CN112381053B - Environment-friendly monitoring system with image tracking function - Google Patents

Environment-friendly monitoring system with image tracking function Download PDF

Info

Publication number
CN112381053B
CN112381053B CN202011386262.8A CN202011386262A CN112381053B CN 112381053 B CN112381053 B CN 112381053B CN 202011386262 A CN202011386262 A CN 202011386262A CN 112381053 B CN112381053 B CN 112381053B
Authority
CN
China
Prior art keywords
target
template
gray
value
area
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.)
Active
Application number
CN202011386262.8A
Other languages
Chinese (zh)
Other versions
CN112381053A (en
Inventor
张燕
修春波
董淑亮
范琳琳
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.)
Lianyungang Haorui Biotechnology Co ltd
Original Assignee
Lianyungang Haorui Biotechnology 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 Lianyungang Haorui Biotechnology Co ltd filed Critical Lianyungang Haorui Biotechnology Co ltd
Priority to CN202011386262.8A priority Critical patent/CN112381053B/en
Publication of CN112381053A publication Critical patent/CN112381053A/en
Application granted granted Critical
Publication of CN112381053B publication Critical patent/CN112381053B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/54—Interprogram communication
    • G06F9/545—Interprogram communication where tasks reside in different layers, e.g. user- and kernel-space
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Security & Cryptography (AREA)
  • Multimedia (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Evolutionary Computation (AREA)
  • Evolutionary Biology (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Human Computer Interaction (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Hardware Design (AREA)
  • Image Analysis (AREA)
  • Closed-Circuit Television Systems (AREA)

Abstract

The invention belongs to the field of environment-friendly detection, and particularly relates to an environment-friendly monitoring system capable of tracking image targets in a sensitive area. The system comprises a sensing layer, a network layer and an application layer. The sensing layer utilizes a bottom layer instrument, a sensor and equipment to collect data information and utilizes a camera to realize the collection of environment image information of a sensitive area. And the network layer processes and transmits the data information obtained by the sensing layer. The application layer realizes the functions of equipment management and maintenance, monitoring and early warning, production scheduling, real-time data curve display, abnormal warning and the like according to the obtained data information. The invention can be applied to an environment-friendly monitoring system.

