CN110392235A - A kind of video monitoring processing system based on artificial intelligence - Google Patents
A kind of video monitoring processing system based on artificial intelligence Download PDFInfo
- Publication number
- CN110392235A CN110392235A CN201910647582.5A CN201910647582A CN110392235A CN 110392235 A CN110392235 A CN 110392235A CN 201910647582 A CN201910647582 A CN 201910647582A CN 110392235 A CN110392235 A CN 110392235A
- Authority
- CN
- China
- Prior art keywords
- frame
- module
- video
- suspect
- human body
- 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
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- 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
-
- 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
- G06V20/49—Segmenting video sequences, i.e. computational techniques such as parsing or cutting the sequence, low-level clustering or determining units such as shots or scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/103—Static body considered as a whole, e.g. static pedestrian or occupant recognition
-
- 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
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Abstract
The video monitoring processing system based on artificial intelligence that the invention discloses a kind of, including video acquisition module, are obtained monitor video to be processed and are numbered by way of video input;Personnel information acquisition module obtains the information of suspect by way of data input;Monitor video is decomposed into each frame by video decomposing module;Personal information extraction module extracts the aspectual character of suspect;Frame matching module, successively the image zooming-out of the human body in each frame is come out, and extract the aspectual character of the human body in frame, the aspectual character of the aspectual character of human body in frame and suspect is compared, the aspectual character of the human body in output frame and the consistent frame of the aspectual character of suspect;Each frame a combination thereof is become a video and watched for user by Video Output Modules.The present invention dislikes the photo to induce one to search in monitor video according to crime, and the video intercepting for the people that is suspected of being guilty is come out, and saves and handles a case the time for policeman in charge of the case.
Description
Technical field
The present invention relates to computer field, in particular to a kind of video monitoring processing system based on artificial intelligence.
Background technique
At present in general case of criminal detection, policeman in charge of the case will be by the video captured by monitoring video to suspect
Whereabouts investigated, obtain the direction of escaping of suspect, find suspect, then suspect is grabbed
It catches.But each monitoring only has the image of part, therefore, present policeman in charge of the case's moment carries out elder brother's prison by computer
The viewing for controlling video recording usually day and night will ceaselessly watch a couple of days available some clues of, in this way for criminal investigation is handled a case
It is very cumbersome, it consumes and largely handles a case the time.
Summary of the invention
The purpose of the present invention is overcoming above-mentioned problems of the prior art, a kind of video based on artificial intelligence is provided
Processing system is monitored, dislikes the photo to induce one to be searched in monitor video according to crime, the video for the people that is suspected of being guilty is cut
It takes out, saves and handle a case the time for policeman in charge of the case.
For this purpose, the present invention provides a kind of video monitoring processing system based on artificial intelligence, comprising:
Video acquisition module obtains monitor video to be processed by way of video input, and to prison to be processed
The front and back for controlling the time according to monitoring of video carries out ascending number.
Personnel information acquisition module obtains the information of suspect by way of data input.
Monitor video collected in video acquisition module is decomposed, obtains each frame, often by video decomposing module
The number of monitor video before the label of one frame is decomposed with the frame is identical.
The feature of suspect in personnel information acquisition module is extracted, is violated by personal information extraction module
The aspectual character of guilty suspect.
The image zooming-out of human body in each of video decomposing module frame is successively come out, and mentioned by frame matching module
The aspectual character for taking the human body in frame, by suspect in the aspectual character of the human body in frame and personal information extraction module
Aspectual character compares, the aspectual character of the human body in output frame and the consistent frame of the aspectual character of suspect.
Video Output Modules, according to the number of each frame exported in frame matching module, using ascending sequence
It successively sorts, and is combined and is watched as a video for user.
Further, the video information acquisition module includes:
Camera information recording module obtains the number of camera by way of typing.
Video collect module, according to the number of the camera of camera information recording module, in the monitoring system in city
Monitor video captured by reference numeral camera is obtained, while each monitor video is cut out by the time range of typing
It cuts, obtains required monitor video of handling a case.
