CN103945197A - Electric power facility external damage prevention warming scheme based on video motion detecting technology - Google Patents
Electric power facility external damage prevention warming scheme based on video motion detecting technology Download PDFInfo
- Publication number
- CN103945197A CN103945197A CN201410199455.0A CN201410199455A CN103945197A CN 103945197 A CN103945197 A CN 103945197A CN 201410199455 A CN201410199455 A CN 201410199455A CN 103945197 A CN103945197 A CN 103945197A
- Authority
- CN
- China
- Prior art keywords
- pattern
- electric power
- power facility
- video
- gaussian profile
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
-
- 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
Abstract
The invention relates to an electric power facility external damage prevention warming scheme based on the video motion detecting technology. The scheme comprises, after frame by frame reading the images of a video detected by a camera and setting a corresponding threshold value system according to the time, processing a series of the frame images of the video to extract the integral contour of an electric power facility and the virtual coil on the entire video images; then determining detecting areas; performing background extraction and update in all the detecting areas through a mixed Gaussian distribution background model; obtaining the foregrounds of the detecting areas through a background substraction method; comparing the pixel data of the foregrounds of the detecting areas with the corresponding detecting threshold values of the threshold value system; if the foreground pixel data exceed the range of the threshold values, issuing a warning signal to perform background update and foreground detection timely and accordingly ensure the real-time performance and the continuity of video detection.
Description
Technical field
The invention belongs to digital image processing field, particularly the Digital Image Processing of the anti-outer broken warning aspect of electric power facility.
Background technology
Along with the development of national economy, how the supply of electric power in occupation of consequence more and more, and ensures that the safe and stable operation of the electric power facilities such as remote ultra-high-tension power transmission line is the problem of needing solution badly in social productive life.The fast development of the computer technologies such as Digital Image Processing makes to occur new thinking about the research and development of the safety monitoring technology of ultra-high-tension power transmission line.Wherein the motion detection technique based on video is as the branch of computer vision application, the technology that to be a kind of function of imitating human eye by video camera and computer combine video image and computerized pattern recognition, day by day becomes in all kinds of supervisory control systems tool advantage, has the detection method of development potentiality most.And video detection technology is applied in the monitoring protection of electric power facility (as ultra-high-tension power transmission line), form the ultra-high-tension power transmission line monitoring early-warning system based on Video Motion Detection, the main flow and the forward position that have become electric power facility monitoring area research, caused showing great attention to of industry.
But about such systematic research and exploitation also ripe far away, also there are the following problems to be seen at present a small amount of this type systematic of report: (1) a lot of systems do not have intelligent detection algorithm, thereby cannot automation identify target, can only be the in the situation that of Attended mode could Monitoring and forecasting system in real-time, thereby produce high human cost; (2) minority system has intelligent detection algorithm, it is not to be completed by fielded system that but video detects, but complete to remote control center by wireless communication transmissions, in view of the low reliability of wireless communications environment is difficult to ensure emergency case to respond in time, once and control centre cannot move, whole system just will be paralysed; (3) only a few formation system is also failed to solve at complex scene, is blocked the in particular cases target detection problems such as scene, night scene, cannot realize the associating optimization of false drop rate and loss.The extensive commercialization of these these type systematics of problems hamper.
Summary of the invention
The technical problem to be solved in the present invention be to provide a kind of realize real-time early warning, practicality better, real-time is higher and accuracy the is higher anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology.