Description

Environment-friendly monitoring system with image tracking function
Technical Field
The invention belongs to the field of environment-friendly detection, relates to an environment-friendly monitoring system with an image tracking function, and particularly relates to an environment-friendly monitoring system capable of tracking image targets in a sensitive area.
Background
The environmental monitoring has important application value in the fields of sewage treatment, pollution gas treatment, construction management and the like. The environmental monitoring system based on the internet of things technology integrates information collected by various sensors, video monitoring, infrared detection, GPS, RFID, satellite remote sensing and the like, realizes collection of various environmental data information of a monitored area, realizes early warning through information processing and integration, and avoids serious pollution. Especially for some important sensitive areas, such as power distribution rooms, machine rooms, operation rooms and the like, video monitoring is needed. When a person enters the system in an unauthorized period, the monitoring camera can lock the moving target, and the target is continuously tracked by the driving of the holder. In order to ensure that stable tracking of the target can be effectively realized in different time periods, the tracking algorithm should have good adaptability and stability. At present, deep learning shows excellent performance in the field of target tracking, but a target tracking method based on deep learning generally requires a large number of training samples and performs long-time training, which puts high requirements on hardware configuration of a system, and causes increase of system hardware cost and runtime cost. The traditional tracking method is usually small in operation amount and low in system hardware requirement, but certain instability exists in tracking performance.
Therefore, the target tracking method with better adaptability is designed, and the method has good application value for improving the performance of the environment-friendly monitoring system.
Disclosure of Invention
The invention aims to solve the technical problem that in order to improve the intelligent level of an environment-friendly monitoring system, the environment-friendly monitoring system with the image target detection and tracking functions is designed, environment information is detected by a sensor, a camera is used for monitoring a sensitive area, an unauthorized entering target is tracked, and alarm is realized.
The technical scheme adopted by the invention is as follows: an environment-friendly monitoring system with an image target tracking function comprises a three-layer structure of a sensing layer, a network layer and an application layer. The sensing layer utilizes a bottom layer instrument, a sensor and equipment to collect data information and utilizes a camera to realize the collection of environment image information of a sensitive area. And the network layer processes and transmits the data information obtained by the sensing layer. The application layer realizes the functions of equipment management and maintenance, monitoring and early warning, production scheduling, real-time data curve display, abnormal warning and the like according to the obtained data information.
The invention aims to construct an environment-friendly detection system which can collect environmental information and can monitor images of a sensitive area, and the environment-friendly detection system has good practicability.
Drawings
FIG. 1 is a schematic diagram of a target area and a non-target area in an image of a scene.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
The sensing layer collects various data information such as temperature, humidity and air pollutants of an environment to be monitored, and image information of a monitoring sensitive area is collected through the camera. When the monitoring sensitive area is in a state of prohibiting personnel from entering, if a moving target is found, the camera is driven by the holder to track the target. The system transmits various monitoring data acquired by the sensing layer, sensitive area images monitored by the camera, whether moving objects enter and other information to the application layer through the network layer. And the application layer stores, displays and alarms according to the acquired data.
For the sensitive areas to be monitored, such as a power distribution room, a machine room, an operation room and the like, an image acquisition device is installed, and the image acquisition device carries out image monitoring on the sensitive areas through a camera driven by a holder. The image acquisition device has two working states, one is a normal scanning shooting state, and the other is a target detection tracking state. The sensitive areas monitored are only accessible to authorized personnel. After authorized personnel input the password for verification, the image acquisition device in the monitored sensitive area works in a normal scanning and shooting state, at the moment, the cradle head drives the camera to continuously rotate, and the shot image is transmitted to the application layer through the network layer. Authorized personnel leave the sensitive area and input an instruction for prohibiting entering, the image acquisition device works in a target detection tracking state, at the moment, the image acquisition device detects whether a moving target exists in the sensitive area, background images of a monitoring scene corresponding to all positions of a holder are prestored in the image acquisition device, the holder in the image acquisition device drives a camera to continuously rotate, target detection is carried out by using a background difference method according to the currently acquired position image and the background image of the prestored position, and when the target is not found, the target detection is carried out by continuously using the background difference method, and image information is transmitted to an application layer through a network layer; when a moving target is detected, the target is tracked, and simultaneously, the image and the alarm information are transmitted to an application layer through a network layer.
When the image acquisition device works in a target detection tracking state, a moving target area is determined by using a background difference method, the moving target area is selected as a tracked target, and the tracked target is tracked by adopting a target tracking method of characteristic weighting matching.
The target tracking method of feature weighted matching respectively establishes a template and a non-target area gray histogram model around the template, determines the enhancement weight coefficient of each gray level according to the template gray histogram model, determines the suppression weight coefficient of each gray level according to the non-target area histogram model around the template, adopts a weighted matching mode, highlights the matching function of the main gray level of the template, suppresses the matching function of the main gray level of the non-target area, and thus improves the accuracy of target identification.
The size of the target tracking template A is set to be M multiplied by N, and the length and the width of the target area of the current frame are expanded outwards in each direction to form a non-target area B, as shown in figure 1. Establishing a gray histogram model q according to the pixel gray value of the target tracking template AAEstablishing a gray histogram model q according to the pixel gray value of the non-target area BB. Dividing the gray value into m levels, and setting the position coordinate of each pixel in the template as { (x)i,yi) 1, 2, …, s. Corresponding to a gray scale characteristic value of bA(xi,yi) Gray level feature histogram model of template
Figure BDA0002809778340000021
Figure BDA0002809778340000022
Where δ is the korneecker function.
The gray level target weight value is defined as:
Figure BDA0002809778340000023
wherein q isA uAnd q isA vRespectively representing the number of pixels of the u-th and v-th gray levels of the target template. w is aA uIs the target weight value of the u-th gray level.
Let the position coordinates of each pixel in the non-target region be { (x)j,yj) 1, 2, …, t. Corresponding to a gray scale characteristic value of bB(xj,yj) Then the histogram model of the gray scale features of the non-target area is
Figure BDA0002809778340000031
Figure BDA0002809778340000032
The gray level non-target weighting value is defined as:
Figure BDA0002809778340000033
wherein q isB uAnd q isB vRespectively representing the number of pixels of the u-th and v-th gray levels of the non-target area. w is aB uA non-target weight value for the u-th gray level.
Pixel point (x) in template image Ai,yi) Has a gray value of fA(xi,yi) And the corresponding pixel point (x) in the matching area C of the image to be matched with the template image A with the same sizei,yi) Has a gray value of fC(xi,yi) The corresponding gray scale characteristic value is bC(xi,yi) Then, the matching value D of the template image A and the image matching area CCIs defined as:
Figure BDA0002809778340000034
and traversing and searching the template A in a search area of the image to be matched, and positioning the matching area with the maximum matching value as a target position. And taking the newly positioned target area as a template, and continuously positioning the target in the next frame, thereby realizing the continuous tracking of the target.
When the matching criterion function is calculated, the distribution information of the gray levels in the template and the non-target area is considered, the matching value of the pixel points with the main gray level in the template plays a main role, and the matching effect of the pixel points with the main gray level in the non-target area is inhibited, so that the matching result can highlight the main characteristics of the template, inhibit the interference of the background and be beneficial to improving the matching accuracy. Compared with the traditional target tracking method, the method has better target positioning accuracy.
The method has the advantages that the pixel points with the main gray scale of the template image in the matching criterion function of the tracking method play a main role, the matching effect of the pixel points with the main gray scale in the non-target area is inhibited, the image target can be positioned in a more complex background, the target positioning accuracy is improved, and the monitoring reliability of the environment-friendly monitoring system on the sensitive area can be improved.