Monitoring period obtains module, and the time of monitoring is extracted from monitor video.
Number module, obtained according to monitoring period time of monitoring for being extracted in module to monitor video carry out by it is small to
Big number.
Further, the camera information recording module includes:
Virtual map module obtains the virtual map in city by the cartographic model in city.
Virtual map in virtual map module is shown to user, and receives user virtually by route recording module
Drawn route in figure.
Camera number obtains module, according to the route that user in route recording module draws, searches corresponding in the route
Camera, and successively obtain according to the direction of route the number of camera.
Further, the mode of information of the personnel information acquisition module in typing suspect include words input,
Image typing and 3D typing.
Further, the aspectual character in the personal information extraction module includes figure feature, garment ornament and face
Feature.
Further, will violate in the aspectual character of the human body in frame and personal information extraction module in the frame matching module
The aspectual character of guilty suspect compares, and includes the following steps:
S1: will decompose the aspectual character of the human body in frame in frame matching module, and it is special to be decomposed into figure feature, dress ornament
Sign and facial characteristics.
S2: by frame matching module by suspect in the garment ornament of the human body in frame and personal information extraction module
Garment ornament compare, if will be in the garment ornament of the human body in frame and personal information extraction module in frame matching module
The garment ornament of suspect is consistent, then carries out step S3, if by the garment ornament of the human body in frame in frame matching module
It is inconsistent with the garment ornament of suspect in personal information extraction module, then the frame is not exported.
S3: by frame matching module by suspect in the figure feature of the human body in frame and personal information extraction module
Figure feature compare, if will be in the figure feature of the human body in frame and personal information extraction module in frame matching module
The figure feature of suspect is consistent, then carries out step S4, if by the figure feature of the human body in frame in frame matching module
It is inconsistent with the figure feature of suspect in personal information extraction module, then the frame is not exported.
S4: by frame matching module by suspect in the facial characteristics of the human body in frame and personal information extraction module
Facial characteristics compare, if will be in the facial characteristics of the human body in frame and personal information extraction module in frame matching module
The facial characteristics of suspect is consistent, then exports the frame, if in frame matching module by the facial characteristics of the human body in frame with
The facial characteristics of suspect is inconsistent in personal information extraction module, then does not export the frame.
A kind of video monitoring processing system based on artificial intelligence provided by the invention, has the following beneficial effects:
1, dislike the photo to induce one to be searched in monitor video according to crime, the video intercepting for the people that is suspected of being guilty is gone out
Come, saves and handle a case the time for policeman in charge of the case;
2, when the monitor video of typing camera, without removing each site collection monitor video, directly in system
The number of middle typing successively typing monitoring camera;
3, user can directly input the route that suspect is passed through, and system is automatic according to the route of suspect
Obtain corresponding monitoring, the monitoring for the acquisition for being it is more perfect, monitoring will not be caused to lack due to artificial fault
Phenomenon.
Detailed description of the invention
Fig. 1 is a kind of each module connection signal frame of the video monitoring processing system based on artificial intelligence provided by the invention
Figure;
Fig. 2 is video information acquisition module in a kind of video monitoring processing system based on artificial intelligence provided by the invention
Connection signal block diagram;
Fig. 3 is each module connection signal of camera information recording module in video information acquisition module provided by the invention
Block diagram;
Fig. 4 is in a kind of frame matching module of the video monitoring processing system based on artificial intelligence provided by the invention by frame
In the aspectual character of human body and the aspectual character of suspect in personal information extraction module do the process of the method compared
Block diagram.
Specific embodiment
With reference to the accompanying drawing, multiple specific embodiments of the invention are described in detail, it is to be understood that of the invention
Protection scope be not limited by the specific implementation.
Embodiment 1
A kind of video monitoring processing system based on artificial intelligence is present embodiments provided, it is special by basic necessary technology
The existing goal of the invention of the invention of levies in kind.
