CN101840422A - Intelligent video retrieval system and method based on target characteristic and alarm behavior - Google Patents
Intelligent video retrieval system and method based on target characteristic and alarm behavior Download PDFInfo
- Publication number
- CN101840422A CN101840422A CN 201010145468 CN201010145468A CN101840422A CN 101840422 A CN101840422 A CN 101840422A CN 201010145468 CN201010145468 CN 201010145468 CN 201010145468 A CN201010145468 A CN 201010145468A CN 101840422 A CN101840422 A CN 101840422A
- Authority
- CN
- China
- Prior art keywords
- video
- retrieval
- target
- user
- feature
- 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
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
An intelligent video retrieval system and method based on target characteristic and alarm behavior relate to an intelligent video retrieval system and method. The system comprises a trajectory tracking module, a feature extraction module, a feature storage module, a search engine module and a retrieval terminal, wherein the trajectory tracking module extracts the motion trajectory and alarm behavior of a target input in the video; the feature extraction module extracts the features of the input image such as color, texture, shape and category; the feature storage module stores the motion trajectory, the alarm behavior, the target characteristic and the related information of the video in a feature database; the search engine module analyzes the retrieval conditions input by a user, performs video retrieval based on characteristic and behavior in the database and returns the video clip satisfying the conditions; and the retrieval terminal, namely client software receives the retrieval conditions input by the user and displays the retrieval result after retrieval. Compared with the prior art, by using the retrieval system, the user can customize retrieval conditions more accurately, video retrieval based on target characteristic and alarm behavior can be performed; and the retrieval result of the features generated by real-time analysis can be fast obtained.
Description
Technical field
The present invention relates to a kind of intelligent video retrieval system and method, relate in particular to a kind of intelligent video retrieval system and method that fully utilizes objects in video feature and warning behavior.
Background technology
Video monitoring system has been stored the video data of magnanimity, in present video monitoring management platform, generally is based on video camera installation site or IP address and binding time, and these videos are inquired about and playback.But for some application-specific, traditional inquiry mode is powerless, searches during such as criminal investigation, and does not know video camera installation site and concrete shooting time, and just knows some features of suspect; Stolen such as a car again, from several days video, locate its stolen time; Again such as thinking that fast browsing passes in and out the people and the vehicle at certain gate.Along with the construction of large-scale safety defense monitoring systems such as " safe cities ", also increasing to the maintenance of magnanimity video, more and more stronger to the demand of quick, intelligent retrieval.
Currently a lot of intelligent video analysis device products occurred, in supervisory system, done behavioural analysis and Realtime Alerts, but also do not have at historical video video frequency searching to be made in the warning behavior of appointment specially; The more current video frequency searching product that content-based (being various characteristics of image) are also arranged is analyzed retrieval to film or news camera lens.These products and academic research provide technical conditions for the comprehensive intelligent retrieval of the magnanimity video of realization supervisory system.
Summary of the invention
Technical matters: technical matters to be solved by this invention is: overcome the deficiency of existing video frequency searching mode, a kind of intelligent video retrieval system and method that fully utilizes target signature and warning behavior is provided.
Technical scheme: the intelligent video retrieval system of based target feature of the present invention and warning behavior is the intelligent video retrieval system of the warning behavior of the feature of moving target and generation in the comprehensive utilization video, and it comprises:
Track following module: the movement locus and the warning behavior of extracting target in the input video;
Characteristic extracting module: extract the feature of input picture, comprise color, texture, shape and classification;
Characteristic storage module: movement locus, warning behavior, target signature and video related information are deposited in property data base;
Search engine module: resolve the search condition of user's input, from database, carry out video frequency searching, return the video segment that satisfies condition based on feature and behavior;
Searching terminal: i.e. client software, receive the search condition of user's input, the retrieval back shows result for retrieval.
