CN102665064A - A traffic video monitoring system based on standard labeling and quick search - Google Patents
A traffic video monitoring system based on standard labeling and quick search Download PDFInfo
- Publication number
- CN102665064A CN102665064A CN2012100560220A CN201210056022A CN102665064A CN 102665064 A CN102665064 A CN 102665064A CN 2012100560220 A CN2012100560220 A CN 2012100560220A CN 201210056022 A CN201210056022 A CN 201210056022A CN 102665064 A CN102665064 A CN 102665064A
- Authority
- CN
- China
- Prior art keywords
- traffic
- video
- monitoring
- module
- standard
- 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
Images
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
The present invention discloses a traffic video monitoring system based on standard labeling and quick search, comprising a traffic monitoring video capturing module, a video image content analyzing module, a traffic video key frame obtaining module, a monitoring expansion data encoding module and a data stream searching module. Based on an SVAC standard, the grammar and semantics of the monitor messages can be appropriately expanded to satisfy the requirements of quick search of monitoring videos. The system provides a unified standard interface to realize labeling and quick search of compressed monitoring video data, and the monitor messages can be appropriately stretched and clipped according to business requirement to meet demand of functions such as data transmission. Meanwhile, an encoding scheme targeting traffic objects and events is worked out and the SVAC standard is used to realize a highly-accurate, simple, effective, unified and fast labeling and quick search method of traffic objects and events.
Description
Technical field
The invention belongs to technical field of video monitoring, relate to a kind of traffic video monitoring system, specifically a kind of based on standard mark and the traffic video monitoring system of retrieving fast.
Background technology
SVAC: English Technical Specification of Surveillance Video and Audio Coding abbreviation; Corresponding Chinese is " safety precaution monitoring digital video-audio encoding and decoding technique requires "; By The First Research Institute of Ministry of Public Security and national guard and alarm system technical committee for standardization (TCST) (SAC/TC100) process combing analysis; Put out the main similarities and differences of safety precaution monitoring video/audio encoding and decoding and broadcasting and TV medium video/audio encoding and decoding in order, clear and definite safety precaution monitoring digital video-audio encoding and decoding specific demands are after repeated discussions after the correction; Finally become national standard, and in formal enforcement on May 1st, 2011.
Be accompanied by the construction energetically in " safe city ", " wisdom city ", road and traffic monitoring become one of its major technique means.Show that according to relevant data by 2010, a lot of large size cities installed more than 20 ten thousand monitoring cameras, these more than 20 ten thousand cameras will spread all over road, bridge and the public transportation system in city mostly.Because professional needs, most of monitor video needs to file behind the compressed encoding, and the technology of employing can be international compression standard; Such as H.264; MPEG-4 etc. also can be company or individual's privately owned algorithms, are directed against the compression algorithm of monitor video etc. such as the Haikang prestige company of looking; Compression howsoever all can bring the traffic monitoring video data after the compression of magnanimity.How interested monitoring content is identified and record, and when the inquiry evidence obtaining, can use the interface of unified standard from mass data, to inquire the major issue that information needed is current video monitoring field efficiently, apace.
The video frequency searching in later stage often need carry out corresponding mark to video content in video preprocessor processing or video analysis stage for ease, for the method for mark, has based on standard with based on off-gauge two kinds of schemes.For off-gauge tagging scheme, be utilize metadata to some simple descriptive data such as scene, recording time, image essential information according to certain format in database or file; Tagging scheme for standard; Major part is the multimedia description scheme that utilizes based on MPEG-7; Target is exactly to produce a kind of standard of describing multimedia content data; Can carry out standardization to various dissimilar multimedia messagess and describe, and should describe with described content and interrelate, retrieve fast and effectively with realization.
Common video frequency searching mode has three kinds.1) utilize forenamed mark of having stored and index information directly video content to be retrieved; 2) video sequence that will handle decompresses earlier, returns to the aerial image prime field, carries out image and video analysis again; See whether content satisfies the condition of retrieval; 3) do not carry out decompression basically, directly utilize the compression domain data to analyze, whether satisfy search condition through the characteristic of obtaining video content in compression domain.But all there is defective in various degree in the prior art.