The technical scheme that realizes the object of the invention is to provide the anti-outer broken early warning scheme of a kind of electric power facility based on Video Motion Detection technology, comprises following several step:
1. reading images, the video that camera is detected reads in internal memory according to a frame two field picture and records the pixel grey scale Value Data of this image;
2. according to the corresponding threshold value system of set of time, time, to be 8 of mornings be defined as pattern at night to being defined as pattern in daytime, evening between at 5 in afternoon at 8 to 5:00 AM, and for being At All Other Times Fuzzy Time region, adopt Bayes theorem to carry out Decision Classfication, night and the corresponding different threshold value systems of pattern employing in daytime;
3. a series of two field picture processing of video by Edge-Detection Algorithm, 1. step being obtained extracts the overall profile of electric power facility;
4., under the threshold value system 2. obtaining in step, the electric power facility profile 3. obtaining according to step generates 3 to 8 virtual coils from inside to outside of whole video image;
5. the virtual coil that 4. the electric power facility profile 3. obtaining according to step and step obtain is determined surveyed area, and surveyed area is the region between region and all two the adjacent virtual coils beyond electric power facility profile, in interior virtual coil;
6. in all surveyed areas that 5. obtain in step, adopt mixed Gaussian distribution background model to carry out background extracting and renewal; Adopt a multiple adaptive mixed Gauss model and detect background dot and foreground point according to the continuation of Gaussian Profile and variability; The renewal of background is by introducing turnover rate
upgrade that the weight of each Gaussian Profile realizes; Background extracting based on mixed Gaussian distribution background model and principle and the processing method of renewal are as follows:
If it is total to be used for describing the Gaussian Profile of each picture element distribution of color
kindividual; In the moment
, certain picture element
ithe probability density function of individual Gaussian Profile is:
（3）
Wherein,
represent the moment
the color vector of the RGB intensity level composition of picture element;
,
be respectively the moment
the
the mean vector of individual Gaussian Profile, covariance matrix;
Each Gaussian Profile has respectively different weights
and priority
, they are according to priority
sort from high to low; Meet formula
before
bindividual Gaussian Profile is considered to background distributions, and other Gaussian Profile thinks that prospect distributes, and in above formula, T is threshold value, and the value of T has determined the number of background distributions; In the time detecting foreground point, will according to priority order
mate one by one with each Gaussian Profile, if the Gaussian Profile that does not represent background distributions with
coupling, judges that this point is foreground point, otherwise is background dot;
If detect time do not find any Gaussian Profile with
coupling, removes a Gaussian Profile of priority minimum, and according to
introduce a new Gaussian Profile, and give less weights and larger variance, if the
kindividual Gaussian Profile with
coupling, to the
ithe right value update of individual Gaussian Profile is as follows:
（4）
Wherein,
for turnover rate, when
when i=k, , otherwise,
;
7. obtain the prospect of surveyed area by background subtraction method, do difference computing by the background pixel data in the image pixel data of the surveyed area to a frame frame and the surveyed area of real-time update, can obtain the prospect of institute's surveyed area;
The threshold value system that 2. pixel data of the prospect of the surveyed area 8. 7. step being drawn and step obtain is that the detection threshold collection under night or daytime pattern compares, if having exceeded threshold range, foreground pixel data enter step 9., otherwise keep circulation step 6. extremely 8., carry out in real time the detection of context update and prospect, after the certain hour of being simultaneously separated by execution step 2. again detect present pattern be daytime pattern or night pattern upgrade corresponding threshold value system;
If 9. foreground pixel data have exceeded threshold range, think and have moving object near electric power facility, now send in time early warning signal by early warning system immediately.
Further, wherein 1. step is during the image file of the frame frame bmp form to video on VC++ 6.0 platforms sequentially reads internal memory and records the pixel grey scale Value Data of this image.
Further, wherein step 3. in, Bayes function is:
（1）
2 pattern class of indicating to be differentiated be daytime pattern and night pattern,
representation feature vector, i.e. current frame image average gray value;
represent the prior probability that 2 patterns occur,
difference with season, surrounding environment changes, and can be obtained by historical data statistics;
represent that respectively under pattern in daytime, night pattern, average gray value is
conditional probability, obtained by experience; Discrimination formula is:
If
(2)
Be judged to pattern in daytime; Otherwise, be judged to pattern at night; This determination methods can be expressed as:
in formula
for current time, by determining, corresponding threshold value system is set after pattern in night or daytime.
Further, wherein step 3. in, Edge-Detection Algorithm adopts one of boundary operator method, curve-fitting method, template matching method or thresholding method.
Further, wherein step 4. in, determine after electric power facility profile 3 to 8 virtual coils from inside to outside generate whole video image around electric power facility profile by the virtual coil generation method based on statistical geometry: the distance of establishing between camera and high-tension line is
, the angle of pitch is
, azimuth is
; Circuit point on image
tangent vector is defined as taking camera near-end as the starting point direction along circuit points to the vector of this point, is expressed as
; Circuit point on image
normal vector is defined as with this point and sets out along the vector of the direction of circuit vertical line, is expressed as
; Set up the geometric function relation of normal vector and tangent vector by statistical theory:
;
In real system, distance
, the angle of pitch
, azimuth
parameter can obtain by field adjustable; Can obtain exactly the coordinate of transmission line each point by the manual mode of visualization interface utilization; On this basis, utilize above-mentioned geometric function relation can obtain the virtual coil of whole circuit.
