CN114387542A - Video acquisition unit abnormity identification system based on portable ball arrangement and control - Google Patents
Video acquisition unit abnormity identification system based on portable ball arrangement and control Download PDFInfo
- Publication number
- CN114387542A CN114387542A CN202111618029.2A CN202111618029A CN114387542A CN 114387542 A CN114387542 A CN 114387542A CN 202111618029 A CN202111618029 A CN 202111618029A CN 114387542 A CN114387542 A CN 114387542A
- Authority
- CN
- China
- Prior art keywords
- algorithm
- detection
- frame
- control
- lens
- 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
- 238000001514 detection method Methods 0.000 claims abstract description 83
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 230000000694 effects Effects 0.000 claims abstract description 9
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000013441 quality evaluation Methods 0.000 claims abstract description 8
- 238000012544 monitoring process Methods 0.000 claims description 10
- 230000005856 abnormality Effects 0.000 claims description 8
- 239000004744 fabric Substances 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 230000006399 behavior Effects 0.000 abstract description 7
- 230000009194 climbing Effects 0.000 abstract description 4
- 206010000117 Abnormal behaviour Diseases 0.000 abstract description 3
- 238000000034 method Methods 0.000 description 7
- 230000000007 visual effect Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001174 ascending effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000036544 posture Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
- Helmets And Other Head Coverings (AREA)
Abstract
The invention relates to the technical field of computer vision, in particular to a video acquisition unit abnormity identification system based on a portable control ball, which comprises the following specific operation flows of S1, network connectivity test; s2, identifying lens occlusion; s3, controlling a control ball to track the operator; s4, detecting the safety helmet; s5, matching the safety belt detection frame with the personnel detection frame; s6, recording abnormal results and generating alarms, wherein the system realizes intelligent snapshot of abnormal behaviors in an actual operation scene by controlling the movement and zooming of a camera, the optimized recognition algorithm can improve the recognition effect on the climbing behaviors of operators and the wearing of safety belts, the system uses a lens shielding detection algorithm combining a rapid image binarization shielding detection algorithm and a video quality evaluation algorithm, can improve the robustness of the system on image noise and the movement of large-area target objects, and simultaneously, the algorithm occupies less memory and computing resources, and is easier to complete the deployment of the algorithm on some edge computing devices.
Description
Technical Field
The invention relates to the technical field of computer vision, in particular to a video acquisition unit abnormity identification system based on a portable cloth control ball.
Background
Guangdong power grid company proposes to build a visual field intelligent safety business card in the whole process, and builds a field intelligent safety person, at present, only the Guangdong power grid has 4000 plus 6000 power operating points every day, 4-6 million field operating personnel every day, multiple and wide operating points, and high difficulty in field safety control, and in the face of the severe situation, the field safety control is carried out by only depending on manpower safety supervision, so that the problems of low supervision efficiency, high manpower cost and easy occurrence of supervision dead zones exist, the field situation is difficult to comprehensively and timely master, and the safety risk is difficult to strictly control.
The video acquisition unit abnormality is: the cloth accuse ball of operation on the building site is sheltered from or the act of breaking rules and regulations appears in the video acquisition unit picture, consequently, need to rely on AI image recognition technology urgently, guarantees can in time remind and supervise the operating personnel in the actual operation, avoids cloth accuse ball to be sheltered from or the operating personnel condition of breaking rules and regulations appears.
The most similar prior art to the present invention:
1. target detection
The task of object detection is to find out interested objects in images or videos and detect the positions and sizes of the interested objects simultaneously, and the method is one of the core problems in the field of machine vision, and the object detection process has a plurality of uncertain factors, such as the number of the objects in the images is uncertain, the objects have different appearances, shapes and postures, and in addition, the interference of factors such as illumination, shielding and the like can be caused during the imaging of the objects, so that the detection algorithm has certain difficulty, and the object detection development is mainly focused in two directions after the deep learning era is entered: the two main differences are that the two algorithms need to generate a proposal (a preselected frame possibly containing an object to be detected) first, and then perform fine-grained object detection, while the one-stage algorithm can directly extract features in a network to predict object classification and position, but these algorithms cannot solve the problem that a target object is very small and cannot be detected due to the fact that a camera is far away from the object.
The prior art has the following disadvantages:
when a target object is far away from a camera, the size of the object in a picture is very small by the existing safety helmet detection algorithm, so that the safety helmet in the picture cannot be detected by the target detection algorithm, and the whole system fails to operate.