Described characteristic storage module, motion track information comprise the image coordinate and the place frame number of size, speed, direction and the track of target at regular intervals; Whether the warning behavioural information comprises behavior type and takes place; Target signature comprises color, texture, shape, all represents with integer vectors; The behaviour of target classification, vehicle, animal or other are represented with corresponding English; Above information stores is to the XML file or directly be stored in database.
Described search engine module comprises following function:
1). the characteristics combination of the text description of selecting according to the user is compared at property data base and is searched, and returns matched record;
2). according to image or the video interception that the user selects, extract proper vector, promptly extract the color in the input inquiry image, texture, and shape facility vector, distance and weighting ordering between compute vector one by one in property data base;
3). type of alarm and the corresponding rule selected according to the user, mate calculating one by one with track in the property data base, extract satisfy rule track as the warning behavior;
4). integrating step 1), step 2) and step 3) in the result that obtains carry out aggregative weighted and ordering.
Described searching terminal, the user therefrom imports search condition, comprising: spot for photography, shooting time, target signature, type, warning behavior type and criterion thereof, condition are one of them or its combination, and can specify the weight of various features.The input of target signature wherein has following mode; (1) feature of text description, the feature that (2) user's sketch is described, (3) sample image or video are as target signature.
The intelligent video search method of based target feature and warning behavior may further comprise the steps:
1). in the time of supervisory control system running, do track following module and feature extraction, real-time target trajectory, warning behavior and target signature are deposited in property data base;
2). the user imports search condition from searching terminal, and target signature is a text description, returns result for retrieval by search engine, is presented at searching terminal.
6. the intelligent video search method of based target feature as claimed in claim 5 and warning behavior is characterized in that, can also carry out according to following steps:
1). the user imports search condition from searching terminal, imports the snapshot picture of a width of cloth reference picture or video, and template image as target signature, is imported the warning rule of conduct as required;
2). the user specifies one or more video files from searching terminal, analyzes these video files, does track following and feature extraction, and the target trajectory that obtains, warning behavior and target signature are deposited in property data base;
3). the user imports search condition from searching terminal, and search engine returns result for retrieval and is presented at searching terminal.
Beneficial effect: this searching system adopts advanced target tracking algorism, feature extraction algorithm, advanced person's database structure and user interface; Compared with prior art, use this searching system, the user can very accurately customize search condition, can make the based target feature and based on the video frequency searching of warning behavior; Can obtain result for retrieval very fast to the feature that real-time analysis produced, and system log (SYSLOG) the movement locus of target, therefore can be according to the coupling fast detecting multiclass warning behavior of track with the health care rule; The carrying cost of property data base is very low.
Description of drawings
Fig. 1 is a system chart of the present invention.
Fig. 2 is the process flow diagram of the embodiment of the invention one.
Fig. 3 is the process flow diagram of the embodiment of the invention two.
Embodiment
The present invention is described in further detail below in conjunction with drawings and Examples:
(1) track following module is analyzed input video, extracts the movement locus of target, if defined the behavior alarm rule, then can produce the warning behavior when movement locus triggering behavior rule.
(2) characteristic extracting module is analyzed input picture, extracts the whole of image or from the feature of the target area that step (1) obtains, comprises color, texture, shape and classification.
(3) characteristic storage module, the movement locus and the warning behavior of the extraction of track following module, and color, shape and the textural characteristics of the target of characteristic extracting module extraction,, together with camera location and shooting time, deposit property data base in, can also can directly deposit database in the form storage of XML file.
(4) search engine module is resolved the search condition that the user imports, and carries out the video frequency searching based on feature and behavior from database, returns the video segment that satisfies condition, by sequencing of similarity.Calculation of similarity degree wherein, feature for text description, value is 1 (coupling) or 0 (not matching), for the sample characteristics of image, value is the Euclidean distance between normalized vector, then according to the crossing judgement of the rule of target trajectory and definition, value is 1 or 0 to goal behavior, at last all similarities is pressed the weights weighted sum.