As shown in Figure 1, the embodiment of the invention provides a kind of video monitoring processing system based on artificial intelligence, comprising:
Video acquisition module obtains monitor video to be processed by way of video input, and to prison to be processed
The front and back for controlling the time according to monitoring of video carries out ascending number.Monitoring period in front, numbers smaller, time
Below, number larger.For example, the number of 15:30 is 1, then the number of 15:31 is exactly 2, and the number of 15:32 successively is
3.It is numbered according to the rule, so that monitor video volume has sequence.
Personnel information acquisition module obtains the information of suspect by way of data input.Suspect's
Information refers to the facial features of suspect, the information such as clothing.These information are to identify suspicion of crime in video
People, there are many kinds of specific typing modes.
Monitor video collected in video acquisition module is decomposed, obtains each frame, often by video decomposing module
The number of monitor video before the label of one frame is decomposed with the frame is identical.The number by frame is put up in this way to the progress later period
Recombination.
The feature of suspect in personnel information acquisition module is extracted, is violated by personal information extraction module
The aspectual character of guilty suspect.The aspectual character that suspect is extracted in personnel information acquisition module, for characteristic value
It extracts, here includes a variety of situations, it is related with the typing mode of information in personnel information acquisition module, if information is to pass through figure
The format of picture carries out typing, then extracts the characteristic value in image, if information is to carry out typing by the format of text, extracts
The keyword of text, but by method that picture and text are converted by text conversion into the characteristic value of image.
The method of picture and text conversion, specifically finds out corresponding image according to the keyword of extraction in picture library and carries out group
It closes, in the characteristic value for the image for extracting combination.The picture library, for storing figure corresponding to several keywords and keyword
Picture.
The image zooming-out of human body in each of video decomposing module frame is successively come out, and mentioned by frame matching module
The aspectual character for taking the human body in frame, by suspect in the aspectual character of the human body in frame and personal information extraction module
Aspectual character compares, the aspectual character of the human body in output frame and the consistent frame of the aspectual character of suspect.It will be each
Aspectual character of the aspectual character of human body in a frame respectively with suspect in personal information extraction module compares, output
The aspectual character of human body in frame and the consistent frame of the aspectual character of suspect, are the screening to frame in video, obtain
The video needed.
Video Output Modules, according to the number of each frame exported in frame matching module, using ascending sequence
It successively sorts, and is combined and is watched as a video for user.The frame that last step screens is combined, is combined
Method be according to its number, ascending is ranked up, by these frames synthesize a video.
In the present invention, the length of frame can be executed according to the length of setting, in video acquisition module, the length of video
It is to be acquired according to the duration of setting.Meanwhile the decomposition for frame in video decomposites the quantity of the frame come in video
It is limited, in general, the frame of video front is only decomposited, the frame of frame and video rear portion in the middle part of video.By the way that frame and crime are disliked
The feature for doubting people compares, the frame of the image for the people that obtains being suspected of being guilty in the image of frame.It is finally combined, obtains by frame
To treated video.To not there is no the part of suspect's image to be filtered in video in this way, shortens the view of personnel in charge of the case
Frequency viewing time improves the efficiency handled a case.
Embodiment 2
The present embodiment is optimized based on embodiment 1 and to the embodiment in embodiment 1, so that the present embodiment is being transported
More stable in capable process, performance is more good, but is not limited in a kind of embodiment party described in the present embodiment
Formula.
Specifically, as shown in Fig. 2, the video information acquisition module includes:
Camera information recording module obtains the number of camera by way of typing.I.e. to the record of camera number
Enter.
Video collect module, according to the number of the camera of camera information recording module, in the monitoring system in city
Monitor video captured by reference numeral camera is obtained, while each monitor video is cut out by the time range of typing
It cuts, obtains required monitor video of handling a case.The video monitored, while every section of typing monitoring are numbered according to above-mentioned camera
The time range of video, system cut monitor video according to the time range of typing, the monitor video needed.It is right
In time range, it is that personnel in charge of the case carries out typing, specifically specific time model can be obtained according to the reasoning of personnel in charge of the case
It encloses.