Claims (1)

1. An environment-friendly monitoring system with an image tracking function is characterized in that the system comprises a three-layer structure of a sensing layer, a network layer and an application layer; the sensing layer collects data information by using a bottom instrument, a sensor and equipment, and collects environmental image information of a sensitive area by using a camera; the network layer processes and transmits the data information obtained by the sensing layer; the application layer realizes the functions of equipment management and maintenance, monitoring and early warning, production scheduling, real-time data curve display, abnormal warning and the like according to the obtained data information; when the image acquisition device works in a target detection tracking state, determining a moving target area by using a background difference method, selecting the moving target area as a tracked target, and tracking the tracked target by adopting a target tracking method of characteristic weighting matching; the target tracking method of feature weighted matching respectively establishes a template and a non-target area gray histogram model around the template, determines an enhanced weight coefficient of each gray level according to the template gray histogram model, determines an inhibition weight coefficient of each gray level according to the non-target area histogram model around the template, adopts a weighted matching mode to highlight the matching function of the main gray level of the template and inhibit the matching function of the main gray level of the non-target area, thereby improving the accuracy of target identification; setting the size of a target tracking template A as M multiplied by N, expanding a certain area of the length and the width of a target area of a current frame in each direction, and removing the target area to form a non-target area B which does not contain the target area; establishing a gray histogram model q according to the pixel gray value of the target tracking template AAEstablishing a gray histogram model q according to the pixel gray value of the non-target area BBDividing the gray scale value into m levels, and setting the position coordinate of each pixel in the template as { (x)i,yi) 1, 2, …, s; corresponding gray scale featuresCharacteristic value of bA(xi,yi) Gray level feature histogram model of template
Figure FDA0003295130410000011
Figure FDA0003295130410000012
Where δ is the korneecker function, the gray level target weighting value is defined as:
Figure FDA0003295130410000013
wherein q isA uAnd q isA vThe pixel numbers respectively representing the u-th and v-th gray levels of the target template; w is aA uA target weight value for the u-th gray level; let the position coordinates of each pixel in the non-target region be { (x)j,yj) 1, 2, …, t; corresponding to a gray scale characteristic value of bB(xj,yj) Then the histogram model of the gray scale features of the non-target area is
Figure FDA0003295130410000014
Figure FDA0003295130410000015
The gray level non-target weighting value is defined as:
Figure FDA0003295130410000016
wherein q isB uAnd q isB vThe number of pixels respectively representing the u-th and v-th gray levels of the non-target area; w is aB uIs the u-thA non-target weighting value for the gray scale; pixel point (x) in template image Ai,yi) Has a gray value of fA(xi,yi) And the corresponding pixel point (x) in the matching area C of the image to be matched with the template image A with the same sizei,yi) Has a gray value of fC(xi,yi) The corresponding gray scale characteristic value is bC(xi,yi) Then, the matching value D of the template image A and the image matching area CCIs defined as:
Figure FDA0003295130410000021
traversing and searching the template A in a search area of an image to be matched, and positioning the matching area with the maximum matching value as a target position; and taking the newly positioned target area as a template, and continuously positioning the target in the next frame, thereby realizing the continuous tracking of the target.
CN202011386262.8A 2020-12-01 2020-12-01 Environment-friendly monitoring system with image tracking function Active CN112381053B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011386262.8A CN112381053B (en) 2020-12-01 2020-12-01 Environment-friendly monitoring system with image tracking function

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011386262.8A CN112381053B (en) 2020-12-01 2020-12-01 Environment-friendly monitoring system with image tracking function

Publications (2)

Publication Number Publication Date
CN112381053A CN112381053A (en) 2021-02-19
CN112381053B true CN112381053B (en) 2021-11-19

Family

ID=74590147

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011386262.8A Active CN112381053B (en) 2020-12-01 2020-12-01 Environment-friendly monitoring system with image tracking function

