CN113657297A - Intelligent operation violation identification method and device based on characteristic analysis - Google Patents
Intelligent operation violation identification method and device based on characteristic analysis Download PDFInfo
- Publication number
- CN113657297A CN113657297A CN202110959232.XA CN202110959232A CN113657297A CN 113657297 A CN113657297 A CN 113657297A CN 202110959232 A CN202110959232 A CN 202110959232A CN 113657297 A CN113657297 A CN 113657297A
- Authority
- CN
- China
- Prior art keywords
- violation
- identification method
- intelligent
- image
- job
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000004458 analytical method Methods 0.000 title claims abstract description 28
- 230000009471 action Effects 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 230000006399 behavior Effects 0.000 claims description 9
- 230000003287 optical effect Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000012423 maintenance Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000002955 isolation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/254—Analysis of motion involving subtraction of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/269—Analysis of motion using gradient-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20212—Image combination
- G06T2207/20224—Image subtraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30196—Human being; Person
- G06T2207/30201—Face
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an intelligent operation violation identification method and equipment based on characteristic analysis, wherein the method comprises the following steps: reading a real-time image sequence from a video to be identified, and preprocessing each frame image of the image sequence; extracting a violation target from each frame of image, and carrying out tracking and behavior understanding analysis based on a real-time image sequence to obtain the action characteristics of the violation target; based on the action characteristics, when the face can be detected, the associated personnel information base is called to compare the face, and the identity of the violation personnel is identified. Compared with the prior art, the method has the advantages of high reliability, capability of timely realizing the identification of the violation personnel and the like.
Description
Technical Field
The invention belongs to the field of risk pre-control, and particularly relates to an intelligent operation violation identification method and equipment based on feature analysis.
Background
The production management in the whole process of the power plant is the safety management of the links of operation, maintenance and technical transformation, and the personal safety, equipment safety and operation safety are ensured. On-site operation and maintenance personnel need to carry out operation maintenance, periodic tests, equipment defect elimination, isolation of an operation and maintenance equipment system and perfection of safety measures on equipment and a site. At the present stage, the electric power industry is in digital and intelligent vigorous development, an intelligent algorithm for field video monitoring is increasingly strong, and the intelligent identification method can be used for intelligently identifying a plurality of violation behaviors in an operation field, such as no safety helmet is worn, no helmet belt is tied, field smoking is carried out, no safety belt is tied in high-altitude operation, and the like, and can automatically give an alarm.
However, the existing intelligent identification method has the following inherent defects: only the phenomenon of violation can be identified, and an accurate judgment method is lacked for who the violation personnel is, particularly the angle of the personnel facing back to the camera or other angles incapable of identifying the face.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide the intelligent operation violation identification method and equipment based on the characteristic analysis, which have high reliability and can realize the identification of the violation personnel in time.
The purpose of the invention can be realized by the following technical scheme:
a job violation intelligent identification method based on feature analysis comprises the following steps:
reading a real-time image sequence from a video to be identified, and preprocessing each frame image of the image sequence;
extracting a violation target from each frame of image, and carrying out tracking and behavior understanding analysis based on a real-time image sequence to obtain the action characteristics of the violation target;
based on the action characteristics, when the face can be detected, the associated personnel information base is called to compare the face, and the identity of the violation personnel is identified.
Further, the preprocessing includes filtering and gray-scale conversion.
Further, the extracting of the violation target from each frame image specifically includes:
and separating a suspected violation area and a background image according to the position and the angle of the person in the image, comparing the suspected violation area with the fixed violation model, judging whether the violation person exists in the image, and if so, acquiring the violation target based on the body area and the outline of the violation person.
Further, the fixed violation model comprises a plurality of violation models with different angles and different light rays.
Further, the suspected violation area is further determined using the difference of the currently extracted image and the background image.
Further, the tracking and behavior understanding analysis is implemented by a motion detection algorithm based on a time-difference comparison and an optical flow method.
Further, the time difference comparison specifically comprises:
and (3) converting the real-time image sequence data, and comparing data differences between two adjacent frames of images, wherein the data differences comprise differences of pixels, coordinates and/or deformation.
Further, the method further comprises:
recording the identity of the violation personnel and the violation event information as a violation log, and pushing the violation log to a management terminal.
Further, the violation event information includes the nature of the violation, the time of the violation, and the location of the violation.
The present invention also provides an electronic device comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for performing a feature analysis based intelligent job violation identification method as described.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention collects an image sequence, carries out reliable face recognition in time based on the action characteristic analysis of the violation target, is suitable for the condition that personnel back to a camera or other angles which can not recognize the face, and solves the problem that the intelligent violation recognition algorithm can not confirm the identity of the violation personnel under specific conditions.
2. The invention adopts image processing, mode recognition and computer vision technology to filter useless or interference information of video pictures, and has high recognition precision.
3. The invention can associate the violation behaviors with the personnel file system, and can automatically record the violation conditions of each operating personnel to form violation records, thereby effectively carrying out pre-warning, in-process treatment and post-examination evidence collection and realizing intellectualization of violation examination.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
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.