Monitoring period obtains module, and the time of monitoring is extracted from monitor video.Since angle is general on monitor video
There will be the monitoring period of monitor video, the main function of the step is the time for extracting monitor video monitoring.
Number module, obtained according to monitoring period time of monitoring for being extracted in module to monitor video carry out by it is small to
Big number.According to the progress of above-mentioned monitoring period, ascending sequence is numbered.I.e. above-mentioned, the number of 15:30 is
1, then the number of 15:31 is exactly 2, and the number of 15:32 successively is 3.It is numbered according to the rule, so that monitor video was compiled
There is sequence.
A kind of monitor video for video acquisition module provided herein and the number for not obtaining monitor video.But simultaneously
It is not limited only to a kind of this embodiment.
More specifically, as shown in figure 3, the camera information recording module includes:
Virtual map module obtains the virtual map in city by the cartographic model in city.It is as described herein virtually
Figure is map shown in map software.
Virtual map in virtual map module is shown to user, and receives user virtually by route recording module
Drawn route in figure.Personnel in charge of the case can see virtual map at the terminal, and terminal is touch display screen, while personnel in charge of the case
By the route in touch display screen output map, which is the route that the suspect being inferred to is passed through.
Camera number obtains module, according to the route that user in route recording module draws, searches corresponding in the route
Camera, and successively obtain according to the direction of route the number of camera.It is successively passed through being found out in route according to route
The number for the camera crossed.
Certainly, in actual handle a case, personnel in charge of the case can not accurately be known that the route of suspect very much,
But can test several times, draw out some specific routes more. more.Since system is when operation, the speed of computer can compare
It is artificial fast very more, it is still to have saved the time from whole angle therefore.
Embodiment 3
The present embodiment is optimized based on embodiment 1 and to the embodiment in embodiment 1, so that the present embodiment is being transported
More stable in capable process, performance is more good, but is not limited in a kind of embodiment party described in the present embodiment
Formula.
Specifically, the mode of information of the personnel information acquisition module in typing suspect include words input,
Image typing and 3D typing.The aspectual character that suspect is extracted in personnel information acquisition module, for characteristic value
It extracts, here includes a variety of situations, it is related with the typing mode of information in personnel information acquisition module, if information is to pass through figure
The format of picture carries out typing, then extracts the characteristic value in image, if information is to carry out typing by the format of text, extracts
The keyword of text, but by method that picture and text are converted by text conversion into the characteristic value of image, recorded if it is by 3D
Enter, is the typing of 3D rendering actually, then it is similar with the processing mode of image typing.
The method of picture and text conversion, specifically finds out corresponding image according to the keyword of extraction in picture library and carries out group
It closes, in the characteristic value for the image for extracting combination.The picture library, for storing figure corresponding to several keywords and keyword
Picture.
Specifically, the aspectual character in the personal information extraction module includes figure feature, garment ornament and face
Feature.Aspectual character is subjected to detailed differentiation, so that when being matched, it can more accurate, obtained result
It can be more accurate.
More specifically, as shown in figure 4, mentioning the aspectual character of the human body in frame with personal information in the frame matching module
The aspectual character of suspect compares in modulus block, includes the following steps:
S1: will decompose the aspectual character of the human body in frame in frame matching module, and it is special to be decomposed into figure feature, dress ornament
Sign and facial characteristics.
S2: by frame matching module by suspect in the garment ornament of the human body in frame and personal information extraction module
Garment ornament compare, if will be in the garment ornament of the human body in frame and personal information extraction module in frame matching module
The garment ornament of suspect is consistent, then carries out step S3, if by the garment ornament of the human body in frame in frame matching module
It is inconsistent with the garment ornament of suspect in personal information extraction module, then the frame is not exported.
S3: by frame matching module by suspect in the figure feature of the human body in frame and personal information extraction module
Figure feature compare, if will be in the figure feature of the human body in frame and personal information extraction module in frame matching module
The figure feature of suspect is consistent, then carries out step S4, if by the figure feature of the human body in frame in frame matching module
It is inconsistent with the figure feature of suspect in personal information extraction module, then the frame is not exported.
