CN107944371A - A kind of public security video monitoring image processing method based on data mining - Google Patents
A kind of public security video monitoring image processing method based on data mining Download PDFInfo
- Publication number
- CN107944371A CN107944371A CN201711144255.5A CN201711144255A CN107944371A CN 107944371 A CN107944371 A CN 107944371A CN 201711144255 A CN201711144255 A CN 201711144255A CN 107944371 A CN107944371 A CN 107944371A
- Authority
- CN
- China
- Prior art keywords
- image
- public security
- feature
- video monitoring
- carried out
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
- G06V20/47—Detecting features for summarising video content
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Alarm Systems (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of public security video monitoring image processing method based on data mining.This method includes:Obtain every frame image data comprising temporal information and positional information of moving target;Image characteristics extraction is carried out using digging technology;The successful data frame packing numbering of similarity mode is carried out to characteristics of image;Characteristic Contrast verification is carried out to numbering identical characteristics of image, and is associated with public security target database;The identical feature data frame of every group # is subjected to image mosaic reduction under corresponding video background.The present invention carries out Image mining processing first, the image of identical image feature is subjected to packing numbering, feature verification again, is associated with public security target database and matched suspected target characteristic image is restored in corresponding video, so as to appear in time and the position of different video monitoring equipment according to suspected target, confirm suspected target trend, the dynamic tracking of precise image feature is realized, improves the efficiency that target is traced in public security search.
Description
Technical field
The present invention relates to technical field of video image processing, more particularly relates to a kind of public security video based on data mining
Monitoring image processing method.
Background technology
Public security organ is as the administrative of public security and criminal case-handling machine in our people's democratic dictatorship regime with arms property
Close, how to effectively improve the scientific and technological informationization level and work efficiency of public security organ, its is significant.In recent years, with me
The fast development of state's economic society and the continuous quickening of scientific and technological information paces, China's level of IT application achieve considerable hair
Exhibition;Wherein, important component of the video monitoring as social safety crime prevention system, development, growth trend are particularly evident.Cause
This, can public security organ effectively integrate, using existing video monitoring resource, and effectively improve public security machine based on existing resource
The case handling efficiency of pass, is of great significance.
At present, when public security is collected evidence by video, only the video image in specific monitoring point monitoring range is seen
Evidence obtaining is examined, such as:To some indoor carry out video monitoring, or video monitoring is carried out to a certain road section scope;Therefore, video is carried out
During image forensics, image forensic result can only confirm when target occurred herein, can not be closed associated video image
Connection is unfavorable for public security search and traces target precisely efficiently to determine the trend of target.
In conclusion public security method of video image processing of the prior art, when carrying out video image evidence obtaining there are public security,
Suspected target investigation carried out by video image in single monitoring range, its precision cannot be guaranteed and inefficiency is asked
Topic.
The content of the invention
The embodiment of the present invention provides a kind of public security video monitoring image processing method based on data mining, existing to solve
Have in technology there are during public security progress video image evidence obtaining, suspected target is carried out by the video image in single monitoring range and is detectd
Look into, its precision cannot be guaranteed and the problem of inefficiency.
The embodiment of the present invention provides a kind of public security video monitoring image processing method based on data mining, including:
The video data of corresponding region is gathered by multiple video monitoring equipments;Based on Gaussian Mixture background modeling to collection
Video data carry out data frame separation, obtain every frame image data comprising temporal information and positional information of moving target;
Edge enhancing is carried out according to intensity profile to every two field picture using data mining technology, to the enhanced image in edge
Image segmentation is carried out by dynamic threshold segmentation method, and characteristics of image is carried out by Principal Component Analysis to the image after segmentation
Extraction;Wherein, the characteristic image of extraction, including:Character image characteristic information and vehicle image characteristic information;
Similarity mode is carried out to the characteristics of image in the video data of each video monitoring equipment collection, by similarity
With the characteristic image successfully with temporal information and positional information characteristic similarity packing numbering is carried out according to data frame;
The characteristics of image identical to the numbering in the video data of each video monitoring equipment collection carries out Characteristic Contrast, school
Test definite precise image feature and be stored in image feature base;Image feature base and public security target database are carried out
Association, and in real time contrasted the characteristic image in image feature base and the target image in public security target database,
If similarity is higher than preset value, early warning is carried out;Wherein, the target image in the public security target database, including:Personage
Image feature information and vehicle image characteristic information;
Video background modeling is carried out using dynamic texture modeling, and passage time and position are closed with characteristic image
Connection;The identical feature data frame of every group # is subjected to image mosaic reduction under corresponding video background, and to each image into
Row time-tracking and location tracking.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Concentration is carried out to video data, the video frequency abstract that obtains including all moving targets and all moving targets
Full snapshot.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Retrieval process is carried out to video data, obtains the target snapshot of the moving target by characteristic similarity arrangement.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Denoising is carried out by image gray processing, and to the image of gray processing.