Example 1
As shown in fig. 1, the present embodiment provides a job violation intelligent identification method based on feature analysis, including the following steps:
s101, reading a real-time image sequence from a video to be identified, and preprocessing each frame of image of the image sequence, including filtering, gray level conversion and the like.
S102, extracting a violation target from each frame of image, and carrying out tracking and behavior understanding analysis based on a real-time image sequence to obtain the action characteristics of the violation target.
The specific steps of extracting the violation target from each frame image are as follows: and separating a suspected violation area and a background image according to the position and the angle of the person in the image, comparing the suspected violation area with the fixed violation model, judging whether the violation person exists in the image, and if so, acquiring the violation target based on the body area and the outline of the violation person.
The fixed violation models comprise various violation models with different angles and different light rays, and are models which are constructed in advance, stored and used for realizing comparison.
In the embodiment, the suspected violation area is further determined by using the difference between the currently extracted image and the background image, the interference of dynamic scene change, such as light irradiation and other conditions, can be eliminated, the effect of accurate separation can be achieved, the body area and the outline of the violation personnel can be correctly segmented, and the subsequent tracking and behavior understanding effects can be improved.
In this embodiment, the tracking and behavior understanding analysis is implemented by a motion detection algorithm based on a time-difference comparison and an optical flow method. Wherein, the time difference comparison specifically comprises: converting real-time image sequence data by using the characteristics of the video image, and comparing data differences between two adjacent frames of images, wherein the data differences comprise differences of pixels, coordinates and/or deformation; in motion detection based on an optical flow method, the optical flow characteristics of a tracked target changing along with time are collected, and a tracking algorithm based on a contour is initialized by calculating a displacement vector optical flow field, so that the moving target is effectively tracked
S103, based on the action characteristics, when the face can be detected, the associated personnel information base is called to compare the face, and the identity of the violation personnel is identified. When the tracked target, namely the violation personnel, rotates to expose the human face in the video image, the identity information of the personnel is immediately determined according to the human face recognition function, and the personnel information base is associated to automatically call the identity file of the personnel.
In a preferred embodiment, the method further comprises: recording the identity of the violation personnel and the violation event information as a violation log, and pushing the violation log to a management terminal. The violation event information includes the nature of the violation, the time of the violation, and the location of the violation.
The above method, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Example 2
The present embodiments provide an electronic device comprising one or more processors, memory, and one or more programs stored in the memory, the one or more programs including instructions for performing the intelligent signature analysis-based job violation identification method of embodiment 1.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions available to those skilled in the art through logic analysis, reasoning and limited experiments based on the prior art according to the concept of the present invention should be within the scope of protection defined by the claims.
Claims (10)
1. A job violation intelligent identification method based on feature analysis is characterized by comprising the following steps:
reading a real-time image sequence from a video to be identified, and preprocessing each frame image of the image sequence;
extracting a violation target from each frame of image, and carrying out tracking and behavior understanding analysis based on a real-time image sequence to obtain the action characteristics of the violation target;
based on the action characteristics, when the face can be detected, the associated personnel information base is called to compare the face, and the identity of the violation personnel is identified.
2. The intelligent job violation identification method based on signature analysis as recited in claim 1 wherein said preprocessing comprises filtering and gray scale conversion.
3. The intelligent job violation identification method based on feature analysis as claimed in claim 1, wherein the extracting of violation targets from each frame image specifically comprises:
and separating a suspected violation area and a background image according to the position and the angle of the person in the image, comparing the suspected violation area with the fixed violation model, judging whether the violation person exists in the image, and if so, acquiring the violation target based on the body area and the outline of the violation person.
4. The intelligent job violation identification method based on signature analysis of claim 3 wherein the fixed violation model comprises multiple violation models with different angles and different light.
5. The intelligent job violation identification method based on signature analysis of claim 3 wherein the area of suspected violation is further determined using the difference between the current extracted image and the background image.
6. The intelligent job violation identification method based on feature analysis as recited in claim 1, wherein the tracking and behavior understanding analysis is implemented based on a time differential comparison and a motion detection algorithm based on an optical flow method.
7. The intelligent job violation identification method based on feature analysis as claimed in claim 6, wherein the time difference comparison specifically comprises:
and (3) converting the real-time image sequence data, and comparing data differences between two adjacent frames of images, wherein the data differences comprise differences of pixels, coordinates and/or deformation.
8. The intelligent job violation identification method based on feature analysis of claim 1 further comprising:
recording the identity of the violation personnel and the violation event information as a violation log, and pushing the violation log to a management terminal.
9. The intelligent signature analysis-based job violation identification method of claim 8 wherein said violation event information includes violation nature, time of violation and location of violation.