S4: by frame matching module by suspect in the facial characteristics of the human body in frame and personal information extraction module
Facial characteristics compare, if will be in the facial characteristics of the human body in frame and personal information extraction module in frame matching module
The facial characteristics of suspect is consistent, then exports the frame, if in frame matching module by the facial characteristics of the human body in frame with
The facial characteristics of suspect is inconsistent in personal information extraction module, then does not export the frame.
Above-mentioned steps describe for identifying suspect's feature in each frame, obtain the specific of suitable frame
Process, specifically, successively being judged that the frame of the obtained people that is suspected of being guilty is very from the feature of dress ornament, figure and face
It is accurate.Meanwhile by judgement and screening successively, the time of comparison is also saved, that is, improves the speed of service of system, makes
The system of obtaining is run more efficient.
In conclusion the invention discloses a kind of video monitoring processing system based on artificial intelligence, including video acquisition
Module obtains monitor video to be processed by way of video input, and to monitor video to be processed according to monitoring
The front and back of time carry out ascending number;Personnel information acquisition module is obtained crime by way of data input and disliked
Doubt the information of people;Monitor video collected in video acquisition module is decomposed, obtains each by video decomposing module
Frame, the number of monitor video before the label of each frame is decomposed with the frame are identical;Personal information extraction module, by personal information
The feature of suspect extracts in acquisition module, obtains the aspectual character of suspect;Frame matching module successively will
The image zooming-out of human body in each of video decomposing module frame comes out, and extracts the aspectual character of the human body in frame, will
The aspectual character of human body in frame and the aspectual character of suspect in personal information extraction module compare, in output frame
The aspectual character of human body and the consistent frame of the aspectual character of suspect;Video Output Modules, according to defeated in frame matching module
The number of each frame out is successively sorted using ascending sequence, and is combined and is seen as a video for user
It sees.The present invention dislikes the photo to induce one to search in monitor video according to crime, and the video intercepting for the people that is suspected of being guilty is gone out
Come, saves and handle a case the time for policeman in charge of the case.
Disclosed above is only several specific embodiments of the invention, and still, the embodiment of the present invention is not limited to this, is appointed
What what those skilled in the art can think variation should all fall into protection scope of the present invention.
Claims (6)
1. a kind of video monitoring processing system based on artificial intelligence characterized by comprising
Video acquisition module is obtained monitor video to be processed by way of video input, and regarded to monitoring to be processed
The front and back of the time according to monitoring of frequency carries out ascending number;
Personnel information acquisition module obtains the information of suspect by way of data input;
Monitor video collected in video acquisition module is decomposed, obtains each frame by video decomposing module, each
The number of monitor video before the label of frame is decomposed with the frame is identical;
Personal information extraction module extracts the feature of suspect in personnel information acquisition module, obtains crime and dislikes
Doubt the aspectual character of people;
The image zooming-out of human body in each of video decomposing module frame is successively come out, and extracts frame by frame matching module
In human body aspectual character, by the posture of suspect in the aspectual character of the human body in frame and personal information extraction module
Feature compares, the aspectual character of the human body in output frame and the consistent frame of the aspectual character of suspect;
Video Output Modules, according to the number of each frame exported in frame matching module, successively using ascending sequence
Sequence, and be combined and watched as a video for user.
2. a kind of video monitoring processing system based on artificial intelligence as described in claim 1, which is characterized in that the video
Information acquisition module includes:
Camera information recording module obtains the number of camera by way of typing;
Video collect module obtains in the monitoring system in city according to the number of the camera of camera information recording module
Monitor video captured by reference numeral camera, while each monitor video is cut by the time range of typing,
Obtain required monitor video of handling a case;
Monitoring period obtains module, and the time of monitoring is extracted from monitor video;
Number module carries out monitor video according to the time that monitoring period obtains the monitoring extracted in module ascending
Number.