Further, step 8. in, after being separated by 40 to 90 minutes execution step 2. again detect present pattern be daytime pattern or night pattern upgrade corresponding threshold value system.
The present invention has positive effect: the anti-outer broken early warning scheme of (1) electric power facility based on Video Motion Detection technology of the present invention is correspondingly set up threshold parameter system according to the different aspects of data and different video surveyed areas, thereby use and improve accuracy and the applicability that video detects for joint decision, and consider in this programme implementation environment that night and daytime, mode image pixel difference was very large, this directly has influence on corresponding detection threshold parameter.Therefore this programme adopt Bayesian decision theory distinguish night pattern and daytime pattern, according to different patterns, different threshold value systems is set simultaneously, threshold parameter system by these real-time update is carried out joint decision, can improve to a greater extent like this accuracy, applicability and the stability of early warning.
(2) the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology of the present invention uses Video Motion Detection treatment technology to detect electric power facility traffic behavior around, can be round-the-clock (night and the daytime two kinds of patterns under) moving object that may destroy electric power facility to those can automatically give warning in advance, real-time is higher.
(3) the anti-outer broken early warning scheme mixed Gaussian distribution background model of the electric power facility based on Video Motion Detection technology of the present invention is carried out extraction and the renewal of image background, adopt background subtraction method to carry out the detection of moving object, the variation of external environment be can adapt to well, rapidity and real-time that video detects ensured.
(4) electric power facility based on Video Motion Detection technology of the present invention is prevented that outer broken early warning scheme is simple and is easy to realize, and has good application prospect.
Brief description of the drawings
Fig. 1 is the virtual coil schematic diagram of transmission line.
Embodiment
(embodiment 1)
The anti-outer broken early warning scheme of electric power facility based on Video Motion Detection technology of the present embodiment comprises the steps:
1. reading images, the video that camera is detected reads in internal memory according to a frame two field picture and records the pixel grey scale Value Data of this image; The present embodiment is during the image file of the frame frame bmp form to video on VC++ 6.0 platforms sequentially reads internal memory and records the pixel grey scale Value Data of this image.
2. according to the corresponding threshold value system of set of time, time, to be 8 of mornings be defined as pattern at night to being defined as pattern in daytime, evening between at 5 in afternoon at 8 to 5:00 AM, and for being At All Other Times Fuzzy Time region, due to brightness gradually change and jumping characteristic strong, situation is more complicated, adopt Bayes theorem to carry out Decision Classfication, Bayes function is:
（1）
2 pattern class of indicating to be differentiated be daytime pattern and night pattern,
representation feature vector (current frame image average gray value).
represent the prior probability that 2 patterns occur,
difference with season, surrounding environment changes, and can be obtained by historical data statistics;
represent that respectively under pattern in daytime, night pattern, average gray value is
conditional probability, obtained by experience.Discrimination formula is:
If
(2)
Be judged to pattern in daytime; Otherwise, be judged to pattern at night.This determination methods can be expressed as:
in formula
for current time, by determining, corresponding different threshold value system is set after pattern in night or daytime.
3. a series of two field picture processing of video by Edge-Detection Algorithm, 1. step being obtained extracts the overall profile of electric power facility; Edge-Detection Algorithm can adopt such as boundary operator method, curve-fitting method, template matching method, thresholding method etc.
4. under the threshold value system 2. obtaining in step, 3. the electric power facility profile obtaining according to step, around electric power facility profile, generate 3 to 8 virtual coils from inside to outside of whole video image by the virtual coil generation method based on statistical geometry: see Fig. 1, the distance of establishing between camera and high-tension line is
, the angle of pitch is
, azimuth is
.Circuit point on image
tangent vector is defined as taking camera near-end as the starting point direction along circuit points to the vector of this point, is expressed as
.Circuit point on image
normal vector is defined as with this point and sets out along the vector of the direction of circuit vertical line, is expressed as
.Set up the geometric function relation of normal vector and tangent vector by statistical theory:
.
