CN113518205A - Video patrol processing method based on AI analysis - Google Patents
Video patrol processing method based on AI analysis Download PDFInfo
- Publication number
- CN113518205A CN113518205A CN202110655168.6A CN202110655168A CN113518205A CN 113518205 A CN113518205 A CN 113518205A CN 202110655168 A CN202110655168 A CN 202110655168A CN 113518205 A CN113518205 A CN 113518205A
- Authority
- CN
- China
- Prior art keywords
- video
- data
- analysis
- processing method
- image
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 36
- 238000003672 processing method Methods 0.000 title claims abstract description 23
- 238000012545 processing Methods 0.000 claims abstract description 46
- 230000002159 abnormal effect Effects 0.000 claims abstract description 44
- 238000012544 monitoring process Methods 0.000 claims abstract description 37
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 238000012549 training Methods 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 238000012806 monitoring device Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000013473 artificial intelligence Methods 0.000 description 32
- 230000009471 action Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Closed-Circuit Television Systems (AREA)
Abstract
The invention relates to the technical field of video processing, in particular to a video patrol processing method based on AI analysis, which comprises the following steps: acquiring a training video data set, preprocessing the training video data set, establishing a video detection abnormal model, acquiring video data through monitoring equipment, and then transmitting the video data to a video processing platform through a network bus by the monitoring equipment; the video patrol processing method based on AI analysis has the advantages of being convenient for analyzing and identifying video image data, being capable of timely clearing out overdue data, being beneficial to detecting abnormal data in images and videos, being capable of effectively improving video patrol processing efficiency, solving the problem that dangers are not processed and early-warned timely when the current video monitoring is abnormal, and further causing safety accidents, and being capable of timely notifying security protection workers to eliminate potential safety hazards when the abnormal occurs.
Description
Technical Field
The invention relates to the technical field of video processing, in particular to a video patrol processing method based on AI analysis.
Background
With the maturity of video monitoring system construction and the deepening of informatization construction, a great amount of data resources shot by the video monitoring system are stored in video libraries of security industry companies and government organs, and how to correlate the great amount of data resources is a difficult problem for facilitating classification management, retrieval and search and data comparison. Due to the development of the big data industry, the data volume presents an explosive growth situation, and the traditional computing architecture cannot support the large-scale parallel computing requirement of deep learning, so that a new round of technical research, development and application research is carried out on an AI (artificial intelligence) chip by the research community.
The AI chip is one of the technical cores of the artificial intelligence era and determines the basic architecture and the development ecology of the platform. According to the technical architecture classification, the mainstream AI chips at present include a GPU, a full-custom chip, a semi-custom chip, and the like. Besides general-purpose computing chips such as GPUs, the types of AI chips are various according to performance and supported algorithm applications, and actual performance of different AI chips under different application algorithms and scenes is also greatly different. In the current AI algorithm application, the best commercialized and most practically applied algorithms are video-related AI applications, including image detection, image recognition, image processing, and the like.
At present, video monitoring needs personnel to invest a large amount of time to watch videos, the situation that video monitoring personnel cannot pay attention to a large number of personnel in time due to the fact that the personnel are numerous in the public environment cannot be processed in the first time when abnormity occurs, and the situation that dangers are not processed and early-warned timely due to the fact that the video monitoring personnel watch invalid videos consumes a large amount of time, so that safety accidents are caused.
Disclosure of Invention
The invention aims to provide a video patrol processing method based on AI analysis, 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 patrol processing method based on AI analysis comprises the following steps:
s1: acquiring a training video data set, preprocessing the training video data set, and establishing a video detection abnormity model;
s2: the method comprises the steps that video data are collected through monitoring equipment, then the monitoring equipment transmits the video data to a video processing platform through a network bus, and the video data are stored in a video library;
s3: the video processing platform sends a screenshot intercepting instruction, intercepts a video picture, sends the intercepted target picture and a target video file to a data processing system, processes data of the video image data based on an image recognition model, and determines a target object and coordinate position information of the target object;
s4: determining the position of the image frame in the video image corresponding to the video image data according to the image frame determined by the coordinate position information of the target object, extracting coordinate pixel point data of the corresponding image frame in the video image data, and labeling the coordinate pixel point data;
s5: the comprehensive AI video recognition module and the AI image recognition module perform comprehensive analysis on the coordinate pixel point data to obtain a recognition result and store the recognition result in the data processing system, and then the display module extracts and displays the analysis result;
s6: and detecting the possibility of abnormity of the video data acquired by the monitoring equipment according to the video detection abnormity model, and if the abnormity of the video data acquired by the monitoring equipment is detected, carrying out abnormity processing.