3. a kind of video monitoring processing system based on artificial intelligence as claimed in claim 2, which is characterized in that the camera shooting
Head data input module include:
Virtual map module obtains the virtual map in city by the cartographic model in city;
Virtual map in virtual map module is shown to user, and receives user in virtual map by route recording module
Drawn route;
Camera number obtains module, according to the route that user in route recording module draws, searches corresponding in the route take the photograph
As head, and successively obtain according to the direction of route the number of camera.
4. a kind of video monitoring processing system based on artificial intelligence as described in claim 1, which is characterized in that the personnel
Information acquisition module includes words input, image typing and 3D typing in the mode of the information of typing suspect.
5. a kind of video monitoring processing system based on artificial intelligence as described in claim 1, which is characterized in that the personnel
Aspectual character in information extraction modules includes figure feature, garment ornament and facial characteristics.
6. a kind of video monitoring processing system based on artificial intelligence as claimed in claim 5, which is characterized in that the frame
With the aspectual character of the human body in frame and the aspectual character of suspect in personal information extraction module are compared in module,
Include the following steps:
S1: will decompose the aspectual character of the human body in frame in frame matching module, be decomposed into figure feature, garment ornament with
And facial characteristics;
S2: by frame matching module by the clothes of suspect in the garment ornament of the human body in frame and personal information extraction module
Decorations feature compares, if by crime in the garment ornament of the human body in frame and personal information extraction module in frame matching module
The garment ornament of suspect is consistent, then carries out step S3, if by the garment ornament of the human body in frame and people in frame matching module
The garment ornament of suspect is inconsistent in member's information extraction modules, then does not export the frame;
S3: by frame matching module by the body of suspect in the figure feature of the human body in frame and personal information extraction module
Shape feature compares, if by crime in the figure feature of the human body in frame and personal information extraction module in frame matching module
The figure feature of suspect is consistent, then carries out step S4, if by the figure feature of the human body in frame and people in frame matching module
The figure feature of suspect is inconsistent in member's information extraction modules, then does not export the frame;
S4: by frame matching module by the face of suspect in the facial characteristics of the human body in frame and personal information extraction module
Portion's feature compares, if by crime in the facial characteristics of the human body in frame and personal information extraction module in frame matching module
The facial characteristics of suspect is consistent, then exports the frame, if by the facial characteristics of the human body in frame and personnel in frame matching module
The facial characteristics of suspect is inconsistent in information extraction modules, then does not export the frame.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910647582.5A CN110392235A (en) | 2019-07-17 | 2019-07-17 | A kind of video monitoring processing system based on artificial intelligence |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910647582.5A CN110392235A (en) | 2019-07-17 | 2019-07-17 | A kind of video monitoring processing system based on artificial intelligence |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110392235A true CN110392235A (en) | 2019-10-29 |
Family
ID=68285109
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910647582.5A Pending CN110392235A (en) | 2019-07-17 | 2019-07-17 | A kind of video monitoring processing system based on artificial intelligence |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110392235A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111402105A (en) * | 2020-03-16 | 2020-07-10 | 新疆联海创智信息科技有限公司 | Community management system |
CN112233421A (en) * | 2020-10-15 | 2021-01-15 | 胡歆柯 | Intelligent city intelligent traffic monitoring system based on machine vision |
CN112270205A (en) * | 2020-09-22 | 2021-01-26 | 苏州千视通视觉科技股份有限公司 | Case investigation method and device |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1472709A (en) * | 2003-05-14 | 2004-02-04 | 大连市公安局交通警察支队 | Method for rapid calling traffic TV monitoring image within required range |
