the field driving away warning module is used for alarming and processing instructions of the field intrusion foreign matters. Compared with the prior art, the invention carries out omnibearing monitoring by means of image processing, and effectively makes up the limitation of the detection range of the traditional electronic fence; the background server is used for identifying and classifying the detected foreign matters, and the medicine is issued according to different foreign matter types, so that the driving warning effectiveness during foreign matter invasion is greatly improved, and the threat of the foreign matter invasion to the normal operation of the transformer substation is reduced.
Description
Technical Field
The invention relates to the field of transformer substation safety protection, in particular to a transformer substation perimeter video intelligent detection system.
Background
The safe and stable operation of the power station is the core requirement of the whole production process. Most transformer substations are remote in installation position and installed outdoors, and often can be invaded by foreign matters, so that the safe and stable operation of power production is seriously threatened, and unmanned and intelligent effects are gradually realized when the condition of a power station is mature. Meanwhile, with the continuous development of video technology, video technology and intelligent detection technology are widely applied in the field of power systems, wherein the video intelligent detection technology is the main application field thereof. It is very necessary to automatically identify foreign matters and alarm the monitored scene by using the video intelligent detection technology and take corresponding measures in time.
Some video foreign matter alarm devices appear in the market at present, but the equipment can only detect the dynamically moving target in the current scene, can not specifically identify the type of the foreign matter, and has no specific solution for eliminating the interference of the foreign matter aiming at the invasion of the foreign matter. And the influence of external factors inevitably causes the shaking of the monitoring probe, thereby causing the alarming of foreign matters in a large range.
Most of the existing substation electronic fences adopt an infrared triggering mode. Once the system is installed, the set detection area and the set detection height are fixed, and the system is difficult to modify adaptively in the follow-up process; moreover, because the infrared light beams have the characteristic of propagating along straight lines, the fixed infrared transmitting and receiving devices are difficult to be flexibly arranged according to the field conditions; in addition, because the linear light beam is used as an alarm trigger signal, once an intruder grasps the equipment arrangement characteristics and crosses the detection light beam, the detection logic of the system can be skipped, and great potential safety hazard exists.
Disclosure of Invention
The invention aims to provide a transformer substation perimeter video intelligent detection system for overcoming the defects of poor applicability, low video monitoring manual viewing efficiency and high false alarm rate of the conventional transformer substation electronic fence.
The purpose of the invention can be realized by the following technical scheme:
a transformer substation perimeter video intelligent detection system comprises:
the front-end video acquisition processing module comprises a video acquisition unit and a video processing unit, acquires and preprocesses field video data in real time, and extracts a dynamic target in the current scene;
the data transmission pushing module is used for realizing data transmission among the modules and real-time communication among the operation and maintenance personnel terminals by utilizing a 4G communication technology;
the back-end server identification processing module is used for identifying the type of the foreign matters, dividing alarm grades and generating processing instructions;
and the field driving away warning module is used for alarming and processing instructions of the field intrusion foreign matters.
The video acquisition unit acquires video data in real time under a current scene, the video processing unit performs Gaussian blurring processing on the real-time video data, then extracts a foreground binaryzation image by using a three-frame difference method, and performs median filtering, down-sampling, expansion, corrosion and up-sampling on the binaryzation image in sequence, so that a dynamic target is accurately extracted.
Before the video processing unit carries out Gaussian blurring processing, an interested area is firstly divided in a current detection area, trees, lights and roads of which the shapes are changed by external factors or self factors (false detection caused by tree shaking, light flickering and road traffic flow) in the interested area in a short time are shielded, and the pixel value of an object with a large dynamic range change is set as a fixed value, so that the part of the object does not participate in subsequent image processing operation.
After the video processing unit collects video data, according to the number and the position of dynamic targets appearing in a current processed video frame, screening a dynamic target extraction result by setting a pixel point threshold value occupied by the targets, if the pixel point occupied by the dynamic targets is smaller than the threshold value, the targets are considered not to be foreign matters, otherwise, the targets are determined to be foreign matters.