Preferably, the character image characteristic information, specifically includes:Face feature, hair style, jacket, hand-characteristic, footwear
Son, height, fat or thin and belongings.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Order according to image data frame is combined the character image feature of successive frame analysis, and it is special to obtain personage's dynamic
Sign.
Preferably, personage's behavioral characteristics, including:Run on foot foot.
Preferably, the vehicle image characteristic information, including:Car plate, vehicle, vehicle LOGO, size and color.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Local feature amplification is carried out to the characteristics of image of extraction;Wherein, the local feature, including:In character image feature
Face's feature, jacket, hand feature and shoes, car plate feature and vehicle LOGO features in vehicle image feature.
In the embodiment of the present invention, there is provided a kind of public security video monitoring image processing method based on data mining, it is and existing
Technology is compared, and its advantage is:The present invention carries out view data by the video data for gathering multiple video monitoring equipments
Excavation processing after, then by the image with identical image feature carry out packing numbering, feature checking treatment, with public security target
Database association processing and by matched suspected target characteristic image according to time and position recovering into corresponding video so that
Time and the position in different video monitoring equipment are appeared according to suspected target, the trend of suspected target is confirmed, realizes essence
The dynamic tracking of quasi- characteristics of image, improves the efficiency that target is traced in public security search;Wherein, packing numbering is carried out to image
With feature checking treatment, feature accuracy is enhanced;The characteristic image of video acquisition processing is associated with public security target database,
The appearance of object is prompted so that police criminal detection personnel take measures in time;And by matched suspected target characteristic image according to
Time and position recovering intuitively efficiently investigate suspected target and target trend into corresponding video easy to public security.
Brief description of the drawings
Fig. 1 is a kind of public security video monitoring image process flow based on data mining provided in an embodiment of the present invention
Figure.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without making creative work
Embodiment, belongs to the scope of protection of the invention.
Fig. 1 is a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention.Such as
Shown in Fig. 1, this method includes:
Step S1, the video data of corresponding region is gathered by multiple video monitoring equipments;Built based on Gaussian Mixture background
Mould carries out data frame separation to the video data of collection, obtains every frame figure comprising temporal information and positional information of moving target
As data.
It should be noted that video monitoring of the multiple video monitoring equipments of the present invention for distribution in an extensive area
Equipment, such as:One area or city;These video monitoring equipments investigate the server communication of unit by internet and public security.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Concentration is carried out to video data, the video frequency abstract that obtains including all moving targets and all moving targets
Full snapshot;And/or retrieval process is carried out to video data, obtain the target snapshot of the moving target by characteristic similarity arrangement.
Step S2, carries out edge enhancing according to intensity profile to every two field picture using data mining technology, edge is strengthened
Image afterwards carries out image segmentation by dynamic threshold segmentation method, and the image after segmentation is carried out by Principal Component Analysis
Image characteristics extraction;Wherein, the characteristic image of extraction, including:Character image characteristic information and vehicle image characteristic information.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Denoising is carried out by image gray processing, and to the image of gray processing.
It should be noted that the above-mentioned processing to image, ensure that the quality of image, the effect of massive video investigation is improved
Rate, reduces the possibility that target is omitted.
Preferably, the character image characteristic information, specifically includes:Face feature, hair style, jacket, hand-characteristic, footwear
Son, height, fat or thin and belongings;The vehicle image characteristic information, including:Car plate, vehicle, vehicle LOGO, size and face
Color.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Order according to image data frame is combined the character image feature of successive frame analysis, and it is special to obtain personage's dynamic
Sign;Personage's behavioral characteristics, such as:Run on foot foot.