Retrieval mode based on metadata token; Utilize simple text, subjective describes, and accuracy is not high; Considerably less for the amount of information of describing video content simultaneously; The diversity that is difficult to reflecting video image itself again often will cooperate a large amount of manual retrievals to assist, and is unpractical for the quick retrieval of the mass data that requires certain accuracy.
Based on the retrieval mode under the multimedia description scheme of MPEG-7 standard; One side technical scheme relative complex; Often needing natural language processing technique, search engine technique and distributed system technology, is not to monitor video on the other hand, more can not be directed against the traffic monitoring video; Do not take into full account and utilize the characteristic of this type of video; Simultaneously complicated mark and index information and the video data through the coding standard compression are independently to separate, and also to the unified interface of monitor video, retrieve fast and the transmission of monitor message is operated so be unfavorable for the standardization of monitor video.
CBIR comprises to two kinds of pixel domain and compression domain data, and it is through analysis and understand the visual information of multimedia messages, retrieves according to the coupling of the multimedia low-level features that obtains.For pure pixel domain data analysis, at first need all decode the video data of compression, carry out video analysis in pixel domain then, for the monitor data of magnanimity,, all be unpractical no matter be spatially or on the time.For the compression domain data analysis, only there is the picture decoding process of very small amount, can ignore; But, need to consume great amount of time, and analysis is compared with pixel domain because analytic process is complicated; Accuracy is on the low side, also is not directed against the unified standard interface of monitor video simultaneously.
Summary of the invention
In order to overcome the above defective that exists in the prior art, the present invention provides a kind of traffic video monitoring system, based on the SVAC standard, and the syntax and semantics of the part of monitor message is wherein carried out suitable expansion, to satisfy the monitor video needs of retrieval fast.Use the SVAC standard; Be to video surveillance network fully; Can solve the problem that video/audio encoding and decoding standard disunity causes in the present video monitoring system system is difficult to interconnect; The solution of this interoperability provides the interface of a unified standard to realize the mark of compression monitor video data and retrieval fast, and can carry out suitable flexible and cutting to monitor message according to service needed; Satisfy the needs of functions such as transmission; Make the encoding scheme of a cover to traffic object and incident simultaneously, finally utilize the SVAC standard to realize the mark and the method for quickly retrieving of high, effectively simple and unified traffic object fast of a kind of accuracy rate and traffic events, technical scheme is:
A kind of based on standard mark and the traffic video monitoring system of retrieving fast; Comprise traffic monitoring video capture module and video image content analysis module; Also comprise and obtain traffic video key frame module, monitoring growth data coding module and to the code stream retrieval module, wherein:
Acting as of video image content analysis module extracts classifiable traffic object and traffic events from key frame;
Obtaining will there be incident in acting as of traffic video key frame module from the motion camera lens image setting is key frame, transmits traffic events and related object;
The monitoring growth data that act as of monitoring growth data coding module is expanded; Satisfy grammatical representation to the traffic object; Monitoring growth data unit is distinguished through extension_id; Get the extension_id value and represent the monitored object extension syntax for 0x6, beginning to the semanteme of reserve_bits from extension_id is consistent with other semantemes of monitoring the same syntax of figs element of growth data unit, and the semanteme of loop grammar is for finding each object from each zone; And from region_object_id, get access to the detailed features information of object; The implication of syntax element value is by application itself decision, and the region_object_id of traffic object is defined, and through the SVAC standard content after the expansion traffic object and traffic events encoded;
To acting as of code stream retrieval module according to the known SVAC code stream and the feature coding of traffic object or traffic events; From the monitoring growth data unit of code stream, find the picture position at traffic object or traffic events place and the position that belongs to zone in the image; Note the concrete parameter of picture position The corresponding area; From the vedio data of coding, find view data and decoding and displaying, mark corresponding area-of-interest simultaneously.
The present invention also can realize in the following manner; Said key frame information is directly from the video image content analysis module; Comprised detected traffic object or traffic events simultaneously, for incident, SVAC has the monitor event extension syntax structure to incident: event_extension; Region_event_id presentation of events characteristic is wherein carried out the coding standard definition with region_event_id to the traffic video business.