Preferably, in step S1, the training video data set is video data of an abnormal scene, and the video data of the abnormal scene is preprocessed.
Preferably, in step S1, the preprocessed video data is processed by a convolution algorithm to establish a video detection abnormal model.
Preferably, in step S2, the monitoring device is a webcam, and the webcam has an embedded chip, and an embedded real-time operating system is adopted, and the webcam encodes and compresses the acquired analog video signal into a digital signal.
Preferably, in step S2, the video data in the video library is converted into MPEG format for storage.
Preferably, in step S3, the picture capturing frequency and the video file capturing frequency are based on the lowest supported cut-off frequency of the control platform, and the cut-off frequencies are set to different frequencies respectively.
Preferably, in step S3, the image recognition model performs depth learning calculation on the video image data to obtain data corresponding to the target object in the video image data, and determines coordinate position information of the target object according to the data of the target object.
Preferably, in step S5, the AI video recognition module is configured to read video information collected by the monitoring device, and the AI image recognition module is configured to read video image data in the data processing system.
Preferably, in step S5, the data processing system is configured to sort the data after the AI identification and clear the expired data.
Preferably, in step S6, if the video data satisfies the video detection abnormal model, the video data is an abnormal video, and if the video data does not satisfy the video detection abnormal model, the video data is a normal video.
Compared with the prior art, the invention has the following beneficial effects:
the video patrol processing method based on AI analysis has the advantages of being convenient for analyzing and identifying video image data, being capable of timely clearing out overdue data, being beneficial to detecting abnormal data in images and videos, being capable of effectively improving video patrol processing efficiency, solving the problem that dangers are not processed and early-warned timely when the current video monitoring is abnormal, and further causing safety accidents, and being capable of timely notifying security protection workers to eliminate potential safety hazards when the abnormal occurs.
Drawings
Fig. 1 is a flow chart of a video patrol processing method 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 drawings in 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, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The first embodiment is as follows:
a video patrol processing method based on AI analysis comprises the following steps:
s1: the method comprises the steps of obtaining a training video data set, preprocessing the training video data set, establishing a video detection abnormal model, wherein the training video data set is video data of an abnormal scene, preprocessing the video data of the abnormal scene, processing the preprocessed video data through a convolution algorithm, establishing the video detection abnormal model, and establishing a more accurate video detection model according to the video data of the abnormal scene, so that analysis of a monitoring video is facilitated;
s2: the method comprises the steps that video data are collected through monitoring equipment, then the monitoring equipment transmits the video data to a video processing platform through a network bus, the video data are stored in a video library, the monitoring equipment is a network camera, an embedded chip is arranged in the network camera, an embedded real-time operating system is adopted, the network camera encodes and compresses collected analog video signals into digital signals, the video data in the video library are converted into an MPEG format for storage, the network camera can be directly accessed into a network switch and routing equipment, transmission of the video data is facilitated, the video data can be compressed, and therefore redundant information in video images is reduced;
s3: the video processing platform sends a screenshot intercepting instruction, intercepts a video picture, sends the intercepted target picture and a target video file to a data processing system, processes data of the video image data based on an image recognition model, and determines a target object and coordinate position information of the target object;
s4: determining the position of the image frame in the video image corresponding to the video image data according to the image frame determined by the coordinate position information of the target object, extracting coordinate pixel point data of the corresponding image frame in the video image data, and labeling the coordinate pixel point data;
s5: the comprehensive AI video recognition module and the AI image recognition module perform comprehensive analysis on the coordinate pixel point data to obtain a recognition result and store the recognition result in the data processing system, and then the display module extracts and displays the analysis result;
s6: and detecting the possibility of abnormity of the video data acquired by the monitoring equipment according to the video detection abnormity model, and if the abnormity of the video data acquired by the monitoring equipment is detected, carrying out abnormity processing.