2. Camera lens occlusion recognition
At present, security monitoring systems of various scales and sizes in various industries in China are very common, security monitoring equipment is also installed in most communities, office buildings, hotels and public places, intelligent security systems also go deep into the field of power construction, when camera lenses in the security monitoring equipment are manually and maliciously shielded, and if monitoring personnel cannot find the security monitoring systems in time, monitoring failure can be caused.
The existing algorithm lens shielding detection algorithm needs extra time to carry out background modeling, or needs extra memory to establish long and short cache regions, and also has a method using deep learning.
The prior art has the following defects:
the disadvantages of the two methods are mainly: the method is sensitive to noise generated in a video image, and particularly cannot correctly judge whether a camera lens is shielded or not in a scene with a large amount of target activities; and the occupied memory and the consumed resource are larger during algorithm analysis.
Therefore, it is very important to design a novel video acquisition unit abnormality identification system based on portable ball arrangement to overcome the technical defects.
Disclosure of Invention
The invention aims to provide a video acquisition unit abnormity identification system based on a portable cloth control ball, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a video acquisition unit abnormity identification system based on portable ball arrangement and control comprises the following specific operation flows:
s1, testing network connectivity;
s2, identifying lens occlusion;
s3, controlling a control ball to track the operator;
s4, detecting the safety helmet;
s5, matching the safety belt detection frame with the personnel detection frame;
and S6, recording the abnormal result and generating an alarm.
As a preferred embodiment of the present invention, the network connectivity test in S1 specifically includes:
the stable connection of the distributed control balls is an important link of the operation of the whole system, and in order to ensure the stable connection of the distributed control balls when the system is started, the network connectivity test of the distributed control balls needs to be performed firstly, so that the real-time and normal transmission of the distributed control ball pictures is ensured, and the guarantee is provided for the operation of the subsequent algorithm.
As a preferable scheme of the present invention, the identifying of the lens occlusion in S2 specifically includes:
after the system starts to operate, lens shielding identification is needed to be carried out on each frame of a ball distribution control video picture, the system achieves the purpose of lens shielding identification by combining a binarization lens shielding detection algorithm and a video picture quality evaluation algorithm, and compared with the existing lens shielding identification algorithm, the algorithm adopted by the system has great performance improvement on the conditions of picture noise and large-area target movement.
As a preferable aspect of the present invention, the controlling of the ball placement and tracking worker in S3 specifically includes:
the system can control the shooting angle and the focal length of the camera through an ONVIF protocol, the specific identification object can be enlarged and focused, the problem that the detection performance of a target detection algorithm on a small object is reduced is solved, meanwhile, the distance between a control ball arrangement frame and a preset detection frame of a control ball arrangement frame can be calculated, when a person to be identified moves, the system can send a control instruction to finely adjust the control ball arrangement frame, the fact that an operator to be identified is always located in the center of a video picture lens is guaranteed, and a correct image is provided for subsequent detection.
As a preferable scheme of the present invention, the detecting of the safety helmet in S4 specifically includes:
through the filtering effect of the S2 lens shielding identification algorithm, the condition that shielding or lens pollution does not exist in the cloth control ball is guaranteed, S3 moves through the camera to zoom, high-definition close shot images of personnel are provided for the detection link, the safety cap detection is carried out on tracked operating personnel through the YOLO safety cap detection algorithm, and the detection real-time performance is guaranteed through the YOLO algorithm.
As a preferable scheme of the present invention, the matching of the seat belt detection box and the person detection box in S5 specifically includes:
and the safety helmet frame obtained through the S5 detection needs to be matched with the detection frame of the operator to judge whether the operator wears the safety helmet or not, and the step comprehensively judges whether the pedestrian wears the safety helmet or not by calculating the size of the IOU of the pedestrian regression frame and the IOU of the safety helmet regression frame and the distance between the center coordinate of the safety helmet regression frame and the coordinate of the quarter position on the pedestrian regression frame.
As a preferable scheme of the present invention, the recording of the abnormal result and the generating of the alarm in S6 specifically includes:
if the worker judged by the S5 does not have the safety helmet, the worker belongs to a dangerous worker, the system intercepts and stores the ball-arrangement video image, generates a warning, prompts the worker with violation in the video monitoring picture, and arranges corresponding countermeasures in time.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the intelligent capturing system, the camera is controlled to move and zoom, the intelligent capturing of the abnormal behaviors of the actual operation scene is realized, and the recognition effect of the climbing behaviors of the operators and the wearing effect of the safety belt can be improved by the optimized recognition algorithm.