Further preferred, before looking for key frame, earlier the motion camera lens is classified according to the vehicle complexity wherein.
Compared with prior art, beneficial effect of the present invention:
(1) retrieval rate is very fast: owing to have only document flow to search and the operation of the key frame of decoding, do not have the decode procedure of multitude of video image and the analysis operation of low layer coding video frequency data.
(2) retrieval rate is high: because the analysis of object and incident and to obtain be at the video monitoring acquisition phase; And the quality that is used for real-time monitor video to compare with the file video quality be high-resolution and high definition, this has just improved the accuracy of video content analysis greatly.
(3) high unity of search criteria: follow the SVAC coding standard fully, simultaneously also traffic object and incident have been carried out unified coding, this just can carry out unified retrieval process to the compression traffic video of the SVAC standard of following of any different regions.
Description of drawings
Fig. 1 is that the present invention is a kind of based on standard mark and the traffic video monitoring system sketch map of retrieving fast;
Fig. 2 is a motion camera lens sketch map;
Fig. 3 is the key frame location drawing;
Fig. 4 is according to area identification flow chart in relevant image of traffic events or traffic characteristics of objects coded query and the image;
Fig. 5 is a flow chart of searching regional details in the image;
Fig. 6 retrieves image and flow for displaying figure.
Specific embodiment
Do explanation in further detail below in conjunction with the accompanying drawing and the embodiment of the invention.
With reference to Fig. 1; A kind of based on standard mark and the traffic video monitoring system of retrieving fast; Comprise traffic monitoring video capture module and video image content analysis module, also comprise and obtain traffic video key frame module, monitoring growth data coding module and to the code stream retrieval module, wherein:
Acting as of video image content analysis module extracts classifiable traffic object and traffic events from key frame;
Obtaining will there be incident in acting as of traffic video key frame module from the motion camera lens image setting is key frame, transmits traffic events and related object;
The monitoring growth data that act as of monitoring growth data coding module is expanded; Satisfy grammatical representation to the traffic object; Monitoring growth data unit is distinguished through extension_id; Get the extension_id value and represent the monitored object extension syntax for 0x6, beginning to the semanteme of reserve_bits from extension_id is consistent with other semantemes of monitoring the same syntax of figs element of growth data unit, and the semanteme of loop grammar is for finding each object from each zone; And from region_object_id, get access to the detailed features information of object; The implication of syntax element value is by application itself decision, and the region_object_id of traffic object is defined, and through the SVAC standard content after the expansion traffic object and traffic events encoded;
To acting as of code stream retrieval module according to the known SVAC code stream and the feature coding of traffic object or traffic events; From the monitoring growth data unit of code stream, find the picture position at traffic object or traffic events place and the position that belongs to zone in the image; Note the concrete parameter of picture position The corresponding area; From the vedio data of coding, find view data and decoding and displaying, mark corresponding area-of-interest simultaneously.
The present invention also can realize in the following manner; Said key frame information is directly from the video image content analysis module; Comprised detected traffic object or traffic events simultaneously, for incident, SVAC has the monitor event extension syntax structure to incident: event_extension; Region_event_id presentation of events characteristic is wherein carried out the coding standard definition with region_event_id to the traffic video business.
Further preferred, before looking for key frame, earlier the motion camera lens is classified according to the vehicle complexity wherein.
Can know that from Fig. 1 native system has comprised traffic monitoring video capture, video image content analysis, obtains the traffic video key frame, retrieved five functional according to SVAC standard code video with to the SVAC compressed bit stream.Wherein, Traffic monitoring video capture and video image content analysis provide necessary interface data as known functional module; And obtain the monitoring growth data coded portion in traffic video key frame, the SVAC coding and be core technology link of the present invention to the realization of code stream retrieving portion, will do detailed introduction below.