(5) searching terminal, promptly client software receives the search condition that the user imports, and the retrieval back shows result for retrieval.
Above-mentioned (5) searching terminal, the user therefrom imports search condition, comprise: spot for photography, shooting time, target signature (color, shape, texture), target type (people, vehicle), warning behavior type (more line, Yue Qu, drive in the wrong direction, object is left over, specified object occurs, specified object disappears) and criterion (mixing line, zone), condition is one of them or its combination, and can specify the weight of various features.
The input of target signature wherein has following mode;
(1) feature of text description, as selected color characteristic then need be appointed as one of following color: red, green, blue, Huang, green grass or young crops, black, white, silver grey etc.; As the selected shape feature, then need be appointed as one of following shape: square, rectangle, triangle, circle etc.
(2) feature of user's sketch description, such as, select a kind of color, sketch to delineate a polygonal profile, textured pattern of sketch picture from palette.
(3) input template image is opened sample image or video, extracts the color, shape, textural characteristics of image or video interception as the implicit expression target signature by searching system.
The searching terminal calling search engine, obtain result for retrieval, show, and show the relevant information of place video with the thumbnail form, comprise spot for photography, shooting time, frame number of living in, similarity marking etc., double-click each thumbnail and can play the video segment before and after the corresponding frame number in the corresponding video.
The intelligent video search method of the warning behavior of the feature of moving target and generation in the comprehensive utilization video may further comprise the steps:
(1) video is done track following, obtain the movement locus of each moving target, then judge whether to have triggered warning if defined alarm rule;
(2) motion target area is done feature extraction, obtain color, texture and the shape facility of target;
(3) Moving Target, warning, characteristic information are deposited in database;
(4) target and the warning behavior that meets the demands from data base querying according to initial conditions.
Target tracking algorism that step (1) track following is used and behavioural analysis algorithm:
(1) movement locus: adopt method to obtain based on the extraction of Harris angle point, SIFT characteristic matching, tracking back cluster, perhaps obtain based on extracting profile and follow the tracks of after Gaussian Background model, the extraction background difference, track algorithm can be carried out according to time needs frame-skipping, the image coordinate of size, speed, direction and the track of a target of per 0.5 second record, corresponding information such as frame number.
(2) behavioural analysis: the movement locus that obtains based on target following, according to movement locus with set and judge intersecting of criterion: intersect the line behavior more that then takes place, track as the track and the line of stumbling and intersect with the zone and the retrograde behavior of the opposite then generation of behavior, direction of motion and assigned direction then takes place to distinguish more, rest on a place for a long time as if track and then leave over for object; Specified object occurs and specified object disappears, and needs to judge according to object features comparison (Harris corners Matching, or SIFT characteristic matching, or template matches).
The used algorithm of step (2) feature extraction:
(1) color characteristic: frame of video or picture decoding are colored bitmap, and from RGB (red, green, blue) color space conversion to HSV (colourity, saturation degree, brightness) color space, set up histogram as proper vector.
(2) shape facility: adopt the edge histogram descriptor (Edge HistogramDescriptor) in the MPEG-7 standard to realize as proper vector.
(3) textural characteristics: curvature scale space (Curvature Scale Space) in the employing MPEG-7 standard or partial binary pattern (Local Binary Pattern) are as proper vector.
(4) target classification: sort out according to shape facility, the ratio of width to height, the textural characteristics of target and to be people, vehicle, animal or other; Also can learn identification according to prior model with histogram of gradients (Histogram of Gradient) features training.
Specific characteristic is described and the warning rule of conduct, retrieves in the video that supervisory system is recorded, and intelligent search method of the present invention may further comprise the steps:
(1) supervisory control system running the time, does track following module and feature extraction, real-time target trajectory, warning behavior and target signature are deposited in property data base.
(2) user imports search condition from searching terminal, and target signature is a text description, returns result for retrieval by search engine, is presented at searching terminal.