Example two:
a video patrol processing method based on AI analysis comprises the following steps:
s1: the method comprises the steps of obtaining a training video data set, preprocessing the training video data set, establishing a video detection abnormal model, wherein the training video data set is video data of an abnormal scene, preprocessing the video data of the abnormal scene, processing the preprocessed video data through a convolution algorithm, establishing the video detection abnormal model, and establishing a more accurate video detection model according to the video data of the abnormal scene, so that analysis of a monitoring video is facilitated;
s2: the method comprises the steps that video data are collected through monitoring equipment, then the monitoring equipment transmits the video data to a video processing platform through a network bus, the video data are stored in a video library, the monitoring equipment is a network camera, an embedded chip is arranged in the network camera, an embedded real-time operating system is adopted, the network camera encodes and compresses collected analog video signals into digital signals, the video data in the video library are converted into an MPEG format for storage, the network camera can be directly accessed into a network switch and routing equipment, transmission of the video data is facilitated, the video data can be compressed, and therefore redundant information in video images is reduced;
s3: the video processing platform sends a screenshot intercepting instruction to intercept a video picture, sends the intercepted target picture and a target video file to a data processing system, performs data processing on video image data based on an image recognition model to determine a target object and coordinate position information of the target object, the intercepting frequency of the picture and the intercepting frequency of the video file are respectively set with different frequencies according to the lowest supported intercepting frequency of the control platform, performing deep learning calculation on the video image data through an image recognition model to obtain data of a corresponding target object in the video image data, determining coordinate position information of the target object according to the data of the target object, the target image and the video can be accurately positioned and analyzed, so that abnormal data in the image and the video can be detected, and the aim of improving the video inspection processing efficiency is fulfilled;
s4: determining the position of the image frame in the video image corresponding to the video image data according to the image frame determined by the coordinate position information of the target object, extracting coordinate pixel point data of the corresponding image frame in the video image data, and labeling the coordinate pixel point data;
s5: the comprehensive AI video recognition module and the AI image recognition module perform comprehensive analysis on the coordinate pixel point data to obtain a recognition result and store the recognition result in the data processing system, and then the display module extracts and displays the analysis result;
s6: and detecting the possibility of abnormity of the video data acquired by the monitoring equipment according to the video detection abnormity model, and if the abnormity of the video data acquired by the monitoring equipment is detected, carrying out abnormity processing.
Example three:
a video patrol processing method based on AI analysis comprises the following steps:
s1: the method comprises the steps of obtaining a training video data set, preprocessing the training video data set, establishing a video detection abnormal model, wherein the training video data set is video data of an abnormal scene, preprocessing the video data of the abnormal scene, processing the preprocessed video data through a convolution algorithm, establishing the video detection abnormal model, and establishing a more accurate video detection model according to the video data of the abnormal scene, so that analysis of a monitoring video is facilitated;
s2: the method comprises the steps that video data are collected through monitoring equipment, then the monitoring equipment transmits the video data to a video processing platform through a network bus, the video data are stored in a video library, the monitoring equipment is a network camera, an embedded chip is arranged in the network camera, an embedded real-time operating system is adopted, the network camera encodes and compresses collected analog video signals into digital signals, the video data in the video library are converted into an MPEG format for storage, the network camera can be directly accessed into a network switch and routing equipment, transmission of the video data is facilitated, the video data can be compressed, and therefore redundant information in video images is reduced;
s3: the video processing platform sends a screenshot intercepting instruction to intercept a video picture, sends the intercepted target picture and a target video file to a data processing system, performs data processing on video image data based on an image recognition model to determine a target object and coordinate position information of the target object, the intercepting frequency of the picture and the intercepting frequency of the video file are respectively set with different frequencies according to the lowest supported intercepting frequency of the control platform, performing deep learning calculation on the video image data through an image recognition model to obtain data of a corresponding target object in the video image data, determining coordinate position information of the target object according to the data of the target object, the target image and the video can be accurately positioned and analyzed, so that abnormal data in the image and the video can be detected, and the aim of improving the video inspection processing efficiency is fulfilled;
s4: determining the position of the image frame in the video image corresponding to the video image data according to the image frame determined by the coordinate position information of the target object, extracting coordinate pixel point data of the corresponding image frame in the video image data, and labeling the coordinate pixel point data;
s5: the comprehensive AI video recognition module and the AI image recognition module perform comprehensive analysis on coordinate pixel point data to obtain a recognition result and store the recognition result into the data processing system, then the display module extracts the analysis result and displays the analysis result, the AI video recognition module is used for reading video information collected by the monitoring equipment, the AI image recognition module is used for reading video image data in the data processing system, the data processing system is used for sorting the data after AI recognition and clearing out-of-date data, the video image data can be conveniently analyzed and recognized, the out-of-date data can be cleared in time, and the memory of the data processing system is prevented from being occupied;
s6: according to the video detection abnormal model, the possibility of abnormity of video data collected by the monitoring equipment is detected, if the video data collected by the monitoring equipment is detected to be abnormal, abnormal processing is carried out, if the video data meets the video detection abnormal model, the video data is an abnormal video, if the video data does not meet the video detection abnormal model, the video data is a normal video, security workers can be timely notified when the abnormity occurs, the purpose of timely eliminating hidden dangers is achieved, and therefore accidents are avoided.