2. According to the invention, the system uses a lens occlusion detection algorithm combining a rapid image binarization occlusion detection algorithm and a video quality evaluation algorithm, so that the robustness of the system to image noise and large-area target object movement can be improved, and meanwhile, the algorithm occupies less memory and computing resources, and is easier to complete the deployment of the algorithm on some edge computing devices.
3. In the invention, the system uses the safety helmet data collected in the actual scene to train the YOLO safety helmet detection algorithm, and the algorithm model can adapt to the safety helmet detection task in the real operation scene. Meanwhile, the YOLO algorithm adopted by the system is good in real-time performance and occupies less computing resources.
Drawings
FIG. 1 is a schematic diagram of a system route frame structure according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments, and all other embodiments obtained by a person of ordinary skill in the art without any creative work based on the embodiments of the present invention belong to the protection scope of the present invention.
While several embodiments of the present invention will be described below in order to facilitate an understanding of the invention, with reference to the related description, the invention may be embodied in many different forms and is not limited to the embodiments described herein, but rather, these embodiments are provided so that this disclosure will be thorough and complete.
It will be understood that when an element is referred to as being "secured to" another element, it can be directly on the other element or intervening elements may also be present, that when an element is referred to as being "connected" to another element, it can be directly connected to the other element or intervening elements may also be present, and that the terms "vertical", "horizontal", "left", "right" and the like are used herein for descriptive purposes only.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, and the terms used herein in the specification of the present invention are for the purpose of describing particular embodiments only and are not intended to limit the present invention, and the term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Referring to fig. 1, the present invention provides a technical solution:
a video acquisition unit abnormity identification system based on portable ball arrangement and control comprises the following specific operation flows:
s1, testing network connectivity;
s2, identifying lens occlusion;
s3, controlling a control ball to track the operator;
s4, detecting the safety helmet;
s5, matching the safety belt detection frame with the personnel detection frame;
and S6, recording the abnormal result and generating an alarm.
Further, the network connectivity test in S1 specifically includes:
the stable connection of the distributed control balls is an important link of the operation of the whole system, and in order to ensure the stable connection of the distributed control balls when the system is started, the network connectivity test of the distributed control balls needs to be performed firstly, so that the real-time and normal transmission of the distributed control ball pictures is ensured, and the guarantee is provided for the operation of the subsequent algorithm.
Further, the identification of the lens occlusion in S2 specifically includes:
after the system starts to operate, lens shielding identification is needed to be carried out on each frame of a ball distribution control video picture, the system achieves the purpose of lens shielding identification by combining a binarization lens shielding detection algorithm and a video picture quality evaluation algorithm, and compared with the existing lens shielding identification algorithm, the algorithm adopted by the system has great performance improvement on the conditions of picture noise and large-area target movement.
Further, the step S3 of controlling the ball placement and tracking operator specifically includes:
the system can control the shooting angle and the focal length of the camera through an ONVIF protocol, the specific identification object can be enlarged and focused, the problem that the detection performance of a target detection algorithm on a small object is reduced is solved, meanwhile, the distance between a control ball arrangement frame and a preset detection frame of a control ball arrangement frame can be calculated, when a person to be identified moves, the system can send a control instruction to finely adjust the control ball arrangement frame, the fact that an operator to be identified is always located in the center of a video picture lens is guaranteed, and a correct image is provided for subsequent detection.
Further, the safety helmet detection in S4 specifically includes:
through the filtering effect of the S2 lens shielding identification algorithm, the condition that shielding or lens pollution does not exist in the cloth control ball is guaranteed, S3 moves through the camera to zoom, high-definition close shot images of personnel are provided for the detection link, the safety cap detection is carried out on tracked operating personnel through the YOLO safety cap detection algorithm, and the detection real-time performance is guaranteed through the YOLO algorithm.
Further, the seat belt detection frame and the personnel detection frame in the S5 are matched to specifically include:
and the safety helmet frame obtained through the S5 detection needs to be matched with the detection frame of the operator to judge whether the operator wears the safety helmet or not, and the step comprehensively judges whether the pedestrian wears the safety helmet or not by calculating the size of the IOU of the pedestrian regression frame and the IOU of the safety helmet regression frame and the distance between the center coordinate of the safety helmet regression frame and the coordinate of the quarter position on the pedestrian regression frame.
Further, the recording of the abnormal result and the generating of the alarm in S6 specifically includes:
if the worker judged by the S5 does not have the safety helmet, the worker belongs to a dangerous worker, the system intercepts and stores the ball-arrangement video image, generates a warning, prompts the worker with violation in the video monitoring picture, and arranges corresponding countermeasures in time.