In monitor video; Two types of important informations that people are concerned about most are object and incident; Obviously for the traffic monitoring video; Be exactly traffic object and traffic events, people search according to object and incident, are " Santana of a white " or " car to car impact incident " such as search condition.So an important job is exactly to find the object of care and incident, follows the SVAC standard again and encodes.We first talk about incident; In general incident is not present in each frame of video of catching, and in the middle of the process of whole monitoring, quantity also is limited; It is by video image content analysis module result who produces that analyzes in monitoring in real time; After analyzing the traffic events that has defined, can give the SVAC coding module the relevant object of frame of video, event type and incident of the incident of generation and handle, concrete processing procedure part after a while has detailed introduction.We then say object now, and object is different from incident, and it possibly be present in each frame of video of catching; If we carry out the analysis of object to each two field picture and obtain, this bring huge workload can for the analysis of image content module, and can't guarantee the real-time handled; So we will utilize the characteristics of monitor video and road traffic; Find out the frame of video (we are referred to as key frame) that need obtain object and carry out the analysis of object and obtain, compare with all frame of video, quantity of key frames has just been lacked a lot; No matter be before coding the object analysis stage or the coding after retrieval phase, this all can bring very big speed improvement.Below just describe the technic relization scheme that obtains the traffic video key frame in detail.
Obtain the traffic video key frame: for the traffic monitoring video, in certain long time, background all is changeless, and we can think that background fixes here.And another characteristics of traffic monitoring are exactly to have no the traffic object to occur in often can be for some time, have only static background to show.Here, we do to give a definition, and all frame of video that have motion traffic object between the double static background frame of video are referred to as a motion camera lens, and are as shown in Figure 2.
Can see that from Fig. 2 n frame and n+61 frame are the static background frames that has no the motion object, there is the motion object in the n+1 frame to the n+60 frame, and these 60 continuous frames are exactly a motion camera lens.The work that we need do finds a most important two field picture as key frame from the motion camera lens exactly; Before looking for key frame, we classify 1 with the motion camera lens according to vehicle complexity therebetween earlier) the simple motion camera lens: in whole camera lens; Have only a car to get in the start frame position; Fade out in the end frame position, the frame of head or the tailstock proximal most position of picking up the car this moment is a key frame, because the most crucial information of vehicle is license plate number; Be license plate number the most clearly the time in proximal most position, also can see whole vehicle body information simultaneously.As shown in Figure 3.
If many cars are arranged; Require the time of many car turnover camera lenses to be consistent basically; Divide two kinds of situation here again, the one, many cars are equidirectional, and then processing is consistent with the key frame processing of a car above-mentioned; The 2nd, there is reciprocal car, the centre position of then getting the motion camera lens is a key frame.2) compound movement camera lens slightly: exist many cars successively to get into start frame in chronological order continuously; (desirable 3-4 second in short time interval; Can adjust according to practical business) camera lens all fades out; Can select 2-3 key frame, make all key frames can cover all information of vehicles of camera lens, the selection of key frame simultaneously be clear with most of car plates in the image be standard.3) compound movement camera lens: the motion object is many and complicated in the camera lens, and perhaps the priority of many vehicle commander's times is come in and gone out continuously, causes the frame number of motion camera lens too much, then obtains the key frame of camera lens this moment according to user configured interval information.
After obtaining key frame, through interface key frame information is passed to the video image content analysis module, by this module the traffic object analysis is come out, the monitoring growth data coded portion that passes in the SVAC coding is handled.
Monitoring growth data coding based on expansion SVAC standard: behind the traffic object that gets access to key frame, need encode to it according to the syntactic information of SVAC.But all syntactic structures of the monitoring growth data in the current standard all can't effectively satisfy the coding of traffic object; Analyze as follows: according to the 5.2.3.8 monitoring growth data unit grammer part of SVAC standard document; For video information; The area-of-interest extension syntax is arranged, monitor event extension syntax, totally four kinds of monitoring alarm extension syntax and absolute time information extension syntax; We do not consider monitoring alarm extension syntax and absolute time information extension syntax here; The monitor event extension syntax is primarily aimed at the coding of monitor event, so under situation about the monitoring syntactic information not being expanded, can only usability region-of-interest extension syntax express the traffic object.Its syntactic structure is as follows:
Can know do not have syntactic element can effectively represent the information of traffic object to the explanation of syntactic element through standard 5.2.4.10.2 part,, satisfy grammatical representation the traffic object so need carry out certain expansion to the monitoring growth data.Describe and to know according to standard 5.2.4.10.1; Monitoring growth data unit is distinguished through extension_id; Used 0x1-0x5 totally five numbers at present, we get the extension_id value and represent the monitored object extension syntax for 0x6, and its syntactic structure is as follows:
Semantic interpretation to newly-increased syntactic structure is following: beginning to the semanteme of reserve_bits from extension_id is consistent with other semantemes of monitoring the same syntax of figs element of growth data unit.The semanteme of following loop grammar is for finding each object from each zone; And from region_object_id, get access to the detailed features information of object; The implication of this syntax element value is determined by application itself; So in the present invention, we have carried out to give a definition the region_object_id of traffic object, and hope can become the SVAC standard pin to the professional part of traffic monitoring.Specifically as shown in table 1.