Preferably, a kind of public security video monitoring image processing method based on data mining provided in an embodiment of the present invention,
Further include:Local feature amplification is carried out to the characteristic image of extraction;Wherein, the local feature, including:In character image feature
Face's feature, jacket, hand feature and shoes, car plate feature and vehicle LOGO features in vehicle image feature.
It should be noted that by carrying out local feature enhanced processing to the characteristic image of extraction, feature recognition degree is improved,
Be conducive to public security investigation identification.
Step S3, similarity mode is carried out to the characteristics of image in the video data of each video monitoring equipment collection, will
Characteristic image of the similarity mode successfully with temporal information and positional information carries out characteristic similarity packing according to data frame
Numbering.
It should be noted that similarity is carried out to the characteristics of image in the video data that is gathered to each video monitoring equipment
Matching, successful match, then illustrate that same moving target is being appeared in the range of different video monitoring equipment;Mass data is carried out
Similarity mode, packing numbering is carried out by the target of successful match, and magnanimity initial data is provided for public security investigation.
Step S4, the characteristics of image identical to the numbering in the video data of each video monitoring equipment collection carry out feature
Contrast, verifies and determines precise image feature and be stored in image feature base;By image feature base and public security number of targets
Be associated according to storehouse, and in real time by the target image in the characteristic image in image feature base and public security target database into
Row contrast, if similarity is higher than preset value, carries out early warning;Wherein, the target image in the public security target database, bag
Include:Character image characteristic information and vehicle image characteristic information.
It should be noted that to the identical characteristics of image of numbering in the video data of each video monitoring equipment collection into
Row Characteristic Contrast, reaffirms precise image feature, improves characteristics of image accuracy.
It should be noted that image feature base and public security target database are associated, real-time tracing public security is disliked
Doubt target and Forewarning Measures are provided, it is not necessary to be manually compared, not only efficient quick, and save manpower.
Step S5, video background modeling, and passage time and position and characteristic image are carried out using dynamic texture modeling
It is associated;The identical feature data frame of every group # is subjected to image mosaic reduction under corresponding video background, and to each
Image carries out time-tracking and location tracking.
It should be noted that the characteristic image for the suspected target that public security confirms is regarded according to time and position recovering in correspondence
Under frequency background, suspected target is intuitively efficiently investigated easy to public security.
In conclusion the present invention is carried out at Image mining by the video data for gathering multiple video monitoring equipments
After reason, then by the image with identical image feature carry out packing numbering, feature checking treatment, with public security target database
Association process and by matched suspected target characteristic image according to time and position recovering into corresponding video so that according to suspicion
Doubtful target appears in time and position in different video monitoring equipment, confirms the trend of suspected target, realizes precise image
The dynamic tracking of feature, improves the efficiency that target is traced in public security search;Wherein, packing numbering and feature are carried out to image
Checking treatment, enhances feature accuracy;The characteristic image of video acquisition processing is associated with public security target database, prompts mesh
The appearance of thing is marked so that police criminal detection personnel take measures in time;And by matched suspected target characteristic image according to the time and
Position recovering intuitively efficiently investigates suspected target and target trend into corresponding video, easy to public security.
Disclosed above is only several specific embodiments of the present invention, and those skilled in the art can carry out the present invention
Various modification and variations without departing from the spirit and scope of the present invention, if these modifications and changes of the present invention belong to the present invention
Within the scope of claim and its equivalent technologies, then the present invention is also intended to comprising including these modification and variations.