The back-end server identification processing module comprises:
the target identification unit is used for generating a foreign matter identification training set by manually marking foreign matters, identifying foreign matters based on TensorFlow, identifying foreign matter images by manually marking the foreign matter identification training set and training a foreign matter identification model, and identifying floaters such as flying birds, personnel, vehicles, balloons, kites and the like;
the intrusion event processing unit is used for receiving the target identification result of the target identification unit, dividing different alarm levels according to different foreign matter types and adopting corresponding processing measures, recording the name of the current alarm transformer substation, the serial number of the alarm camera, the alarm time and the corresponding alarm level immediately once the foreign matter type information is received, then generating a report of the event and sending the report to related operation and maintenance personnel;
and the model optimization upgrading unit retrains the foreign matter recognition model by utilizing the error of the daily alarm information, so that the accuracy of the recognition of the target recognition unit is improved.
Before the system is put into use, the back-end server identification processing module collects data of a current detection area, counts the number of alarm events of the same frame of video data in the current detection area, and sets an alarm event number threshold; after the system is put into use, if the number of alarm events exceeding the current detection area exceeds a threshold value, no alarm is given.
The target identification unit identifies the identity of a person through the color of whether the person wears a safety helmet or not and whether the entering vehicle is a working vehicle or not according to the uniform coating identification of the working vehicle, and if the identification result shows that the invading person and vehicle are the working person and the working vehicle, the person and vehicle do not enter the alarm process.
The on-site driving-away warning module comprises an ultrasonic driving-away unit and a personnel invasion warning driving-away unit, the ultrasonic driving-away unit drives away birds intruding into the overhead of the power equipment of the transformer substation by utilizing ultrasonic waves, and the personnel invasion warning driving-away unit warns non-working personnel and non-working vehicles through signals such as sound, light and the like;
aiming at the invasion of air floating objects such as kites, balloons and the like, the alarm priority is set to be the highest, and a report of the invasion event is immediately sent to an operation and maintenance personnel terminal, so that the operation and maintenance personnel are required to pay close attention to the foreign matter condition on site, and the early treatment is realized. And after receiving the alarm report, the operation and maintenance personnel can evaluate the alarm, and if the alarm information is not consistent with the actual condition, the operation and maintenance personnel revise the information and upload the information to the model optimization and upgrade unit. The corrected alarm information can optimize the recognition model to improve the accuracy of the recognition of the target recognition unit.
Compared with the prior art, the invention has the following advantages:
(1) the omnibearing monitoring is carried out through the means of image processing, and the limitation of the detection range of the traditional electronic fence is effectively made up.
(2) The background server is used for identifying and classifying the detected foreign matters, and the medicine is issued according to different foreign matter types, so that the driving warning effectiveness during foreign matter invasion is greatly improved, and the threat of the foreign matter invasion to the normal operation of the transformer substation is reduced.
(3) Compared with the past detection and prevention mode, the operation and maintenance personnel can timely receive the information such as the picture, the type and the invasion state of the invaded foreign matter, the efficiency of troubleshooting is improved, and the problem of manual core peer-to-peer after the electronic fence is misreported is solved.
(4) Before the system is put into use, the back-end server identification processing module collects data of a current detection area, counts the number of alarm events of the same frame of video data in the current detection area, and sets an alarm event number threshold; after the device is put into use, if the number of alarm events exceeding the current detection area exceeds a threshold value, no alarm is given, and the anti-jitter performance of the device is effectively improved.
Drawings
Fig. 1 is a schematic diagram of the field layout of the present embodiment.
Fig. 2 is a schematic diagram of the system structure of the present embodiment.
Fig. 3 is a flowchart of the front-end video acquisition processing module according to this embodiment.
Fig. 4 is a schematic diagram illustrating the principle of removing the effect of shake in a single group of camera views according to this embodiment.
FIG. 5 is a logic diagram of the recognition alarm of the present embodiment.
Detailed Description
The invention is described in detail below with reference to the figures and specific embodiments. The present embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation manner and a specific operation process are given, but the scope of the present invention is not limited to the following embodiments.