10. An electronic device, comprising:
one or more processors;
a memory; and
one or more programs stored in the memory, the one or more programs including instructions for performing the intelligent signature analysis-based job violation identification method of any of claims 1-9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110959232.XA CN113657297A (en) | 2021-08-20 | 2021-08-20 | Intelligent operation violation identification method and device based on characteristic analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110959232.XA CN113657297A (en) | 2021-08-20 | 2021-08-20 | Intelligent operation violation identification method and device based on characteristic analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113657297A true CN113657297A (en) | 2021-11-16 |
Family
ID=78481480
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110959232.XA Pending CN113657297A (en) | 2021-08-20 | 2021-08-20 | Intelligent operation violation identification method and device based on characteristic analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113657297A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101587543A (en) * | 2009-06-19 | 2009-11-25 | 电子科技大学 | Face recognition method |
| CN109961014A (en) * | 2019-02-25 | 2019-07-02 | 中国科学院重庆绿色智能技术研究院 | A kind of coal mine conveying belt danger zone monitoring method and system |
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| CN111582117A (en) * | 2020-04-29 | 2020-08-25 | 长江大学 | Unmanned aerial vehicle illegal building inspection method, equipment and storage medium |
| CN112261384A (en) * | 2020-11-11 | 2021-01-22 | 华能(福建漳州)能源有限责任公司 | Artificial intelligence violation behavior recognition system |
| CN112800975A (en) * | 2021-01-29 | 2021-05-14 | 中国船舶重工集团公司第七一三研究所 | Behavior identification method in security check channel based on image processing |
| CN113239759A (en) * | 2021-04-29 | 2021-08-10 | 国网江苏省电力有限公司苏州供电分公司 | Power grid operation field violation identification method |
-
2021
- 2021-08-20 CN CN202110959232.XA patent/CN113657297A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101587543A (en) * | 2009-06-19 | 2009-11-25 | 电子科技大学 | Face recognition method |
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| CN109961014A (en) * | 2019-02-25 | 2019-07-02 | 中国科学院重庆绿色智能技术研究院 | A kind of coal mine conveying belt danger zone monitoring method and system |
| CN111582117A (en) * | 2020-04-29 | 2020-08-25 | 长江大学 | Unmanned aerial vehicle illegal building inspection method, equipment and storage medium |
| CN112261384A (en) * | 2020-11-11 | 2021-01-22 | 华能(福建漳州)能源有限责任公司 | Artificial intelligence violation behavior recognition system |
| CN112800975A (en) * | 2021-01-29 | 2021-05-14 | 中国船舶重工集团公司第七一三研究所 | Behavior identification method in security check channel based on image processing |
| CN113239759A (en) * | 2021-04-29 | 2021-08-10 | 国网江苏省电力有限公司苏州供电分公司 | Power grid operation field violation identification method |
Non-Patent Citations (1)
| Title |
|---|
| 谢剑斌等: "《视觉感知与智能视频监控》", 国防科技大学出版社, pages: 163 - 164 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110826538B (en) | Abnormal off-duty identification system for electric power business hall | |
| CN110689054B (en) | Worker violation monitoring method | |
| CN110458101B (en) | Criminal personnel sign monitoring method and equipment based on combination of video and equipment | |
| CN106056079B (en) | A kind of occlusion detection method of image capture device and human face five-sense-organ | |
| CN105678213B (en) | Dual-mode mask person event automatic detection method based on video feature statistics | |
| CN110728252B (en) | Face detection method applied to regional personnel motion trail monitoring | |
| CN113297926B (en) | Behavior detection and recognition method and system | |
| CN113343779B (en) | Environment abnormality detection method, device, computer equipment and storage medium | |
| CN105957300B (en) | A kind of wisdom gold eyeball identification is suspicious to put up masking alarm method and device | |
| CN114898261A (en) | Sleep quality assessment method and system based on fusion of video and physiological data | |
| CN112800975A (en) | Behavior identification method in security check channel based on image processing | |
| CN114155472A (en) | Method, device and equipment for detecting abnormal state of factory scene empty face protection equipment | |
| CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
| CN111753658A (en) | Post sleep warning method and device and computer equipment | |
| CN117475353A (en) | Video-based abnormal smoke identification method and system | |
| Daogang et al. | Anomaly identification of critical power plant facilities based on YOLOX-CBAM | |
| CN210666820U (en) | Pedestrian abnormal behavior detection system based on DSP edge calculation | |
| CN113657297A (en) | Intelligent operation violation identification method and device based on characteristic analysis | |
| CN115346169B (en) | Method and system for detecting sleep post behaviors | |
| CN107403192B (en) | Multi-classifier-based rapid target detection method and system | |
| CN114758418A (en) | Water quality evaluation method, device, equipment and storage medium | |
| CN114494355A (en) | Trajectory analysis method and device based on artificial intelligence, terminal equipment and medium | |
| CN112347824A (en) | Wearing object identification method, device, equipment and storage medium | |
| CN117315592B (en) | Identification early warning system based on robot end real-time monitoring camera shooting | |
| CN111813030B (en) | Intelligent safety motion controller and control system |
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 |