Country Status (1)

Country Link
CN (1) CN112381053B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114581781B (en) * 2022-05-05 2022-08-09 之江实验室 Target detection method and device for high-resolution remote sensing image

Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6901110B1 (en) * 2000-03-10 2005-05-31 Obvious Technology Systems and methods for tracking objects in video sequences
CN101251928A (en) * 2008-03-13 2008-08-27 上海交通大学 Object tracking method based on core
CN101369346A (en) * 2007-08-13 2009-02-18 北京航空航天大学 Tracing method for video movement objective self-adapting window
JP2009087090A (en) * 2007-09-28 2009-04-23 Sony Computer Entertainment Inc Object tracking device and object tracing method
CN101667294A (en) * 2009-09-10 2010-03-10 天津工业大学 Object detecting and tracking device
CN102663773A (en) * 2012-03-26 2012-09-12 上海交通大学 Dual-core type adaptive fusion tracking method of video object
CN103078951A (en) * 2013-01-23 2013-05-01 李朝阳 Environmental-protection data acquisition device based on mobile application
CN104616433A (en) * 2015-02-04 2015-05-13 清华大学 Real-time monitoring and early warning system for foundation pit engineering
CN105118071A (en) * 2015-08-04 2015-12-02 山东大学 Novel video tracking method based on self-adaptive partitioning
CN105469532A (en) * 2015-12-10 2016-04-06 东华大学 A substation box temperature monitoring antitheft alarm system based on video monitoring
CN106164994A (en) * 2014-04-09 2016-11-23 株式会社技术未来 Numerical loss/accident system of defense, methods and procedures
CN106683118A (en) * 2016-12-30 2017-05-17 北京航空航天大学 Unmanned plane target tracking method based on hierarchical model
CN107808392A (en) * 2017-10-31 2018-03-16 中科信达（福建）科技发展有限公司 The automatic method for tracking and positioning of safety check vehicle and system of open scene
CN208171339U (en) * 2018-05-22 2018-11-30 大唐环境产业集团股份有限公司 A kind of power plant's intelligent environment protection emission monitoring system
CN109257417A (en) * 2018-08-20 2019-01-22 山东润智能科技有限公司 Boiler in hospital security stereo monitors cloud platform, system and method
CN109448194A (en) * 2018-12-03 2019-03-08 厦门路桥信息股份有限公司 Intrusion detecting tracking system and method
CN109544604A (en) * 2018-11-28 2019-03-29 天津工业大学 Method for tracking target based on cognition network
CN109859245A (en) * 2019-01-22 2019-06-07 深圳大学 Multi-object tracking method, device and the storage medium of video object
CN110874905A (en) * 2018-08-31 2020-03-10 杭州海康威视数字技术股份有限公司 Monitoring method and device

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020176001A1 (en) * 2001-05-11 2002-11-28 Miroslav Trajkovic Object tracking based on color distribution
CN104820996B (en) * 2015-05-11 2018-04-03 河海大学常州校区 A kind of method for tracking target of the adaptive piecemeal based on video
CN106152949A (en) * 2016-07-15 2016-11-23 同济大学 A kind of noncontact video displacement measurement method
CN110796688A (en) * 2019-11-05 2020-02-14 广东机场白云信息科技有限公司 Multi-target face recognition intelligent flight information display method and system