In real system, distance
, the angle of pitch
, azimuth
parameter can obtain by field adjustable.And, also obtain exactly the coordinate of transmission line each point by the manual mode of visualization interface utilization.On this basis, utilize above-mentioned geometric function relation can obtain the virtual coil of whole circuit.
5. the virtual coil that 4. the electric power facility profile 3. obtaining according to step and step obtain is determined surveyed area, and surveyed area is the region between region and all two the adjacent virtual coils beyond electric power facility profile, in interior virtual coil.
6. in all surveyed areas that 5. obtain in step, adopt mixed Gaussian distribution background model to carry out background extracting and renewal.The extraction of video image background has determined the accuracy of image detection to a great extent, and Algorithms for Background Extraction based on different background model is also good and bad different.This programme adopts mixed Gaussian distribution background model, adopts a multiple adaptive mixed Gauss model and detects background dot and foreground point according to the continuation of Gaussian Profile and variability.The renewal of background is by introducing turnover rate
upgrade that the weight of each Gaussian Profile realizes.Background extracting based on mixed Gaussian distribution background model and principle and the processing method of renewal are as follows:
If it is total to be used for describing the Gaussian Profile of each picture element distribution of color
kindividual.In the moment
, certain picture element
ithe probability density function of individual Gaussian Profile is:
（3）
Wherein,
represent the moment
the color vector of the RGB intensity level composition of picture element;
,
be respectively the moment
the
the mean vector of individual Gaussian Profile, covariance matrix.
Each Gaussian Profile has respectively different weights
and priority
, they are according to priority
sort from high to low.Meet formula
before (T is threshold value, and the value of T has determined the number of background distributions)
bindividual Gaussian Profile is considered to background distributions, and other Gaussian Profile thinks that prospect distributes.In the time detecting foreground point, will according to priority order
mate one by one with each Gaussian Profile, if the Gaussian Profile that does not represent background distributions with
coupling, judges that this point is foreground point, otherwise is background dot.
If detect time do not find any Gaussian Profile with
coupling, removes a Gaussian Profile of priority minimum, and according to
introduce a new Gaussian Profile, and give less weights and larger variance, if the
kindividual Gaussian Profile with
coupling, to the
ithe right value update of individual Gaussian Profile is as follows:
（4）
Wherein,
for turnover rate, when
when i=k, , otherwise,
.
7. obtain the prospect of surveyed area by background subtraction method.Background subtraction method is a kind of technology of utilizing current frame image and the gray scale difference value of the corresponding picture element of background image to detect moving object: if the picture element gray value difference of the picture element of present image and background image is very large, just think that this picture element has moving object; On the contrary, if the picture element gray value difference of the picture element of present image and background image is less, in certain threshold range, just think that this picture element is background pixels point.Do difference computing by the background pixel data in the image pixel data of the surveyed area to a frame frame and the surveyed area of real-time update, can obtain the prospect of institute's surveyed area.
The threshold value system that 2. pixel data of the prospect of the surveyed area 8. 7. step being drawn and step obtain is that the detection threshold collection under night or daytime pattern compares, due to night and daytime mode image pixel difference very large, this directly has influence on corresponding detection threshold parameter, if having exceeded threshold range, foreground pixel data enter step 9., otherwise keep circulation step 6. extremely 8., carry out in real time the detection of context update and prospect, the execution step of being simultaneously separated by after certain hour 2. again detect present pattern be daytime pattern or night pattern upgrade corresponding threshold value system, conventionally be 40 minutes to 90 minutes interval time, guarantee real-time and continuation that video detects.
If 9. foreground pixel data have exceeded threshold range, think and have moving object near electric power facility, now send in time early warning signal by early warning system immediately.