Table 1
U (n) expression needs the unsigned number of n position to encode.So the code length of whole region_object_id is 2+4+6+3+41=56bits.
Can know according to top analysis; Key frame information also might be directly from the video image content analysis module; Comprised detected traffic events and relevant object simultaneously, the syntactic structure of object is still as above-mentioned, for incident; SVAC has the monitor event extension syntax structure to incident: event_extension; Region_event_id presentation of events characteristic wherein, in order to satisfy the retrieval service of traffic monitoring video, the present invention carries out certain coding standard definition with region_event_id to the traffic video business here.
Extension syntax definition above having had; We are when adopting SVAC standard compression coding to the traffic monitoring video; Just can accurately the traffic events of key frame or the feature description of traffic object be written in the code stream, in the middle of decode procedure, need only so and just can find events corresponding or object fast according to syntactic structure.
Retrieving in the SVAC code stream: the first step of at first retrieving is from the monitoring growth data unit of code stream, to find the picture position at object or incident place and belong to position regional in the image (promptly to be present in which area-of-interest in the image according to known SVAC code stream and the feature coding of traffic object or traffic events (definition of coding basic format such as above-mentioned region_event_id and region_object_id is described); Because possibly there be n the area-of-interest of depositing object in the image), as shown in Figure 4.The syntactic structure of nal_unit is referring to SVAC standard 5.2.3.1 part, and semantic description is referring to the 5.2.4.2 part.The syntactic structure of monitoring growth data unit is referring to the SVAC standard.5.2.3.8 part, semantic description is referring to the 5.2.4.10 part.See " based on the monitoring growth data coding of expansion SVAC standard " part of this document for the syntax and semantics of the object_extension that the present invention expanded.This flow process can be stored in picture position that finds and corresponding regional location among the list data structure FoundPicRegionList; Utilize these data in flow process " is searched regional details in the image ", to find and to characterize regional concrete parameter; Comprise the upper left point coordinates (Left of zone in image; Top) and wide height (Width, Height), as shown in Figure 5.According to searching the back result FoundPicRegionList data are upgraded; Note the concrete parameter of picture position The corresponding area; From the vedio data of coding, find view data and decoding and displaying according to upgrading the back data then; Mark corresponding area-of-interest simultaneously, as shown in Figure 6.
Efficiency analysis: whole retrieving is main with the document flow Search and Orientation of SVAC coding mainly, and this search procedure is very fast.Because object and incident all are from key frame, generally our key frame is set to the I frame, can direct decoding, and need not decodes again needs other frames of reference.
Claims (3)
1. one kind based on the standard mark and the quick traffic video monitoring system of retrieval; Comprise traffic monitoring video capture module and video image content analysis module; It is characterized in that, also comprise and obtain traffic video key frame module, monitoring growth data coding module and to the code stream retrieval module, wherein:
Acting as of video image content analysis module extracts classifiable traffic object and traffic events from key frame;
Obtaining will there be incident in acting as of traffic video key frame module from the motion camera lens image setting is key frame, transmits traffic events and related object;
The monitoring growth data that act as of monitoring growth data coding module is expanded; Satisfy grammatical representation to the traffic object; Monitoring growth data unit is distinguished through extension_id; Get the extension_id value and represent the monitored object extension syntax for 0x6, beginning to the semanteme of reserve_bits from extension_id is consistent with other semantemes of monitoring the same syntax of figs element of growth data unit, and the semanteme of loop grammar is for finding each object from each zone; And from region_object_id, get access to the detailed features information of object; The implication of syntax element value is by application itself decision, and the region_object_id of traffic object is defined, and through the SVAC standard content after the expansion traffic object and traffic events encoded;
To acting as of code stream retrieval module according to the known SVAC code stream and the feature coding of traffic object or traffic events; From the monitoring growth data unit of code stream, find the picture position at traffic object or traffic events place and the position that belongs to zone in the image; Note the concrete parameter of picture position The corresponding area; From the vedio data of coding, find view data and decoding and displaying, mark corresponding area-of-interest simultaneously.