Claims (9)
- A kind of 1. public security video monitoring image processing method based on data mining, it is characterised in that including:The video data of corresponding region is gathered by multiple video monitoring equipments;Collection is regarded based on Gaussian Mixture background modeling Frequency obtains every frame image data comprising temporal information and positional information of moving target according to data frame separation is carried out;Edge enhancing is carried out according to intensity profile to every two field picture using data mining technology, the enhanced image in edge is passed through Dynamic threshold segmentation method carries out image segmentation, and carries out characteristics of image by Principal Component Analysis to the image after segmentation and carry Take;Wherein, the characteristic image of extraction, including:Character image characteristic information and vehicle image characteristic information;To each video monitoring equipment collection video data in characteristics of image carry out similarity mode, by similarity mode into The characteristic image with temporal information and positional information of work(carries out characteristic similarity packing numbering according to data frame;The characteristics of image identical to the numbering in the video data of each video monitoring equipment collection carries out Characteristic Contrast, and verification is true Determine precise image feature and be stored in image feature base;Image feature base and public security target database are closed Connection, and in real time contrasted the characteristic image in image feature base and the target image in public security target database, such as Fruit similarity is higher than preset value, then carries out early warning;Wherein, the target image in the public security target database, including:Figure map As characteristic information and vehicle image characteristic information;Video background modeling is carried out using dynamic texture modeling, and passage time and position are associated with characteristic image;Will Image mosaic reduction is carried out under corresponding video background per the identical feature data frame of group #, and the time is carried out to each image Tracking and location tracking.
- 2. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that also wrap Include:Concentration is carried out to video data, the video frequency abstract that obtains including all moving targets and all moving targets it is complete soon According to.
- 3. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that also wrap Include:Retrieval process is carried out to video data, obtains the target snapshot of the moving target by characteristic similarity arrangement.
- 4. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that also wrap Include:Denoising is carried out by image gray processing, and to the image of gray processing.
- 5. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that described Character image characteristic information, specifically includes:Face feature, hair style, jacket, hand-characteristic, shoes, height, fat or thin and belongings Product.
- 6. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that also wrap Include:Order according to image data frame is combined the character image feature of successive frame analysis, obtains personage's behavioral characteristics.
- 7. the public security video monitoring image processing method based on data mining as claimed in claim 6, it is characterised in that described Personage's behavioral characteristics, including:Run on foot foot.
- 8. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that described Vehicle image characteristic information, including:Car plate, vehicle, vehicle LOGO, size and color.
- 9. the public security video monitoring image processing method based on data mining as claimed in claim 1, it is characterised in that also wrap Include:Local feature amplification is carried out to the characteristics of image of extraction;Wherein, the local feature, including:Face in character image feature Portion's feature, jacket, hand feature and shoes, car plate feature and vehicle LOGO features in vehicle image feature.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711144255.5A CN107944371A (en) | 2017-11-17 | 2017-11-17 | A kind of public security video monitoring image processing method based on data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711144255.5A CN107944371A (en) | 2017-11-17 | 2017-11-17 | A kind of public security video monitoring image processing method based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107944371A true CN107944371A (en) | 2018-04-20 |
Family
ID=61932762
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711144255.5A Pending CN107944371A (en) | 2017-11-17 | 2017-11-17 | A kind of public security video monitoring image processing method based on data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107944371A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110177255A (en) * | 2019-05-30 | 2019-08-27 | 北京易华录信息技术股份有限公司 | A kind of video information dissemination method and system based on case scheduling |
CN110213651A (en) * | 2019-05-28 | 2019-09-06 | 暨南大学 | A kind of intelligent merit Computer Aided Analysis System and method based on security protection video |