CN103379307A (en) * | 2012-04-13 | 2013-10-30 | 何磊 | Video track tracking monitoring and retrieval playback system based on wireless positioning |
CN107909033A (en) * | 2017-11-15 | 2018-04-13 | 西安交通大学 | Suspect's fast track method based on monitor video |
US20180316877A1 (en) * | 2017-05-01 | 2018-11-01 | Sensormatic Electronics, LLC | Video Display System for Video Surveillance |
US20190080003A1 (en) * | 2017-09-14 | 2019-03-14 | Avigilon Corporation | Method and system for interfacing with a user to facilitate an image search for a person-of-interest |
-
2019
- 2019-07-17 CN CN201910647582.5A patent/CN110392235A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1472709A (en) * | 2003-05-14 | 2004-02-04 | 大连市公安局交通警察支队 | Method for rapid calling traffic TV monitoring image within required range |
CN103379307A (en) * | 2012-04-13 | 2013-10-30 | 何磊 | Video track tracking monitoring and retrieval playback system based on wireless positioning |
US20180316877A1 (en) * | 2017-05-01 | 2018-11-01 | Sensormatic Electronics, LLC | Video Display System for Video Surveillance |
US20190080003A1 (en) * | 2017-09-14 | 2019-03-14 | Avigilon Corporation | Method and system for interfacing with a user to facilitate an image search for a person-of-interest |
CN107909033A (en) * | 2017-11-15 | 2018-04-13 | 西安交通大学 | Suspect's fast track method based on monitor video |
Non-Patent Citations (2)
Title |
---|
卞强: "智能视频监控中运动目标检测与跟踪算法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
苏松志 等: "《行人检测 理论与实践》", 31 March 2016, 厦门大学出版社 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111402105A (en) * | 2020-03-16 | 2020-07-10 | 新疆联海创智信息科技有限公司 | Community management system |
CN111402105B (en) * | 2020-03-16 | 2024-01-16 | 新疆联海创智信息科技有限公司 | Community management system |
CN112270205A (en) * | 2020-09-22 | 2021-01-26 | 苏州千视通视觉科技股份有限公司 | Case investigation method and device |
CN112233421A (en) * | 2020-10-15 | 2021-01-15 | 胡歆柯 | Intelligent city intelligent traffic monitoring system based on machine vision |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110263613A (en) | Monitor video processing method and processing device | |
CN110392235A (en) | A kind of video monitoring processing system based on artificial intelligence | |
US9141184B2 (en) | Person detection system | |
CN101772782B (en) | Device for displaying result of similar image search and method for displaying result of similar image search | |
US8811755B2 (en) | Detecting recurring events in consumer image collections | |
CN101425133B (en) | Human image retrieval system | |
US6052492A (en) | System and method for automatically generating an image to represent a video sequence | |
CN110084103A (en) | A kind of same pedestrian's analysis method and system based on face recognition technology | |
US8594373B2 (en) | Method for identifying an object in a video archive | |
CN109684913A (en) | A kind of video human face mask method and system based on community discovery cluster | |
US20080317353A1 (en) | Method and system for searching images with figures and recording medium storing metadata of image | |
CN110348347A (en) | A kind of information processing method and device, storage medium | |
CN111209446A (en) | Method and device for presenting personnel retrieval information and electronic equipment | |
CN106603999A (en) | Video monitoring alarming method and system | |
US20210089784A1 (en) | System and Method for Processing Video Data from Archive | |
JP3538112B2 (en) | Remote monitoring method, apparatus, and recording medium recording remote monitoring program | |
EP3570207B1 (en) | Video cookies | |
CN107851129A (en) | Information processor, information processing method and program | |
CN108334852A (en) | A kind of image analysis identifying system and image analysis recognition methods | |
Axenopoulos et al. | A Framework for Large-Scale Analysis of Video\" in the Wild\" to Assist Digital Forensic Examination | |
JP2020060923A (en) | Image search device, image search system, image search method and program | |
CN115623164A (en) | Fault positioning platform based on cloud monitoring | |
CN111191620B (en) | Method for constructing human-object interaction detection data set | |
WO2017077902A1 (en) | Data processing device, data processing method, and program | |
CN112906516A (en) | Violent behavior identification method based on deep learning, storage device and server |
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 |
Application publication date: 20191029 |
|
RJ01 | Rejection of invention patent application after publication |