2. according to claim 1 based on standard mark and the traffic video monitoring system of retrieving fast; It is characterized in that; Said key frame information is directly from the video image content analysis module; Comprised detected traffic object or traffic events simultaneously, for incident, SVAC has the monitor event extension syntax structure to incident: event_extension; Region_event_id presentation of events characteristic is wherein carried out the coding standard definition with region_event_id to the traffic video business.
3. the traffic video monitoring system based on standard mark and quick retrieval according to claim 1 is characterized in that, before looking for key frame, earlier the motion camera lens is classified according to the vehicle complexity wherein.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100560220A CN102665064A (en) | 2012-03-01 | 2012-03-01 | A traffic video monitoring system based on standard labeling and quick search |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2012100560220A CN102665064A (en) | 2012-03-01 | 2012-03-01 | A traffic video monitoring system based on standard labeling and quick search |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102665064A true CN102665064A (en) | 2012-09-12 |
Family
ID=46774463
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2012100560220A Pending CN102665064A (en) | 2012-03-01 | 2012-03-01 | A traffic video monitoring system based on standard labeling and quick search |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102665064A (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103268702A (en) * | 2013-05-03 | 2013-08-28 | 福建工程学院 | Method for obtaining evidence of illegal occupying of non-bus vehicles on bus lane |
CN103412859A (en) * | 2012-10-11 | 2013-11-27 | 华迪计算机集团有限公司 | Method and device for rapidly searching for enormous videos based on media asset management system |
CN104504732A (en) * | 2014-12-25 | 2015-04-08 | 合肥寰景信息技术有限公司 | Video content retrieval method based on key frame extraction |
CN105450978A (en) * | 2014-06-24 | 2016-03-30 | 杭州海康威视数字技术股份有限公司 | Method and device for achieving structural description in video monitoring system |
CN106851204A (en) * | 2017-02-17 | 2017-06-13 | 深圳市中博睿存信息技术有限公司 | The method and apparatus that video data is processed based on SVAC |
CN111898416A (en) * | 2020-06-17 | 2020-11-06 | 绍兴埃瓦科技有限公司 | Video stream processing method and device, computer equipment and storage medium |
CN113840160A (en) * | 2021-09-29 | 2021-12-24 | 重庆紫光华山智安科技有限公司 | Event data transmission method, system, electronic equipment and readable storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101547351A (en) * | 2008-03-24 | 2009-09-30 | 展讯通信(上海)有限公司 | Method for generating and processing video data stream and equipment thereof |
CN101778260A (en) * | 2009-12-29 | 2010-07-14 | 公安部第三研究所 | Method and system for monitoring and managing videos on basis of structured description |
CN101902617A (en) * | 2010-06-11 | 2010-12-01 | 公安部第三研究所 | Device and method for realizing video structural description by using DSP and FPGA |
CN102207966A (en) * | 2011-06-01 | 2011-10-05 | 华南理工大学 | Video content quick retrieving method based on object tag |
-
2012
- 2012-03-01 CN CN2012100560220A patent/CN102665064A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101547351A (en) * | 2008-03-24 | 2009-09-30 | 展讯通信(上海)有限公司 | Method for generating and processing video data stream and equipment thereof |
CN101778260A (en) * | 2009-12-29 | 2010-07-14 | 公安部第三研究所 | Method and system for monitoring and managing videos on basis of structured description |
CN101902617A (en) * | 2010-06-11 | 2010-12-01 | 公安部第三研究所 | Device and method for realizing video structural description by using DSP and FPGA |
CN102207966A (en) * | 2011-06-01 | 2011-10-05 | 华南理工大学 | Video content quick retrieving method based on object tag |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103412859A (en) * | 2012-10-11 | 2013-11-27 | 华迪计算机集团有限公司 | Method and device for rapidly searching for enormous videos based on media asset management system |