If by input sample image implicit expression intended target feature, or only retrieve in the designated file, the present invention can also descend step to carry out:
(1) user imports search condition from searching terminal, imports the snapshot picture of a width of cloth reference picture or video, and template image as target signature, is imported the warning rule of conduct as required.
(2) user specifies one or more video files from searching terminal, analyzes these video files, does track following and feature extraction, and the target trajectory that obtains, warning behavior and target signature are deposited in property data base.
(3) user imports search condition from searching terminal, and search engine returns result for retrieval and is presented at searching terminal.
Fig. 1 is a system chart of the present invention, with the property data base is the center, video flowing is sent into target trajectory and warning message the characteristic storage module, simultaneously characteristic extracting module is sent in the target area by the track following module, the target signature that obtains is also sent into the characteristic storage module, and these information gather and are stored in property data base; The user is by searching terminal (client software) input inquiry condition, and the automatic calling search engine module of searching terminal is to the characteristic library inquiry, and Query Result returns to searching terminal by search engine module and shows.
Wherein querying condition includes but not limited to: the screenshotss that target signature is described (color, shape, texture), sample image or sample video as template (extracting its color, shape, texture, category feature automatically), shooting time, spot for photography, warning behavior type by system (more line, Yue Qu, drive in the wrong direction, object is left over, specified object occurs, specified object disappears) and rule of conduct (straight line or zone), the limit search scope of correspondence be one or more video files etc., but above search condition combination in any, and appointment weight separately.
Online generation when the generation of property data base can be taken by video camera also can generate from the video of the interim appointment of user, all is to obtain by calling track following module, characteristic extracting module and characteristic storage module.
Searching terminal software includes on the interface: target signature classification and the tabulation of feature description separately, shooting time tabulation, spot for photography are tabulated, the warning behavior is tabulated, draw straight line and draw regional instrument, selection sample image and show, select sample video, broadcast and screenshotss, specify in one or more video files, thumbnail demonstration result for retrieval, the double-click of wherein doing retrieval can play corresponding user interfaces such as video segment.
Embodiment one
The embodiment of the invention one process flow diagram as shown in Figure 2, the user retrieves the video segment that satisfies condition in the video of supervisory system, the retrieval carry out according to the following steps:
When (1) supervisory system was moved at ordinary times, the video source of video camera was done track following and feature extraction, and target trajectory, warning behavior and the target signature extracted have been deposited in property data base.
(2) user imports search condition from searching terminal, mainly is all kinds of feature descriptions and alarm rule.Pass through the red automobile of certain bar warning line such as retrieval, then target signature is set at redness, and the target classification is an automobile, and the warning behavior is line more, and draws straight line as mixing the line rule.If do not establish alarm rule, then be all red automobiles of retrieval; If do not establish target signature, has only alarm rule, then the All Alerts behavior of crossing warning line for retrieval arbitrary motion target.
(3) the searching terminal calling search engine obtains result for retrieval, show with the thumbnail form, and the relevant information of demonstration place video, comprise spot for photography, shooting time, frame number of living in, similarity marking etc., double-click thumbnail and can play the video segment before and after the corresponding frame number in the corresponding video.
Embodiment two
The embodiment of the invention two process flow diagrams as shown in Figure 2, supervisory system is operation not, or supervisory system do not do track following and feature extraction, perhaps the user is indifferent to the video data of supervisory system, is the property data base that does not have the user to need in a word.The user retrieves the video segment similar to specify image in the video of appointment, retrieval is carried out according to the following steps:
(1) user imports search condition from searching terminal, the target signature of this moment is not according to description, but opens piece image as template, makes screenshotss when perhaps opening a video playback to certain frame, at template image or screenshotss image setting area-of-interest, this area image becomes To Template; Searching terminal can be done feature extraction automatically to obtain target feature vector, and the user also can set characteristic type and the alarm rule of being concerned about, these conditions all can be sent into search engine automatically.Cross the warning behavior in this zone such as retrieving the target similar to the shape of specifying template image, the setting characteristic type is a shape, and the warning behavior is distinguished for getting over, and draws a polygonal region.If do not establish alarm rule, then be all moving targets similar of retrieval to the shape facility of template image; If do not establish characteristic type, have only alarm rule, then cross this regional All Alerts behavior for the retrieval target similar to the global feature of template image.