Examples
As shown in fig. 1 and 2, a transformer substation perimeter video intelligent detection system includes:
1. the front-end video acquisition processing module 110 includes a video acquisition unit 111 and a video processing unit 11, the video acquisition unit 111 performs real-time acquisition of video data in a current scene, and the video processing unit 112 processes the original video data by the following steps:
1) and dividing the region of interest, and setting a fixed value for the pixel value of the region where the tree, light, road and other objects with excessively large dynamic range change are located, so that the region of interest does not participate in the subsequent image processing step.
2) Adopting the following formula to carry out Gaussian fuzzification processing on video data:
where the radius of blur r ═ x2+y2And (4) carrying out adaptive adjustment according to an actual scene, wherein the sigma is the standard deviation of normal distribution.
3) The data of the current frame, the previous frame and the previous two frames of the real-time video are cached, and the dynamic foreign matter under the current scene is extracted by utilizing a three-frame difference method. The specific operation steps are as follows:
selecting a current video frame Vn(x, y), previous frame Vn-1(x, y) and the first two frames Vn-2(x, y) video data. Current video frame Vn(x, y) are respectively associated with the previous frame Vn-1(x, y) and the first two frames Vn-2Difference operation is carried out on (x, y) video data to obtain a difference image D1(x, y) and D2(x, y), the formula of the calculation process is as follows:
D1(x,y)＝Vn(x,y)-Vn-1(x,y)
D2(x,y)＝Vn(x,y)-Vn-2(x,y)
for differential image D1(x, y) and D2(x, y) performing a thresholding process, wherein TnTo set the threshold:
further, the region of influence is removed by an and operation between pixels to obtain a feature image F (x, y), that is:
F(x,y)＝B1(x,y)∧B2(x,y)
the characteristic image F (x, y) is morphologically processed so as to accurately locate the dynamic foreign body. And subsequently, performing median filtering, down-sampling, expansion, corrosion and up-sampling operations in sequence. Counting the number of pixel points of a connected region in the characteristic image F (x, y), if the number of the pixel points is larger than a set threshold value T, regarding the region as a dynamic foreign matter, and drawing a rectangular foreign matter identification frame to mark the region.
4) Aiming at the problem of camera shaking caused by external factors, the invention provides the following method:
as shown in fig. 4, a captured detection scene video frame is divided into an N × M grid. Counting the number of alarm identification frames of each grid in the equipment debugging stage, and respectively calculating the reasonable threshold value T of each gridi×j. Wherein i ∈ [0, N ∈ >],j∈[0,M]，Ti×jThe grid alarm frame number threshold value is the ith row and the jth column. Once the number of alarm frames in a certain grid area in the video data of the current frame exceeds a set threshold value Ti×jThen the video data received at the current frame time is considered to be bad, and therefore the frame identification result is filtered out.
2. And the data transmission pushing module 120 is used for data transmission and instruction issuing among the modules and pushing alarm information between the system and operation and maintenance personnel.
3. The back-end server identification processing module 130, with specific identification logic as shown in fig. 5, includes:
the target identification unit 131 is used for generating a foreign matter identification training set by manually marking foreign matters, identifying the identity of a person according to whether the person wears a safety helmet and the color of the safety helmet based on TensorFlow, identifying whether the entering vehicle is a working vehicle according to the uniform coating of the working vehicle, and if the identification result shows that the invading person and the working vehicle are the working person and the working vehicle, not entering an alarm flow;
an intrusion event processing unit 132 for receiving the object recognition result of the object recognition unit 131, classifying different alarm levels according to different types of foreign objects, and taking corresponding processing measures;
the model optimization and upgrade unit 133 retrains the foreign object recognition model by using the error of the daily alarm information, and improves the accuracy of the recognition of the target recognition unit 131.
4. The field driving and away warning module 140 comprises an ultrasonic wave driving and away unit 141 and a personnel invasion warning and away unit 142, wherein the ultrasonic wave driving and away unit 141 is used for driving away birds which intrude into the upper space of the substation power equipment, and the personnel invasion warning and away unit 142 warns non-working personnel and non-working vehicles through signals such as sound and light.