CN103412859B (en) * | 2012-10-11 | 2016-09-14 | 华迪计算机集团有限公司 | Massive video method for quickly retrieving based on media asset management system and device |
CN103268702A (en) * | 2013-05-03 | 2013-08-28 | 福建工程学院 | Method for obtaining evidence of illegal occupying of non-bus vehicles on bus lane |
CN103268702B (en) * | 2013-05-03 | 2015-09-23 | 福建工程学院 | A kind of non-bus breaks rules and regulations to take the evidence collecting method of bus special lane |
CN105450978A (en) * | 2014-06-24 | 2016-03-30 | 杭州海康威视数字技术股份有限公司 | Method and device for achieving structural description in video monitoring system |
CN104504732A (en) * | 2014-12-25 | 2015-04-08 | 合肥寰景信息技术有限公司 | Video content retrieval method based on key frame extraction |
CN106851204A (en) * | 2017-02-17 | 2017-06-13 | 深圳市中博睿存信息技术有限公司 | The method and apparatus that video data is processed based on SVAC |
CN106851204B (en) * | 2017-02-17 | 2020-04-07 | 北京同有飞骥科技股份有限公司 | Method and device for processing video data based on SVAC |
CN111898416A (en) * | 2020-06-17 | 2020-11-06 | 绍兴埃瓦科技有限公司 | Video stream processing method and device, computer equipment and storage medium |
CN113840160A (en) * | 2021-09-29 | 2021-12-24 | 重庆紫光华山智安科技有限公司 | Event data transmission method, system, electronic equipment and readable storage medium |
CN113840160B (en) * | 2021-09-29 | 2023-09-29 | 重庆紫光华山智安科技有限公司 | Event data transmission method, system, electronic device and readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102665064A (en) | A traffic video monitoring system based on standard labeling and quick search | |
CN102819528B (en) | The method and apparatus generating video frequency abstract | |
Simoens et al. | Scalable crowd-sourcing of video from mobile devices | |
US9602738B2 (en) | Automatic event detection, text generation, and use thereof | |
Hampapur et al. | Virage video engine | |
CN101778260B (en) | Method and system for monitoring and managing videos on basis of structured description | |
US9740940B2 (en) | Event triggered location based participatory surveillance | |
WO2016119528A1 (en) | Intelligent processing method and system for video data | |
US9436692B1 (en) | Large scale video analytics architecture | |
CN100452871C (en) | Video analysis, archiving and alerting methods and apparatus for a video surveillance system | |
CN101631237A (en) | Video monitoring data storing and managing system | |
JP2018148560A (en) | Subsumption architecture for processing fragments of video stream | |
CN103347167A (en) | Surveillance video content description method based on fragments | |
CN102982311A (en) | Vehicle video characteristic extraction system and vehicle video characteristic extraction method based on video structure description | |
CN103268528A (en) | Intelligent skynet video resource analyzing system | |
WO2011127859A2 (en) | Method for processing video data and method and apparatus for displaying video images | |
CN105450978A (en) | Method and device for achieving structural description in video monitoring system | |
CN103412859A (en) | Method and device for rapidly searching for enormous videos based on media asset management system | |
KR20080093847A (en) | A integrated file format structure with multi-video data and meta data, and the resulting multi-video management system and methods | |
CN104283729A (en) | Kinescope recording system and working method thereof | |
CN111090773A (en) | Digital retina architecture and software architecture method and system | |
CN112804188B (en) | Scalable vision computing system | |
KR101519973B1 (en) | System and Method for Managing Integrated Image of Vehicle Blackbox | |
CN106878676A (en) | A kind of storage method for intelligent monitoring video data | |
Xu et al. | Automated pedestrian safety analysis using data from traffic monitoring cameras |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C12 | Rejection of a patent application after its publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120912 |