The video patrol processing method based on AI analysis has the advantages of being convenient for analyzing and identifying video image data, being capable of timely clearing out overdue data, being beneficial to detecting abnormal data in images and videos, being capable of effectively improving video patrol processing efficiency, solving the problem that dangers are not processed and early-warned timely when the current video monitoring is abnormal, and further causing safety accidents, and being capable of timely notifying security protection workers to eliminate potential safety hazards when the abnormal occurs.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
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 (10)
1. A video patrol processing method based on AI analysis is characterized in that: the method comprises the following steps:
s1: acquiring a training video data set, preprocessing the training video data set, and establishing a video detection abnormity model;
s2: the method comprises the steps that video data are collected through monitoring equipment, then the monitoring equipment transmits the video data to a video processing platform through a network bus, and the video data are stored in a video library;
s3: the video processing platform sends a screenshot intercepting instruction, intercepts a video picture, sends the intercepted target picture and a target video file to a data processing system, processes data of the video image data based on an image recognition model, and determines a target object and coordinate position information of the target object;
s4: determining the position of the image frame in the video image corresponding to the video image data according to the image frame determined by the coordinate position information of the target object, extracting coordinate pixel point data of the corresponding image frame in the video image data, and labeling the coordinate pixel point data;
s5: the comprehensive AI video recognition module and the AI image recognition module perform comprehensive analysis on the coordinate pixel point data to obtain a recognition result and store the recognition result in the data processing system, and then the display module extracts and displays the analysis result;
s6: and detecting the possibility of abnormity of the video data acquired by the monitoring equipment according to the video detection abnormity model, and if the abnormity of the video data acquired by the monitoring equipment is detected, carrying out abnormity processing.
2. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S1, the training video data set is video data of an abnormal scene, and the video data of the abnormal scene is preprocessed.
3. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S1, the preprocessed video data is processed by a convolution algorithm to establish a video detection anomaly model.
4. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S2, the monitoring device is a webcam, and the webcam has an embedded chip built therein, and the webcam encodes and compresses the acquired analog video signal into a digital signal by using an embedded real-time operating system.
5. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S2, the video data in the video library is converted into MPEG format for storage.
6. The AI-analysis-based video patrol processing method according to claim 1, wherein: in the step S3, the picture interception frequency and the video file interception frequency are based on the lowest supported interception frequency of the control platform, and the interception frequencies are set to different frequencies respectively.
7. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S3, the image recognition model performs deep learning calculation on the video image data to obtain data corresponding to the target object in the video image data, and determines coordinate position information of the target object according to the data of the target object.
8. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S5, the AI video identification module is configured to read video information collected by the monitoring device, and the AI image identification module is configured to read video image data in the data processing system.
9. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S5, the data processing system is configured to sort the data after the AI identification and clear the expired data.
