CN104284149A - Electric line dangerous source point oversize vehicle shape change detection video recognition method - Google Patents

Electric line dangerous source point oversize vehicle shape change detection video recognition method Download PDF

Info

Publication number
CN104284149A
CN104284149A CN201410419200.0A CN201410419200A CN104284149A CN 104284149 A CN104284149 A CN 104284149A CN 201410419200 A CN201410419200 A CN 201410419200A CN 104284149 A CN104284149 A CN 104284149A
Authority
CN
China
Prior art keywords
electric line
oversize
dangerous
pictures
picture
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
Application number
CN201410419200.0A
Other languages
Chinese (zh)
Inventor
刘家茂
朱富云
徐剑峰
朱建宝
龚灯才
黄金鑫
陆春峰
林亚阳
鞠易
樊立帆
李学钧
戴相龙
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
JIANGSU HAOHAN INFORMATION TECHNOLOGY Co Ltd
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Nantong Power Supply Co of Jiangsu Electric Power Co Ltd
Original Assignee
JIANGSU HAOHAN INFORMATION TECHNOLOGY Co Ltd
State Grid Corp of China SGCC
State Grid Jiangsu Electric Power Co Ltd
Nantong Power Supply Co of Jiangsu Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by JIANGSU HAOHAN INFORMATION TECHNOLOGY Co Ltd, State Grid Corp of China SGCC, State Grid Jiangsu Electric Power Co Ltd, Nantong Power Supply Co of Jiangsu Electric Power Co Ltd filed Critical JIANGSU HAOHAN INFORMATION TECHNOLOGY Co Ltd
Priority to CN201410419200.0A priority Critical patent/CN104284149A/en
Publication of CN104284149A publication Critical patent/CN104284149A/en
Pending legal-status Critical Current

Links

Abstract

The invention discloses an electric line dangerous source point oversize vehicle shape change detection video recognition method. The method comprises the steps that video images collected by a front end camera are decompressed and resolved into YUV pictures; the YUV pictures are transformed into RGB pictures; the later frames of pictures are compared with the previous frames of pictures, the background environment is updated in real time through self-learning, and moving target objects, specifically oversize dangerous vehicles, are drawn out of background environment; after the target objects are targeted, gray level calculation is conducted on the oversize dangerous vehicles, and recognition and alarming are conducted after the oversize dangerous vehicles stay at the positions of dangerous source points and have shape changes. By means of the electric line dangerous source point oversize vehicle shape change detection video recognition method, the situation of the body changes of the oversize dangerous vehicles at the electric line dangerous source points can be conveniently recognized in time; the electric line dangerous source points can be uninterruptedly monitored in 7*24 hours, the external force destructive incidents brought by the negligence of people can be excluded, and a third line of defense for preventing external deconstruction is formed.