If the foreign matter type is a flying bird, the rear-end server identification processing module 130 issues a trigger instruction to the ultrasonic bird repelling unit 141, starts a bird repelling program, automatically records the name of the transformer substation, the number of the camera and the operation and maintenance responsible person in the area of the flying bird invasion event at the same time, and stores the recorded name and number in a log; and generating a flying bird invasion report and sending the flying bird invasion report to a terminal App end of an operation and maintenance worker of the current transformer substation.
If the foreign matter type is a foreign person vehicle, the back-end server recognition processing module 130 issues a trigger instruction to the person intrusion warning drive-off unit 142, the intrusion warning drive-off unit is started, the intruder vehicle is forcibly warned and driven off by adopting a sound alarm and highlight lamp flashing method, and meanwhile, the information of the name of the alarm transformer substation, the camera number and the like is automatically recorded and stored in a log; and meanwhile, generating a report form of the vehicle intrusion event of the external personnel and sending the report form to the terminal App of the operation and maintenance personnel of the current transformer substation.
Aiming at the air floating object type foreign matters such as kites, balloons and the like, the rear-end server recognition processing module records the detailed information of the alarm event, starts the highest-level alarm measure, namely immediately sends the highest-level alarm measure to the operation and maintenance personnel terminal App of the current transformer substation, informs the operator terminal App of going to the site to pay close attention to the foreign matters, and timely handles the hidden danger.
And the transformer substation worker evaluates the alarm operation after receiving the alarm report, and if the alarm event is of a false alarm type, the evaluation information needs to be corrected. The corrected result is automatically uploaded to a foreign body model training set in the back-end server recognition processing module 130 by the terminal App to automatically complete the training of the foreign body model, so that the accuracy of foreign body recognition is improved.
Claims (8)
1. The utility model provides a transformer substation's perimeter video intelligent detection system which characterized in that includes:
the front-end video acquisition processing module (110) comprises a video acquisition unit (111) and a video processing unit (112), acquires and preprocesses field video data in real time, and extracts a dynamic target under the current scene;
the data transmission pushing module (120) is used for data transmission and instruction issuing among the modules;
the back-end server identification processing module (130) is used for identifying the type of the foreign matters, classifying alarm grades and generating processing instructions;
and the field driving away warning module (140) is used for alarming and processing instructions of the field intrusion foreign matters.
2. The transformer substation perimeter video intelligent detection system according to claim 1, wherein the video acquisition unit (111) acquires video data in a current scene in real time, the video processing unit (112) performs Gaussian blurring on the real-time video data, extracts a foreground binarized image by a three-frame difference method, and performs median filtering, down-sampling, expansion, corrosion and up-sampling on the binarized image in sequence, so as to accurately extract a dynamic target.
3. The substation perimeter video intelligent detection system according to claim 2, wherein the video processing unit (112) divides an area of interest in a current detection region before performing the gaussian blurring processing, performs shielding processing on trees, lights and roads of which forms are changed by external factors or self factors in the area of interest in a short time, sets the pixel value of the object with a large dynamic range change as a fixed value, and enables the part of the object not to participate in subsequent image processing operations.
4. The transformer substation perimeter video intelligent detection system according to claim 2, wherein after video data is collected, the video processing unit (112) screens the dynamic target extraction result by setting a threshold of pixel points occupied by the target according to the number and position of dynamic targets appearing in a currently processed video frame, and if the pixel points occupied by the dynamic target are smaller than the threshold, the target is considered not to be a foreign object, otherwise, the target is determined to be a foreign object.
5. The substation perimeter video intelligent detection system according to claim 1, wherein the backend server identification processing module (130) comprises:
the target recognition unit (131) generates a foreign matter recognition training set by manually marking foreign matters, and performs foreign matter recognition based on TensorFlow;
the intrusion event processing unit (132) receives the target identification result of the target identification unit (131), divides different alarm levels according to different foreign matter types and takes corresponding processing measures;
and the model optimization upgrading unit (133) retrains the foreign matter recognition model by using the error of the daily alarm information, and improves the accuracy of recognition of the target recognition unit (131).