Claims (6)
1. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology, is characterized in that comprising following several step:
1. reading images, the video that camera is detected reads in internal memory according to a frame two field picture and records the pixel grey scale Value Data of this image;
2. according to the corresponding threshold value system of set of time, time, to be 8 of mornings be defined as pattern at night to being defined as pattern in daytime, evening between at 5 in afternoon at 8 to 5:00 AM, and for being At All Other Times Fuzzy Time region, adopt Bayes theorem to carry out Decision Classfication, night and the corresponding different threshold value systems of pattern employing in daytime;
3. a series of two field picture processing of video by Edge-Detection Algorithm, 1. step being obtained extracts the overall profile of electric power facility;
4., under the threshold value system 2. obtaining in step, the electric power facility profile 3. obtaining according to step generates 3 to 8 virtual coils from inside to outside of whole video image;
5. the virtual coil that 4. the electric power facility profile 3. obtaining according to step and step obtain is determined surveyed area, and surveyed area is the region between region and all two the adjacent virtual coils beyond electric power facility profile, in interior virtual coil;
6. in all surveyed areas that 5. obtain in step, adopt mixed Gaussian distribution background model to carry out background extracting and renewal; Adopt a multiple adaptive mixed Gauss model and detect background dot and foreground point according to the continuation of Gaussian Profile and variability; The renewal of background is by introducing turnover rate
upgrade that the weight of each Gaussian Profile realizes; Background extracting based on mixed Gaussian distribution background model and principle and the processing method of renewal are as follows:
If it is total to be used for describing the Gaussian Profile of each picture element distribution of color
kindividual; In the moment
, certain picture element
ithe probability density function of individual Gaussian Profile is:
（3）
Wherein,
represent the moment
the color vector of the RGB intensity level composition of picture element;
,
be respectively the moment
the
the mean vector of individual Gaussian Profile, covariance matrix;
Each Gaussian Profile has respectively different weights
and priority
, they are according to priority
sort from high to low; Meet formula
before
bindividual Gaussian Profile is considered to background distributions, and other Gaussian Profile thinks that prospect distributes, and in above formula, T is threshold value, and the value of T has determined the number of background distributions; In the time detecting foreground point, will according to priority order
mate one by one with each Gaussian Profile, if the Gaussian Profile that does not represent background distributions with
coupling, judges that this point is foreground point, otherwise is background dot;
If detect time do not find any Gaussian Profile with
coupling, removes a Gaussian Profile of priority minimum, and according to
introduce a new Gaussian Profile, and give less weights and larger variance, if the
kindividual Gaussian Profile with
coupling, to the
ithe right value update of individual Gaussian Profile is as follows:
（4）
Wherein,
for turnover rate, when
i=ktime,
, otherwise,
;
7. obtain the prospect of surveyed area by background subtraction method, do difference computing by the background pixel data in the image pixel data of the surveyed area to a frame frame and the surveyed area of real-time update, can obtain the prospect of institute's surveyed area;
The threshold value system that 2. pixel data of the prospect of the surveyed area 8. 7. step being drawn and step obtain is that the detection threshold collection under night or daytime pattern compares, if having exceeded threshold range, foreground pixel data enter step 9., otherwise keep circulation step 6. extremely 8., carry out in real time the detection of context update and prospect, after the certain hour of being simultaneously separated by execution step 2. again detect present pattern be daytime pattern or night pattern upgrade corresponding threshold value system;
If 9. foreground pixel data have exceeded threshold range, think and have moving object near electric power facility, now send in time early warning signal by early warning system immediately.
2. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology according to claim 1, is characterized in that: wherein 1. step is during the image file of the frame frame bmp form to video on VC++ 6.0 platforms sequentially reads internal memory and records the pixel grey scale Value Data of this image.
3. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology according to claim 1, is characterized in that: wherein step 3. in, Bayes function is:
（1）
2 pattern class of indicating to be differentiated be daytime pattern and night pattern,
representation feature vector, i.e. current frame image average gray value;
represent the prior probability that 2 patterns occur,
difference with season, surrounding environment changes, and can be obtained by historical data statistics;
represent that respectively under pattern in daytime, night pattern, average gray value is
conditional probability, obtained by experience; Discrimination formula is:
If
(2)
Be judged to pattern in daytime; Otherwise, be judged to pattern at night; This determination methods can be expressed as:
in formula
for current time, by determining, corresponding threshold value system is set after pattern in night or daytime.
4. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology according to claim 1, it is characterized in that: wherein step 3. in, Edge-Detection Algorithm adopts one of boundary operator method, curve-fitting method, template matching method or thresholding method.
5. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology according to claim 1, it is characterized in that: wherein step 4. in, determine after electric power facility profile 3 to 8 virtual coils from inside to outside generate whole video image around electric power facility profile by the virtual coil generation method based on statistical geometry: the distance of establishing between camera and high-tension line is
, the angle of pitch is
, azimuth is
; Circuit point on image
tangent vector is defined as taking camera near-end as the starting point direction along circuit points to the vector of this point, is expressed as
; Circuit point on image
normal vector is defined as with this point and sets out along the vector of the direction of circuit vertical line, is expressed as
; Set up the geometric function relation of normal vector and tangent vector by statistical theory:
;
In real system, distance
, the angle of pitch
, azimuth
parameter can obtain by field adjustable; Can obtain exactly the coordinate of transmission line each point by the manual mode of visualization interface utilization; On this basis, utilize above-mentioned geometric function relation can obtain the virtual coil of whole circuit.
6. the anti-outer broken early warning scheme of the electric power facility based on Video Motion Detection technology according to claim 1, it is characterized in that: step 8. in, after being separated by 40 to 90 minutes execution step 2. again detect present pattern be daytime pattern or night pattern upgrade corresponding threshold value system.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710575689.4A CN107222726B (en) | 2014-05-12 | 2014-05-12 | Early warning method for preventing external damage of electric power facility |
| CN201410199455.0A CN103945197B (en) | 2014-05-12 | 2014-05-12 | Electric power facility external force damage prevention early warning scheme based on Video Motion Detection technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410199455.0A CN103945197B (en) | 2014-05-12 | 2014-05-12 | Electric power facility external force damage prevention early warning scheme based on Video Motion Detection technology |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710575689.4A Division CN107222726B (en) | 2014-05-12 | 2014-05-12 | Early warning method for preventing external damage of electric power facility |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103945197A true CN103945197A (en) | 2014-07-23 |
| CN103945197B CN103945197B (en) | 2017-07-18 |
Family
ID=51192646
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410199455.0A Active CN103945197B (en) | 2014-05-12 | 2014-05-12 | Electric power facility external force damage prevention early warning scheme based on Video Motion Detection technology |
| CN201710575689.4A Active CN107222726B (en) | 2014-05-12 | 2014-05-12 | Early warning method for preventing external damage of electric power facility |
Family Applications After (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710575689.4A Active CN107222726B (en) | 2014-05-12 | 2014-05-12 | Early warning method for preventing external damage of electric power facility |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN103945197B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299224A (en) * | 2014-08-21 | 2015-01-21 | 华南理工大学 | Method for property protection based on video image background matching |
| CN105894701A (en) * | 2016-04-05 | 2016-08-24 | 江苏电力信息技术有限公司 | Large construction vehicle identification and alarm method for preventing external damage to transmission lines |
| CN108074370A (en) * | 2016-11-11 | 2018-05-25 | 国网湖北省电力公司咸宁供电公司 | The early warning system and method that a kind of anti-external force of electric power transmission line based on machine vision is destroyed |
| CN110418192A (en) * | 2019-06-26 | 2019-11-05 | 视联动力信息技术股份有限公司 | A kind of image processing method, device and storage medium |
| CN112312087A (en) * | 2020-10-22 | 2021-02-02 | 中科曙光南京研究院有限公司 | Method and system for quickly positioning event occurrence time in long-term monitoring video |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111724558B (en) * | 2019-03-21 | 2021-10-19 | 杭州海康威视数字技术股份有限公司 | Monitoring method, monitoring device and intrusion alarm system |
| CN109859427A (en) * | 2019-04-04 | 2019-06-07 | 上海天诚比集科技有限公司 | Anti-climbing alarm method based on image variance algorithm |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
| CN101237522A (en) * | 2007-02-02 | 2008-08-06 | 华为技术有限公司 | Motion detection method and device |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100538723C (en) * | 2007-10-26 | 2009-09-09 | 浙江工业大学 | The inner river ship automatic identification system that multiple vision sensor information merges |
| CN102654902B (en) * | 2012-01-16 | 2013-11-20 | 江南大学 | Contour vector feature-based embedded real-time image matching method |