CN110876092A (en) * | 2018-09-04 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Video abstract generation method and device, electronic equipment and readable storage medium |
CN111241344A (en) * | 2020-01-14 | 2020-06-05 | 新华智云科技有限公司 | Video duplicate checking method, system, server and storage medium |
CN111881787A (en) * | 2020-07-13 | 2020-11-03 | 深圳力维智联技术有限公司 | Camera-based store illegal operation behavior identification method and system |
CN113691729A (en) * | 2021-08-27 | 2021-11-23 | 维沃移动通信有限公司 | Image processing method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006146378A (en) * | 2004-11-17 | 2006-06-08 | Hitachi Ltd | Monitoring system using multiple camera |
CN103020275A (en) * | 2012-12-28 | 2013-04-03 | 苏州千视通信科技有限公司 | Video analysis method based on video abstraction and video retrieval |
CN106250846A (en) * | 2016-07-29 | 2016-12-21 | 昆明理工大学 | A kind of public security image method for detecting based on video monitoring |
-
2017
- 2017-11-17 CN CN201711144255.5A patent/CN107944371A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2006146378A (en) * | 2004-11-17 | 2006-06-08 | Hitachi Ltd | Monitoring system using multiple camera |
CN103020275A (en) * | 2012-12-28 | 2013-04-03 | 苏州千视通信科技有限公司 | Video analysis method based on video abstraction and video retrieval |
CN106250846A (en) * | 2016-07-29 | 2016-12-21 | 昆明理工大学 | A kind of public security image method for detecting based on video monitoring |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110876092A (en) * | 2018-09-04 | 2020-03-10 | 杭州海康威视数字技术股份有限公司 | Video abstract generation method and device, electronic equipment and readable storage medium |
CN110876092B (en) * | 2018-09-04 | 2021-08-24 | 杭州海康威视数字技术股份有限公司 | Video abstract generation method and device, electronic equipment and readable storage medium |
CN110213651A (en) * | 2019-05-28 | 2019-09-06 | 暨南大学 | A kind of intelligent merit Computer Aided Analysis System and method based on security protection video |
CN110177255A (en) * | 2019-05-30 | 2019-08-27 | 北京易华录信息技术股份有限公司 | A kind of video information dissemination method and system based on case scheduling |
CN111241344A (en) * | 2020-01-14 | 2020-06-05 | 新华智云科技有限公司 | Video duplicate checking method, system, server and storage medium |
CN111241344B (en) * | 2020-01-14 | 2023-09-05 | 新华智云科技有限公司 | Video duplicate checking method, system, server and storage medium |
CN111881787A (en) * | 2020-07-13 | 2020-11-03 | 深圳力维智联技术有限公司 | Camera-based store illegal operation behavior identification method and system |
CN113691729A (en) * | 2021-08-27 | 2021-11-23 | 维沃移动通信有限公司 | Image processing method and device |
CN113691729B (en) * | 2021-08-27 | 2023-08-22 | 维沃移动通信有限公司 | Image processing method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107944371A (en) | A kind of public security video monitoring image processing method based on data mining | |
WO2016141641A1 (en) | Method and device for recognizing suspicious person | |
CN102610102B (en) | Suspect vehicle inspection and control method and system | |
CN106056079B (en) | A kind of occlusion detection method of image capture device and human face five-sense-organ | |
CN110648352B (en) | Abnormal event detection method and device and electronic equipment | |
CN108229335A (en) | It is associated with face identification method and device, electronic equipment, storage medium, program | |
CN108053427A (en) | A kind of modified multi-object tracking method, system and device based on KCF and Kalman | |
CN109446936A (en) | A kind of personal identification method and device for monitoring scene | |
CN105160318A (en) | Facial expression based lie detection method and system | |
CN102521565A (en) | Garment identification method and system for low-resolution video | |
CN106355154B (en) | Method for detecting frequent passing of people in surveillance video | |
CN106874372A (en) | The method and device of destination object identification information is obtained based on unmanned plane | |
CN110414459A (en) | Establish the associated method and device of people's vehicle | |
CN107526997A (en) | A kind of personnel's track recognizing method and device | |
CN108830204B (en) | Method for detecting abnormality in target-oriented surveillance video | |
Al-Hmouz et al. | License plate localization using a statistical analysis of Discrete Fourier Transform signal | |
CN113011300A (en) | Method, system and equipment for AI visual identification of violation behavior | |
Pinthong et al. | The License Plate Recognition system for tracking stolen vehicles | |
CN115687460B (en) | Method and system for mining associated object of key crowd by using trajectory data | |
CN108171187A (en) | A kind of abnormal behaviour automatic identifying method and device based on the extraction of bone point | |
CN106023166A (en) | Method and device for detecting dangerous objects hidden by human bodies based on microwave images | |
CN103400382A (en) | Abnormal panel detection algorithm based on ATM (Automatic Teller Machine) scene | |
CN113469080A (en) | Individual, group and scene interactive collaborative perception method, system and equipment | |
CN106714007A (en) | Video abstract method and apparatus | |
CN111062295A (en) | Area positioning method and device, and storage medium |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180420 |