10. The AI-analysis-based video patrol processing method according to claim 1, wherein: in step S6, if the video data satisfies the video detection abnormal model, the video data is an abnormal video, and if the video data does not satisfy the video detection abnormal model, the video data is a normal video.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655168.6A CN113518205A (en) | 2021-06-11 | 2021-06-11 | Video patrol processing method based on AI analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110655168.6A CN113518205A (en) | 2021-06-11 | 2021-06-11 | Video patrol processing method based on AI analysis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113518205A true CN113518205A (en) | 2021-10-19 |
Family
ID=78065874
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110655168.6A Pending CN113518205A (en) | 2021-06-11 | 2021-06-11 | Video patrol processing method based on AI analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113518205A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115293508A (en) * | 2022-07-05 | 2022-11-04 | 国网江苏省电力有限公司南通市通州区供电分公司 | Visual optical cable running state monitoring method and system |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108900801A (en) * | 2018-06-29 | 2018-11-27 | 深圳市九洲电器有限公司 | A kind of video monitoring method based on artificial intelligence, system and Cloud Server |
| CN109803108A (en) * | 2019-01-22 | 2019-05-24 | 国网信息通信产业集团有限公司 | A kind of image-recognizing method and device |
| CN111325872A (en) * | 2020-01-21 | 2020-06-23 | 和智信(山东)大数据科技有限公司 | Driver driving abnormity detection equipment and detection method based on computer vision |
| CN111428083A (en) * | 2020-03-19 | 2020-07-17 | 平安国际智慧城市科技股份有限公司 | Video monitoring warning method, device, equipment and storage medium |
-
2021
- 2021-06-11 CN CN202110655168.6A patent/CN113518205A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108900801A (en) * | 2018-06-29 | 2018-11-27 | 深圳市九洲电器有限公司 | A kind of video monitoring method based on artificial intelligence, system and Cloud Server |
| CN109803108A (en) * | 2019-01-22 | 2019-05-24 | 国网信息通信产业集团有限公司 | A kind of image-recognizing method and device |
| CN111325872A (en) * | 2020-01-21 | 2020-06-23 | 和智信(山东)大数据科技有限公司 | Driver driving abnormity detection equipment and detection method based on computer vision |
| CN111428083A (en) * | 2020-03-19 | 2020-07-17 | 平安国际智慧城市科技股份有限公司 | Video monitoring warning method, device, equipment and storage medium |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115293508A (en) * | 2022-07-05 | 2022-11-04 | 国网江苏省电力有限公司南通市通州区供电分公司 | Visual optical cable running state monitoring method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
| CN109858367B (en) | Visual automatic detection method and system for worker through supporting unsafe behaviors | |
| CN107222660B (en) | Distributed network vision monitoring system | |
| CN112070135A (en) | Power equipment image detection method and device, power equipment and storage medium | |
| CN112449147B (en) | Video cluster monitoring system of photovoltaic power station and image processing method thereof | |
| CN112163572A (en) | Method and device for identifying object | |
| CN112541393A (en) | Transformer substation personnel detection method and device based on deep learning | |
| CN114708537A (en) | Multi-view-angle-based system and method for analyzing abnormal behaviors of complex places | |
| CN113660484B (en) | Audio and video attribute comparison method, system, terminal and medium based on audio and video content | |
| CN111353436A (en) | Super store operation analysis method and device based on image deep learning algorithm | |
| CN113343779A (en) | Environment anomaly detection method and device, computer equipment and storage medium | |
| CN111815576B (en) | Method, device, equipment and storage medium for detecting corrosion condition of metal part | |
| CN115346169B (en) | Method and system for detecting sleep post behaviors | |
| CN117576632B (en) | Multi-mode AI large model-based power grid monitoring fire early warning system and method | |
| CN113518205A (en) | Video patrol processing method based on AI analysis | |
| CN114694130A (en) | Method and device for detecting telegraph poles and pole numbers along railway based on deep learning | |
| CN111541877A (en) | Automatic monitoring system for substation equipment | |
| CN115909144A (en) | Method and system for detecting abnormity of surveillance video based on counterstudy | |
| CN116416208A (en) | Pipeline defect detection method and device, electronic equipment and storage medium | |
| CN115565135A (en) | Target tracking method and device and electronic equipment | |
| CN115719428A (en) | Face image clustering method, device, equipment and medium based on classification model | |
| CN114898181A (en) | Hidden danger violation identification method and device for explosion-related video | |
| CN113392770A (en) | Typical violation behavior detection method and system for transformer substation operating personnel | |
| CN114385837A (en) | Automatic media content detection and verification method and system | |
| CN114140879A (en) | Behavior identification method and device based on multi-head cascade attention network and time convolution network |
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 |