(2) user specifies in some video file by searching terminal and retrieves, this moment, searching terminal can be done track following and feature extraction automatically, these videos are analyzed, and target trajectory, warning behavior and the target signature extracted deposited in property data base, how much relevant the execution time in this step is with video content.
When (3) user begins to retrieve by searching terminal, obtain result for retrieval, be reflected on the interface of searching terminal by search engine.
The present invention can also have other implementation method, and the technical scheme that equal replacement of all employings or equivalent transformation form all drops within the scope of protection of present invention.
Claims (6)
1. the intelligent video retrieval system of based target feature and warning behavior is characterized in that, comprising:
Track following module: the movement locus and the warning behavior of extracting target in the input video;
Characteristic extracting module: extract the feature of input picture, comprise color, texture, shape and classification;
Characteristic storage module: movement locus, warning behavior, target signature and video related information are deposited in property data base;
Search engine module: resolve the search condition of user's input, from database, carry out video frequency searching, return the video segment that satisfies condition based on feature and behavior;
Searching terminal: i.e. client software, receive the search condition of user's input, the retrieval back shows result for retrieval.
2. the intelligent video retrieval system of based target feature as claimed in claim 1 and warning behavior, it is characterized in that: described characteristic storage module, motion track information comprise the image coordinate and the place frame number of size, speed, direction and the track of target at regular intervals; Whether the warning behavioural information comprises behavior type and takes place; Target signature comprises color, texture, shape, all represents with integer vectors; The behaviour of target classification, vehicle, animal or other are represented with corresponding English; Above information stores is to the XML file or directly be stored in database.
3. the intelligent video retrieval system of based target feature as claimed in claim 1 and warning behavior is characterized in that: described search engine module comprises following function:
1). the characteristics combination of the text description of selecting according to the user is compared at property data base and is searched, and returns matched record;
2). according to image or the video interception that the user selects, extract proper vector, promptly extract the color in the input inquiry image, texture, and shape facility vector, distance and weighting ordering between compute vector one by one in property data base;
3). type of alarm and the corresponding rule selected according to the user, mate calculating one by one with track in the property data base, extract satisfy rule track as the warning behavior;
4). integrating step 1), step 2) and step 3) in the result that obtains carry out aggregative weighted and ordering.
4. the intelligent video retrieval system of based target feature as claimed in claim 1 and warning behavior, it is characterized in that: described searching terminal, the user therefrom imports search condition, comprise: spot for photography, shooting time, target signature, type, warning behavior type and criterion thereof, condition is one of them or its combination, and can specify the weight of various features.The input of target signature wherein has following mode; (1) feature of text description, the feature that (2) user's sketch is described, (3) sample image or video are as target signature.
5. the intelligent video search method of based target feature and warning behavior is characterized in that this method may further comprise the steps:
1). in the time of supervisory control system running, do track following module and feature extraction, real-time target trajectory, warning behavior and target signature are deposited in property data base;
2). the user imports search condition from searching terminal, and target signature is a text description, returns result for retrieval by search engine, is presented at searching terminal.