The specific implementation case is as follows:
please refer to fig. 1:
the method comprises the following steps: testing network connectivity;
the stable connection of the distributed control balls is an important link of the operation of the whole system, and in order to ensure the stable connection of the distributed control balls when the system is started, the network connectivity test of the distributed control balls needs to be carried out firstly, so that the real-time and normal transmission of the distributed control ball pictures is ensured, and the guarantee is provided for the operation of a subsequent algorithm;
step two: identifying lens shielding;
after the system starts to operate, lens shielding identification is needed to be carried out on each frame of a ball distribution control video picture, the system combines a binarization lens shielding detection algorithm and a video picture quality evaluation algorithm to achieve the purpose of lens shielding identification, and compared with the existing lens shielding identification algorithm, the algorithm adopted by the system has great performance improvement on the conditions of picture noise and large-area target movement;
step three: controlling a distribution control ball to track an operator;
the system can control the shooting angle and the focal length of a camera through an ONVIF protocol, magnifies and focuses to a specific identification object, solves the problem that the detection performance of a target detection algorithm on a small object is reduced, simultaneously calculates the distance between a control ball and a preset detection frame of a control ball picture according to the detection frame of the target object, sends a control instruction to finely adjust the control ball when a person to be identified moves, ensures that an operator to be identified is always positioned in the center of a video picture lens, and provides a correct image for subsequent detection;
step four: detecting a safety helmet;
through the filtering effect of the lens shielding identification algorithm in the step two, the condition that the cloth control ball is not shielded or the lens is polluted is ensured, the movement zooming of the camera is carried out in the step three, a high-definition close shot image of the personnel is provided for the detection link, the safety helmet detection is carried out on the tracked operating personnel through the safety helmet detection algorithm based on the YOLO algorithm in the link, and the real-time performance of the detection is ensured through the YOLO algorithm;
step five: the safety belt detection frame is matched with the personnel detection frame;
whether the safety helmet is worn by the pedestrian is comprehensively judged by calculating the size of IOUs of the pedestrian regression frame and the safety helmet regression frame and the distance between the central coordinate of the safety helmet regression frame and the coordinate of the quarter position on the pedestrian regression frame;
step six: recording abnormal results and generating an alarm;
if the worker judged by the S5 does not have the safety helmet, the worker belongs to a dangerous worker, the system intercepts and stores the ball-arrangement video image, generates a warning, prompts the worker with violation in the video monitoring picture, and arranges corresponding countermeasures in time.
The key technical points of the invention are as follows:
1. intelligent snapshot technology for operation scene based on zoom switching
In order to solve the problem of low accuracy of target detection and behavior recognition algorithm under a long distance, the system realizes intelligent snapshot of an actual operation scene by controlling the movement and zooming control of the camera, and can improve the recognition effect of the ascending behavior and the escalator behavior of an operator.
Detailed technical description: according to the actual situation of an operation field, the ONVIF camera control protocol can be used for controlling the camera to adjust the focal length, different visual angles (a macroscopic visual angle and a microscopic visual angle) are switched to identify the climbing operation behavior and the escalator behavior, and under the macroscopic visual angle, the spatial position between a person and an escalator is judged to identify whether the person is performing the climbing operation; under the microcosmic visual angle, whether there is the staircase personnel is discerned through analysis personnel gesture. And the abnormal behavior of the operator in the picture is captured.
2. Lens occlusion detection algorithm combining binarization occlusion detection algorithm and video quality evaluation algorithm
In order to solve the problems that the existing lens shielding detection algorithm is sensitive to image noise and mistaken shielding judgment of large-area moving objects is carried out, a video quality evaluation module is added on the basis of the traditional shielding detection in the lens detection algorithm adopted by the system, the two conditions are effectively solved, a background modeling-based rapid image binarization segmentation algorithm is adopted in the selection of the shielding detection algorithm, and compared with a cache region-based camera lens shielding algorithm, the system has the advantages that the occupied memory and the consumed resources are smaller.
Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions and alterations can be made in these embodiments without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (7)
1. The video acquisition unit abnormity identification system based on the portable ball arrangement and control is characterized by comprising the following specific operation flows:
s1, testing network connectivity;
s2, identifying lens occlusion;
s3, controlling a control ball to track the operator;
s4, detecting the safety helmet;
s5, matching the safety belt detection frame with the personnel detection frame;
and S6, recording the abnormal result and generating an alarm.
2. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: the network connectivity test in S1 specifically includes:
the stable connection of the distributed control balls is an important link of the operation of the whole system, and in order to ensure the stable connection of the distributed control balls when the system is started, the network connectivity test of the distributed control balls needs to be performed firstly, so that the real-time and normal transmission of the distributed control ball pictures is ensured, and the guarantee is provided for the operation of the subsequent algorithm.
3. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: the identification of the lens occlusion in the S2 specifically includes:
after the system starts to operate, lens shielding identification is needed to be carried out on each frame of a ball distribution control video picture, the system achieves the purpose of lens shielding identification by combining a binarization lens shielding detection algorithm and a video picture quality evaluation algorithm, and compared with the existing lens shielding identification algorithm, the algorithm adopted by the system has great performance improvement on the conditions of picture noise and large-area target movement.
4. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: the step S3 of controlling a ball placement and tracking operator specifically includes:
the system can control the shooting angle and the focal length of the camera through an ONVIF protocol, the specific identification object can be enlarged and focused, the problem that the detection performance of a target detection algorithm on a small object is reduced is solved, meanwhile, the distance between a control ball arrangement frame and a preset detection frame of a control ball arrangement frame can be calculated, when a person to be identified moves, the system can send a control instruction to finely adjust the control ball arrangement frame, the fact that an operator to be identified is always located in the center of a video picture lens is guaranteed, and a correct image is provided for subsequent detection.
5. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: the safety helmet detection in the S4 specifically includes:
through the filtering effect of the S2 lens shielding identification algorithm, the condition that shielding or lens pollution does not exist in the cloth control ball is guaranteed, S3 moves through the camera to zoom, high-definition close shot images of personnel are provided for the detection link, the safety cap detection is carried out on tracked operating personnel through the YOLO safety cap detection algorithm, and the detection real-time performance is guaranteed through the YOLO algorithm.
6. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: the seat belt detection frame and the personnel detection frame in the S5 are matched and specifically comprise:
and the safety helmet frame obtained through the S5 detection needs to be matched with the detection frame of the operator to judge whether the operator wears the safety helmet or not, and the step comprehensively judges whether the pedestrian wears the safety helmet or not by calculating the size of the IOU of the pedestrian regression frame and the IOU of the safety helmet regression frame and the distance between the center coordinate of the safety helmet regression frame and the coordinate of the quarter position on the pedestrian regression frame.
7. The system for recognizing the abnormality of the video acquisition unit based on the portable ball game controller according to the claim 1, is characterized in that: recording the abnormal result and generating the alarm in the S6 specifically include:
if the worker judged by the S5 does not have the safety helmet, the worker belongs to a dangerous worker, the system intercepts and stores the ball-arrangement video image, generates a warning, prompts the worker with violation in the video monitoring picture, and arranges corresponding countermeasures in time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111618029.2A CN114387542A (en) | 2021-12-27 | 2021-12-27 | Video acquisition unit abnormity identification system based on portable ball arrangement and control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111618029.2A CN114387542A (en) | 2021-12-27 | 2021-12-27 | Video acquisition unit abnormity identification system based on portable ball arrangement and control |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114387542A true CN114387542A (en) | 2022-04-22 |
Family
ID=81198748
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111618029.2A Pending CN114387542A (en) | 2021-12-27 | 2021-12-27 | Video acquisition unit abnormity identification system based on portable ball arrangement and control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114387542A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035458A (en) * | 2022-07-06 | 2022-09-09 | 中国安全生产科学研究院 | Safety risk evaluation method and system |
| CN118226769A (en) * | 2024-05-22 | 2024-06-21 | 天津合佳威立雅环境服务有限公司 | Impurity purging control method and system for monitoring equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201681466U (en) * | 2010-05-07 | 2010-12-22 | 深圳市飞瑞斯科技有限公司 | Monitoring unit with framing barrier alarm unit |