Description

Electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method
Technical field
The present invention relates to a kind of electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method.
Background technology
For electric power facility, how by analyzing electric line hazard Identification oversize vehicle body shape changes situation, being the target of technical staff's long-sought, not having desirable method yet so far.
Summary of the invention
The object of the present invention is to provide convenient, the timely electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method that electric line hazard Identification oversize vehicle body shape changes situation is identified of a kind of energy.
Technical solution of the present invention is:
A kind of electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method, is characterized in that: concrete steps:
(1) video image is gathered by front-end camera;
(2) decompress gathering the video image of returning, and resolve into the YUV picture of intellectual analysis needs;
(3) YUV picture is converted to RGB picture;
25 frame RGB pictures can be resolved into (4) one seconds, then therefrom randomly draw 10 frames and carry out analysis contrast;
(5) a rear frame picture and former frame picture are contrasted, and utilize self study, real-time update background environment, therefrom detach moving target object-refer in particular to large-scale hazardous vehicles;
(6) after locking onto target object, gray scale calculating is carried out to large-scale hazardous vehicles, when large-scale hazardous vehicles stops in hazard Identification position, and give to identify after there is body shape changes and report to the police.
The present invention can facilitate, identify electric line hazard Identification oversize vehicle body shape changes situation in time; Rest on electric line hazard Identification region by the large-scale hazardous vehicles of the continual detection of intelligent video monitoring and whether have body shape changes, can realize the continual monitoring in 7x24 hour of electric line hazard Identification, get rid of the outside destroy event because human negligence brings, form anti-outer broken three lines of defence.Being mainly used in intelligent video analysis, whether have body shape changes, whether cause potential safety hazard to electric line if detecting the large-scale hazardous vehicles resting on electric line hazard Identification region.
Below in conjunction with embodiment, the invention will be further described.
Embodiment
A kind of electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method, is characterized in that: concrete steps:
(1) video image is gathered by front-end camera;
(2) decompress gathering the video image of returning, and resolve into the YUV picture of intellectual analysis needs;
(3) YUV picture is converted to RGB picture;
25 frame RGB pictures can be resolved into (4) one seconds, then therefrom randomly draw 10 frames and carry out analysis contrast;
(5) a rear frame picture and former frame picture are contrasted, and utilize self study, real-time update background environment, therefrom detach moving target object-refer in particular to large-scale hazardous vehicles;
(6) after locking onto target object, gray scale calculating is carried out to large-scale hazardous vehicles, when large-scale hazardous vehicles stops in hazard Identification position, and give to identify after there is body shape changes and report to the police.
Electric line hazard Identification oversize vehicle body shape changes detects intelligent video recognition methods with intelligent image analytical technology for core, so-called intelligent image analytical technology uses computer picture Visual analysis techniques exactly, by background in scene being separated with target and then analyzing and follow the trail of the target occurred in camera scene, after determining target, target object body identified and gray scale is calculated, finally determining whether the oversize vehicle resting on hazard Identification region has body shape changes.
The picture breakdown of front-end camera collection is become picture one by one, select suitable frame to pass to core intelligence image analysis module according to actual conditions and carry out graphical analysis, the rear image of a frame and the image of former frame are contrasted, and utilize the slight change of automatic learning scene, thus set up and safeguard the background environment of a real-time update, this background environment can slight change environmentally and changing.Again the thing beyond background is therefrom detached, thus form the object on picture.Because every sample object can detach from background, and object pixel coordinate corresponding in picture can be provided, we just can calculate its gray scale according to its coordinate position, and whether detect the large-scale hazardous vehicles rested in hazard Identification region has body shape changes.

Claims (1)

1. an electric line hazard Identification oversize vehicle body shape changes detecting video frequency identifying method, is characterized in that: concrete steps:
(1) video image is gathered by front-end camera;
(2) decompress gathering the video image of returning, and resolve into the YUV picture of intellectual analysis needs;
(3) YUV picture is converted to RGB picture;
25 frame RGB pictures can be resolved into (4) one seconds, then therefrom randomly draw 10 frames and carry out analysis contrast;
(5) a rear frame picture and former frame picture are contrasted, and utilize self study, real-time update background environment, therefrom detach moving target object-refer in particular to large-scale hazardous vehicles;
(6) after locking onto target object, gray scale calculating is carried out to large-scale hazardous vehicles, when large-scale hazardous vehicles stops in hazard Identification position, and give to identify after there is body shape changes and report to the police.
CN201410419200.0A 2014-08-25 2014-08-25 Electric line dangerous source point oversize vehicle shape change detection video recognition method Pending CN104284149A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201410419200.0A CN104284149A (en) 2014-08-25 2014-08-25 Electric line dangerous source point oversize vehicle shape change detection video recognition method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201410419200.0A CN104284149A (en) 2014-08-25 2014-08-25 Electric line dangerous source point oversize vehicle shape change detection video recognition method

Publications (1)

Publication Number Publication Date
CN104284149A true CN104284149A (en) 2015-01-14

Family

ID=52258568

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201410419200.0A Pending CN104284149A (en) 2014-08-25 2014-08-25 Electric line dangerous source point oversize vehicle shape change detection video recognition method

Country Status (1)