6. The transformer substation perimeter video intelligent detection system according to claim 5, wherein before the system is put into use, the back-end server identification processing module (130) collects data of a current detection area, counts the number of alarm events of the same frame of video data in the current detection area, and sets an alarm event number threshold; and after the system is put into use, if the number of the alarm events in the current detection area exceeds a threshold value, no alarm is given.
7. The transformer substation perimeter video intelligent detection system according to claim 5, wherein the target identification unit (131) identifies the identity of a person through whether the person wears a safety helmet and the color of the safety helmet, identifies whether an entering vehicle is a working vehicle according to the uniform coating of the working vehicle, and does not include an alarm process if the identification result shows that the invading person and the working vehicle are the working person and the working vehicle.
8. The substation perimeter video intelligent detection system according to claim 1, wherein the field drive-away warning module (140) comprises an ultrasonic drive-away unit (141) and a personnel intrusion warning drive-away unit (142), the ultrasonic drive-away unit (141) is used for driving away birds intruding into substation power equipment, and the personnel intrusion warning drive-away unit (142) warns non-working personnel and non-working vehicles through signals such as sound and light.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911062983.0A CN110691224A (en) | 2019-10-31 | 2019-10-31 | Transformer substation perimeter video intelligent detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911062983.0A CN110691224A (en) | 2019-10-31 | 2019-10-31 | Transformer substation perimeter video intelligent detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110691224A true CN110691224A (en) | 2020-01-14 |
Family
ID=69115354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911062983.0A Pending CN110691224A (en) | 2019-10-31 | 2019-10-31 | Transformer substation perimeter video intelligent detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110691224A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239960A (en) * | 2021-04-09 | 2021-08-10 | 中用科技有限公司 | Intelligent early warning method and system for road protection by fusing AI visual algorithm |
| CN113255494A (en) * | 2021-05-17 | 2021-08-13 | 开放智能机器（上海）有限公司 | Method and system for monitoring illegally-invaded vehicle in real time |
| CN113792578A (en) * | 2021-07-30 | 2021-12-14 | 北京智芯微电子科技有限公司 | Method, device and system for detecting abnormity of transformer substation |
| CN114977511A (en) * | 2022-06-21 | 2022-08-30 | 众芯汉创（北京）科技有限公司 | Wind power plant transformer substation monitoring system based on block chain |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6233006B1 (en) * | 1997-05-27 | 2001-05-15 | Samsong Industries, Ltd. | Image change detecting machine by using character generator and method thereof |
| CN102750707A (en) * | 2011-08-29 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Image processing method and image processing device based on regions of interest |
| CN103404504A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Living creatures repeller |
| CN103716635A (en) * | 2013-12-12 | 2014-04-09 | 浙江宇视科技有限公司 | Method and device for improving intelligent analysis performance |
| CN106846813A (en) * | 2017-03-17 | 2017-06-13 | 西安电子科技大学 | The method for building urban road vehicle image data base |
| CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
| CN109040669A (en) * | 2018-06-28 | 2018-12-18 | 国网山东省电力公司菏泽供电公司 | Intelligent substation video fence method and system |
| 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 |
| CN110188624A (en) * | 2019-05-10 | 2019-08-30 | 国网福建省电力有限公司龙岩供电公司 | A kind of substation's wind drift recognition methods and system based on deep learning |
-
2019
- 2019-10-31 CN CN201911062983.0A patent/CN110691224A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6233006B1 (en) * | 1997-05-27 | 2001-05-15 | Samsong Industries, Ltd. | Image change detecting machine by using character generator and method thereof |
| CN102750707A (en) * | 2011-08-29 | 2012-10-24 | 新奥特（北京）视频技术有限公司 | Image processing method and image processing device based on regions of interest |