| CN111914636A (en) * | 2019-11-25 | 2020-11-10 | 南京桂瑞得信息科技有限公司 | Method and device for detecting whether pedestrian wears safety helmet |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
| CN112906533A (en) * | 2021-02-07 | 2021-06-04 | 成都睿码科技有限责任公司 | Safety helmet wearing detection method based on self-adaptive detection area |
| CN112906488A (en) * | 2021-01-26 | 2021-06-04 | 广东电网有限责任公司 | Security protection video quality evaluation system based on artificial intelligence |
| CN113411573A (en) * | 2021-07-30 | 2021-09-17 | 广东电网有限责任公司东莞供电局 | Power grid monitoring system detection method and device, computer equipment and medium |
| CN113593177A (en) * | 2021-07-27 | 2021-11-02 | 南京南瑞信息通信科技有限公司 | Video alarm linkage implementation method based on high-precision positioning and image recognition |
-
2021
- 2021-12-27 CN CN202111618029.2A patent/CN114387542A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201681466U (en) * | 2010-05-07 | 2010-12-22 | 深圳市飞瑞斯科技有限公司 | Monitoring unit with framing barrier alarm unit |
| CN111914636A (en) * | 2019-11-25 | 2020-11-10 | 南京桂瑞得信息科技有限公司 | Method and device for detecting whether pedestrian wears safety helmet |
| CN112770090A (en) * | 2020-12-28 | 2021-05-07 | 杭州电子科技大学 | Monitoring method based on transaction detection and target tracking |
| CN112906488A (en) * | 2021-01-26 | 2021-06-04 | 广东电网有限责任公司 | Security protection video quality evaluation system based on artificial intelligence |
| CN112906533A (en) * | 2021-02-07 | 2021-06-04 | 成都睿码科技有限责任公司 | Safety helmet wearing detection method based on self-adaptive detection area |
| CN113593177A (en) * | 2021-07-27 | 2021-11-02 | 南京南瑞信息通信科技有限公司 | Video alarm linkage implementation method based on high-precision positioning and image recognition |
| CN113411573A (en) * | 2021-07-30 | 2021-09-17 | 广东电网有限责任公司东莞供电局 | Power grid monitoring system detection method and device, computer equipment and medium |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115035458A (en) * | 2022-07-06 | 2022-09-09 | 中国安全生产科学研究院 | Safety risk evaluation method and system |
| CN115035458B (en) * | 2022-07-06 | 2023-02-03 | 中国安全生产科学研究院 | Safety risk evaluation method and system |
| CN118226769A (en) * | 2024-05-22 | 2024-06-21 | 天津合佳威立雅环境服务有限公司 | Impurity purging control method and system for monitoring equipment |
| CN118226769B (en) * | 2024-05-22 | 2024-07-19 | 天津合佳威立雅环境服务有限公司 | Impurity purging control method and system for monitoring equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111507308B (en) | Transformer substation safety monitoring system and method based on video identification technology | |
| KR101808587B1 (en) | Intelligent integration visual surveillance control system by object detection and tracking and detecting abnormal behaviors | |
| CN108062542B (en) | Method for detecting shielded human face | |
| CN101751744B (en) | Detection and early warning method of smoke | |
| CN114387542A (en) | Video acquisition unit abnormity identification system based on portable ball arrangement and control | |
| CN109996182B (en) | Positioning method, device and system based on combination of UWB positioning and monitoring | |
| CN111241959A (en) | Method for detecting person without wearing safety helmet through construction site video stream | |
| CN103456024B (en) | A kind of moving target gets over line determination methods | |
| CN112112629A (en) | Safety business management system and method in drilling operation process | |
| KR101541272B1 (en) | Apparatus and method for detecting terrorism using irregular motion of peoples | |
| KR101036947B1 (en) | The automatic guard system to prevent the crime and accident using computer video image analysis technology | |
| CN111932709A (en) | Method for realizing violation safety supervision of inspection operation of gas station based on AI identification | |
| CN112532927A (en) | Intelligent safety management and control system for construction site | |
| CN210222962U (en) | Intelligent electronic fence system | |
| KR102434154B1 (en) | Method for tracking multi target in traffic image-monitoring-system | |
| CN112613361A (en) | Intelligent behavior analysis system for security monitoring | |
| CN113989711B (en) | Power distribution construction safety tool use identification method and system | |
| CN113012374A (en) | Intelligent park security system and control method thereof | |
| CN113111771A (en) | Method for identifying unsafe behaviors of power plant workers | |
| CN112287823A (en) | Facial mask identification method based on video monitoring | |
| KR20200059643A (en) | ATM security system based on image analyses and the method thereof | |
| CN110390784A (en) | A kind of transmission line of electricity external force damage prevention monitoring system based on deep learning | |
| CN114495011A (en) | Non-motor vehicle and pedestrian illegal intrusion identification method based on target detection, storage medium and computer equipment | |
| CN114387665A (en) | Unmanned staircase identification system ascends a height based on portable cloth accuse ball | |
| Chern et al. | Context-aware safety assessment system for far-field monitoring |
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 |