Country Link
CN (1) CN104284149A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105025263A (en) * 2015-07-10 2015-11-04 国家电网公司 Large-size vehicle positioning method for power transmission and distribution line channel
CN105022997A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent truck crane video identification method for power transmission and distribution line channel
CN105022998A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent plastic greenhouse flotage video identification method for power transmission and distribution line channel
CN105022996A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent concrete pump truck video identification method for power transmission and distribution line channel
CN105160363A (en) * 2015-07-10 2015-12-16 国家电网公司 Power transmission and distribution line channel color steel tile floater intelligent video identification method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102737463A (en) * 2011-04-07 2012-10-17 胡茂林 Monitoring and alarming system for indoor personnel intrusion based on intelligent video
CN103108159A (en) * 2013-01-17 2013-05-15 新疆电力公司乌鲁木齐电业局 Electric power intelligent video analyzing and monitoring system and method
US20130328596A1 (en) * 2012-06-11 2013-12-12 Thomas Alois Zoels Apparatus and method for power switch health monitoring

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102737463A (en) * 2011-04-07 2012-10-17 胡茂林 Monitoring and alarming system for indoor personnel intrusion based on intelligent video
US20130328596A1 (en) * 2012-06-11 2013-12-12 Thomas Alois Zoels Apparatus and method for power switch health monitoring
CN103108159A (en) * 2013-01-17 2013-05-15 新疆电力公司乌鲁木齐电业局 Electric power intelligent video analyzing and monitoring system and method

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
赵向梅 等: "基于视频图像的目标检测技术研究", 《电子设计工程》 *

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105025263A (en) * 2015-07-10 2015-11-04 国家电网公司 Large-size vehicle positioning method for power transmission and distribution line channel
CN105022997A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent truck crane video identification method for power transmission and distribution line channel
CN105022998A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent plastic greenhouse flotage video identification method for power transmission and distribution line channel
CN105022996A (en) * 2015-07-10 2015-11-04 国家电网公司 Intelligent concrete pump truck video identification method for power transmission and distribution line channel
CN105160363A (en) * 2015-07-10 2015-12-16 国家电网公司 Power transmission and distribution line channel color steel tile floater intelligent video identification method

Similar Documents

Publication Publication Date Title
CN104284149A (en) Electric line dangerous source point oversize vehicle shape change detection video recognition method
CN106341661B (en) Patrol robot
CN103413395B (en) Flue gas intelligent detecting prewarning method and device
CN103366565B (en) Method and system of detecting pedestrian running red light based on Kinect
CN102665071B (en) Intelligent processing and search method for social security video monitoring images
CN103986906B (en) Door opening and closing detection method based on monitoring videos
CN102164270A (en) Intelligent video monitoring method and system capable of exploring abnormal events
CN105469073A (en) Kinect-based call making and answering monitoring method of driver
EP2851841A8 (en) System and method of alerting a driver that visual perception of pedestrian may be difficult
CN104123567A (en) Method for site remaining intelligent video recognition of electric power operation tools and instruments
CN104077581A (en) Smart video identification method for wearing safety helmet rightly
CN106651855A (en) Image monitoring and shooting method for automatic identification and alarming of hidden troubles of power transmission line channel
WO2021020866A9 (en) Image analysis system and method for remote monitoring
CN103150901A (en) Abnormal traffic condition detection method based on vehicle motion vector field analysis
CN104112146A (en) Power operation single-person work effective monitoring intelligent video recognizing method
CN110703760A (en) Newly-increased suspicious object detection method for security inspection robot
CN102254396B (en) Intrusion detection method and device based on video
CN104103074A (en) Valve control identification method of vehicle operation lift arm
CN104092922A (en) Transformer substation electrified body intelligent video distance management and control method
CN104243852A (en) Traffic monitoring and environment information collecting system
CN104392201A (en) Human fall identification method based on omnidirectional visual sense
CN110992629A (en) Method for detecting static human body based on video monitoring
CN105069397A (en) Intelligent video identification method for out-of-control kite on power transmission and distribution line channel
CN105022998A (en) Intelligent plastic greenhouse flotage video identification method for power transmission and distribution line channel
JP2018151765A5 (en)

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20150114