| CN202632468U (en) * | 2012-04-27 | 2012-12-26 | 江苏省电力公司南通供电公司 | Novel intelligent monitoring system for preventing damage on electric power circuit by external force |
| CN102646313A (en) * | 2012-04-27 | 2012-08-22 | 江苏省电力公司南通供电公司 | Electric power line external-damage-preventive intelligent monitoring system |
| CN203204743U (en) * | 2013-04-08 | 2013-09-18 | 西安英诺视通信息技术有限公司 | Mobile external-damage-preventive remote monitoring device of electric transmission line |
-
2014
- 2014-05-12 CN CN201410199455.0A patent/CN103945197B/en active Active
- 2014-05-12 CN CN201710575689.4A patent/CN107222726B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101237522A (en) * | 2007-02-02 | 2008-08-06 | 华为技术有限公司 | Motion detection method and device |
| CN101025862A (en) * | 2007-02-12 | 2007-08-29 | 吉林大学 | Video based mixed traffic flow parameter detecting method |
Non-Patent Citations (3)
| Title |
|---|
| 习可: "基于智能视频技术的铁路入侵检测", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 王瑜: "贝叶斯理论在移动目标检测中的应用", 《计算机工程与应用》 * |
| 葛大伟: "基于视频内容分析的铁路入侵检测研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299224A (en) * | 2014-08-21 | 2015-01-21 | 华南理工大学 | Method for property protection based on video image background matching |
| CN104299224B (en) * | 2014-08-21 | 2017-02-15 | 华南理工大学 | Method for property protection based on video image background matching |
| CN105894701A (en) * | 2016-04-05 | 2016-08-24 | 江苏电力信息技术有限公司 | Large construction vehicle identification and alarm method for preventing external damage to transmission lines |
| CN108074370A (en) * | 2016-11-11 | 2018-05-25 | 国网湖北省电力公司咸宁供电公司 | The early warning system and method that a kind of anti-external force of electric power transmission line based on machine vision is destroyed |
| CN110418192A (en) * | 2019-06-26 | 2019-11-05 | 视联动力信息技术股份有限公司 | A kind of image processing method, device and storage medium |
| CN112312087A (en) * | 2020-10-22 | 2021-02-02 | 中科曙光南京研究院有限公司 | Method and system for quickly positioning event occurrence time in long-term monitoring video |
| CN112312087B (en) * | 2020-10-22 | 2022-07-29 | 中科曙光南京研究院有限公司 | Method and system for quickly positioning event occurrence time in long-term monitoring video |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107222726B (en) | 2020-01-10 |
| CN103945197B (en) | 2017-07-18 |
| CN107222726A (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103945197A (en) | Electric power facility external damage prevention warming scheme based on video motion detecting technology | |
| CN108307146B (en) | System and method for detecting potential safety hazard of high-voltage transmission line | |
| CN109416413B (en) | Solar energy forecast | |
| CN101556142B (en) | Visual detection method of ice coating thickness of overhead lines | |
| CN103246896B (en) | A kind of real-time detection and tracking method of robustness vehicle | |
| CN113205063A (en) | Visual identification and positioning method for defects of power transmission conductor | |
| CN103093192B (en) | The recognition methods that high voltage transmission line is waved | |
| CN107679495A (en) | A kind of detection method of transmission line of electricity periphery activity engineering truck | |
| CN104820995A (en) | Large public place-oriented people stream density monitoring and early warning method | |
| CN103971384B (en) | Node cooperation target tracking method of wireless video sensor | |
| CN105469038A (en) | Safety cap video detection method for electric power switching station | |
| CN103338336A (en) | Video detection method for firework early warning of overhead power transmission line passage | |
| CN116824517B (en) | Substation operation and maintenance safety control system based on visualization | |
| CN106851229A (en) | A kind of method and system of the security protection intelligent decision based on image recognition | |
| CN104159088A (en) | System and method of remote monitoring of intelligent vehicle | |
| CN107657260B (en) | Method for detecting ground hidden danger in power transmission line surrounding environment | |
| CN113099242A (en) | Power transmission line video monitoring data processing method and system | |
| CN105469054A (en) | Model construction method of normal behaviors and detection method of abnormal behaviors | |
| CN110378892A (en) | A kind of method of quick detection electric transmission line channel hidden danger | |
| CN113139431B (en) | Image saliency target detection method based on deep supervised learning | |
| CN107729811B (en) | Night flame detection method based on scene modeling | |
| CN111416964B (en) | Remote image intelligent identification method for hydraulic engineering deformation | |
| CN109740527A (en) | Image processing method in a kind of video frame | |
| CN105335981A (en) | Image-based goods monitoring method | |
| CN115830641B (en) | Employee identification method and device, electronic equipment and storage medium |
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 |