Patent Citations (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6901110B1 (en) * 2000-03-10 2005-05-31 Obvious Technology Systems and methods for tracking objects in video sequences
CN101369346A (en) * 2007-08-13 2009-02-18 北京航空航天大学 Tracing method for video movement objective self-adapting window
JP2009087090A (en) * 2007-09-28 2009-04-23 Sony Computer Entertainment Inc Object tracking device and object tracing method
CN101251928A (en) * 2008-03-13 2008-08-27 上海交通大学 Object tracking method based on core
CN101667294A (en) * 2009-09-10 2010-03-10 天津工业大学 Object detecting and tracking device
CN102663773A (en) * 2012-03-26 2012-09-12 上海交通大学 Dual-core type adaptive fusion tracking method of video object
CN103078951A (en) * 2013-01-23 2013-05-01 李朝阳 Environmental-protection data acquisition device based on mobile application
CN106164994A (en) * 2014-04-09 2016-11-23 株式会社技术未来 Numerical loss/accident system of defense, methods and procedures
CN104616433A (en) * 2015-02-04 2015-05-13 清华大学 Real-time monitoring and early warning system for foundation pit engineering
CN105118071A (en) * 2015-08-04 2015-12-02 山东大学 Novel video tracking method based on self-adaptive partitioning
CN105469532A (en) * 2015-12-10 2016-04-06 东华大学 A substation box temperature monitoring antitheft alarm system based on video monitoring
CN106683118A (en) * 2016-12-30 2017-05-17 北京航空航天大学 Unmanned plane target tracking method based on hierarchical model
CN107808392A (en) * 2017-10-31 2018-03-16 中科信达（福建）科技发展有限公司 The automatic method for tracking and positioning of safety check vehicle and system of open scene
CN208171339U (en) * 2018-05-22 2018-11-30 大唐环境产业集团股份有限公司 A kind of power plant's intelligent environment protection emission monitoring system
CN109257417A (en) * 2018-08-20 2019-01-22 山东润智能科技有限公司 Boiler in hospital security stereo monitors cloud platform, system and method
CN110874905A (en) * 2018-08-31 2020-03-10 杭州海康威视数字技术股份有限公司 Monitoring method and device
CN109544604A (en) * 2018-11-28 2019-03-29 天津工业大学 Method for tracking target based on cognition network
CN109448194A (en) * 2018-12-03 2019-03-08 厦门路桥信息股份有限公司 Intrusion detecting tracking system and method
CN109859245A (en) * 2019-01-22 2019-06-07 深圳大学 Multi-object tracking method, device and the storage medium of video object

Non-Patent Citations (6)

* Cited by examiner, † Cited by third party
Title
Improved camshift algorithm based on weighted histogram model;Liu Wang et al;《The 27th Chinese Control and Decision Conference (2015 CCDC)》;20150720;第5795-5798页 *
Object Tracking in Video Sequence Images Based on Color Histogram and Central Voting;Ahmad samaeifar et al;《International Journal of Mathematics and Computer Sciences (IJMCS)》;20141031;第34卷;第990-1106页 *
Visual tracking by partition-based histogram backprojection and maximum support criteria;Jae-Yeong Lee et al;《2011 IEEE International Conference on Robotics and Biomimetics》;20120412;第2860-2865页 *
基于直方图比的背景加权的mean shift目标跟踪算法;王晓卫等;《强激光与粒子束》;20160531;第28卷(第5期);第1-5页 *
显著性直方图模型的camshift跟踪方法;修春波等;《光学精密工程》;20150630;第23卷(第6期);第2节 *
背景抑制直方图模型的连续自适应均值漂移跟踪算法;王旭东等;《电子与信息学报》;20190630;第41卷(第6期);第1480-1487页 *

Also Published As

Publication number Publication date
CN112381053A (en) 2021-02-19

Similar Documents

Publication Publication Date Title
CN110321853B (en) Distributed cable external-damage-prevention system based on video intelligent detection
CN105894702B (en) Intrusion detection alarm system based on multi-camera data fusion and detection method thereof
US9619999B2 (en) Sensor event assessor input/output controller
KR101788269B1 (en) Method and apparatus for sensing innormal situation
KR101644443B1 (en) Warning method and system using prompt situation information data
CN106781165A (en) A kind of indoor multi-cam intelligent linkage supervising device based on depth sensing
CN110040595B (en) Elevator door state detection method and system based on image histogram
CN108629935B (en) Method and system for detecting burglary of climbing stairs and turning windows based on video monitoring
CN103517042A (en) Nursing home old man dangerous act monitoring method
CN110275042B (en) High-altitude parabolic detection method based on computer vision and radio signal analysis
CN109740411A (en) Intelligent monitor system, monitoring method based on recognition of face and quickly go out alarm method
CN102254394A (en) Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis
CN112907869B (en) Intrusion detection system based on multiple sensing technologies
CN104933542B (en) A kind of logistic storage monitoring method based on computer vision
CN103152558B (en) Based on the intrusion detection method of scene Recognition
CN109033979B (en) Indoor pedestrian detection method based on WIFI and camera sensor decision-level fusion
CN112381053B (en) Environment-friendly monitoring system with image tracking function
CN115035470A (en) Low, small and slow target identification and positioning method and system based on mixed vision
CN110703760A (en) Newly-increased suspicious object detection method for security inspection robot
CN111885349A (en) Pipe rack abnormity detection system and method
CN117275158A (en) Intelligent surrounding biological identification tracking method and system
Yu et al. Review of intelligent video surveillance technology research
US11983963B2 (en) Anti-spoofing visual authentication
CN113239772A (en) Personnel gathering early warning method and system in self-service bank or ATM environment
Huang et al. Smoke identification of low-light indoor video based on support vector machine

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
GR01 Patent grant
GR01 Patent grant