| CN103404504A (en) * | 2013-08-19 | 2013-11-27 | 国家电网公司 | Living creatures repeller |
| CN103716635A (en) * | 2013-12-12 | 2014-04-09 | 浙江宇视科技有限公司 | Method and device for improving intelligent analysis performance |
| CN106846813A (en) * | 2017-03-17 | 2017-06-13 | 西安电子科技大学 | The method for building urban road vehicle image data base |
| CN109002744A (en) * | 2017-06-06 | 2018-12-14 | 中兴通讯股份有限公司 | Image-recognizing method, device and video monitoring equipment |
| CN109040669A (en) * | 2018-06-28 | 2018-12-18 | 国网山东省电力公司菏泽供电公司 | Intelligent substation video fence method and system |
| 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 |
| CN110188624A (en) * | 2019-05-10 | 2019-08-30 | 国网福建省电力有限公司龙岩供电公司 | A kind of substation's wind drift recognition methods and system based on deep learning |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239960A (en) * | 2021-04-09 | 2021-08-10 | 中用科技有限公司 | Intelligent early warning method and system for road protection by fusing AI visual algorithm |
| CN113239960B (en) * | 2021-04-09 | 2024-05-28 | 中用科技有限公司 | Intelligent road protection early warning method and system integrating AI vision algorithm |
| CN113255494A (en) * | 2021-05-17 | 2021-08-13 | 开放智能机器（上海）有限公司 | Method and system for monitoring illegally-invaded vehicle in real time |
| CN113792578A (en) * | 2021-07-30 | 2021-12-14 | 北京智芯微电子科技有限公司 | Method, device and system for detecting abnormity of transformer substation |
| CN114977511A (en) * | 2022-06-21 | 2022-08-30 | 众芯汉创（北京）科技有限公司 | Wind power plant transformer substation monitoring system based on block chain |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110691224A (en) | Transformer substation perimeter video intelligent detection system | |
| CN108710126B (en) | Automatic target detection and eviction method and system | |
| CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
| CN105744232B (en) | A kind of method of the transmission line of electricity video external force damage prevention of Behavior-based control analytical technology | |
| US6985172B1 (en) | Model-based incident detection system with motion classification | |
| CN103287464B (en) | Intelligent video surveillance system at railway crossing and implement method of system | |
| CN113850123A (en) | Video-based road monitoring method and device, storage medium and monitoring system | |
| CN107845264A (en) | A kind of volume of traffic acquisition system and method based on video monitoring | |
| CN103106766A (en) | Forest fire identification method and forest fire identification system | |
| CN111523397B (en) | Intelligent lamp post visual identification device, method and system and electronic equipment thereof | |
| CN111161312B (en) | Object trajectory tracking and identifying device and system based on computer vision | |
| CN113676702B (en) | Video stream-based target tracking and monitoring method, system, device and storage medium | |
| Kulkarni et al. | Real time vehicle detection, tracking and counting using Raspberry-Pi | |
| CN111833598A (en) | Automatic traffic incident monitoring method and system for unmanned aerial vehicle on highway | |
| CN112084892B (en) | Road abnormal event detection management device and method thereof | |
| CN111783700B (en) | Automatic recognition and early warning method and system for pavement foreign matters | |
| CN105046948A (en) | System and method of monitoring illegal traffic parking in yellow grid line area | |
| CN116846059A (en) | Edge detection system for power grid inspection and monitoring | |
| CN208271388U (en) | A kind of volume of traffic acquisition system based on video monitoring | |
| CN114325856A (en) | Power transmission line foreign matter monitoring method based on edge calculation | |
| CN105095891A (en) | Human face capturing method, device and system | |
| CN111862621B (en) | Intelligent snapshot system of multi-type adaptive black cigarette vehicle | |
| CN110481600B (en) | Unmanned autonomous comprehensive alarm system | |
| CN212785620U (en) | Monitoring system for power transmission network | |
| CN111460949A (en) | Real-time monitoring method and system for preventing external damage of power transmission line |
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 |
Application publication date: 20200114 |
|
| RJ01 | Rejection of invention patent application after publication |