6. the intelligent video search method of based target feature as claimed in claim 5 and warning behavior is characterized in that, can also carry out according to following steps:
1). the user imports search condition from searching terminal, imports the snapshot picture of a width of cloth reference picture or video, and template image as target signature, is imported the warning rule of conduct as required;
2). the user specifies one or more video files from searching terminal, analyzes these video files, does track following and feature extraction, and the target trajectory that obtains, warning behavior and target signature are deposited in property data base;
3). the user imports search condition from searching terminal, and search engine returns result for retrieval and is presented at searching terminal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010145468 CN101840422A (en) | 2010-04-09 | 2010-04-09 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 201010145468 CN101840422A (en) | 2010-04-09 | 2010-04-09 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN101840422A true CN101840422A (en) | 2010-09-22 |
Family
ID=42743795
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 201010145468 Pending CN101840422A (en) | 2010-04-09 | 2010-04-09 | Intelligent video retrieval system and method based on target characteristic and alarm behavior |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101840422A (en) |
Cited By (62)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419750A (en) * | 2010-09-27 | 2012-04-18 | 北京中星微电子有限公司 | Video retrieval method and system |
| CN102543124A (en) * | 2012-01-17 | 2012-07-04 | 中兴通讯股份有限公司 | System and method for providing value-added services based on radio frequency identification technology |
| CN102543125A (en) * | 2012-01-17 | 2012-07-04 | 中兴通讯股份有限公司 | Method and system for providing value-added service based on radio frequency identification technique |
| CN102663359A (en) * | 2012-03-30 | 2012-09-12 | 博康智能网络科技股份有限公司 | Method and system for pedestrian retrieval based on internet of things |
| CN102665071A (en) * | 2012-05-14 | 2012-09-12 | 安徽三联交通应用技术股份有限公司 | Intelligent processing and search method for social security video monitoring images |
| CN102819578A (en) * | 2012-07-24 | 2012-12-12 | 武汉大千信息技术有限公司 | Suspected target analyzing system and method by video investigation |
| CN102999622A (en) * | 2012-11-30 | 2013-03-27 | 杭州易尊数字科技有限公司 | Method for searching target in videos based on database |
| CN103020198A (en) * | 2012-11-30 | 2013-04-03 | 杭州易尊数字科技有限公司 | Method for searching target in video |
| CN103150375A (en) * | 2013-03-11 | 2013-06-12 | 浙江捷尚视觉科技有限公司 | Quick video retrieval system and quick video retrieval method for video detection |
| CN103198110A (en) * | 2013-03-28 | 2013-07-10 | 广州中国科学院软件应用技术研究所 | Method and system for rapid video data characteristic retrieval |
| CN103283226A (en) * | 2010-12-30 | 2013-09-04 | 派尔高公司 | Searching recorded video |
| CN103324682A (en) * | 2013-05-31 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Video searching method and device based on images |
| WO2013143465A1 (en) * | 2012-03-27 | 2013-10-03 | 华为技术有限公司 | Video query method, device and system |
| CN103366573A (en) * | 2013-07-10 | 2013-10-23 | 中兴智能交通（无锡）有限公司 | Vehicle running information tracking method and system based on cloud computing |
| CN103500230A (en) * | 2013-10-25 | 2014-01-08 | 苏州千视通信科技有限公司 | Video retrieval method based on sample image |
| CN103778159A (en) * | 2012-10-26 | 2014-05-07 | 苏州千视通信科技有限公司 | Video detection process based on video abstraction and video retrieval |
| CN103797494A (en) * | 2011-03-31 | 2014-05-14 | 维塔克公司 | Devices, systems, methods, and media for detecting, indexing, and comparing video signals from a video display in a background scene using a camera-enabled device |
| CN103870569A (en) * | 2014-03-13 | 2014-06-18 | 北方信息控制集团有限公司 | Colorful animal image retrieval method based on content and colorful animal image retrieval system based on content |
| CN103942337A (en) * | 2014-05-08 | 2014-07-23 | 北京航空航天大学 | Video search system based on image recognition and matching |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN104185032A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video identification method and system |
| CN104216938A (en) * | 2013-05-31 | 2014-12-17 | 三星Sds株式会社 | Video search apparatus and method |
| CN104539304A (en) * | 2014-11-28 | 2015-04-22 | 广东小天才科技有限公司 | Method, device and terminal for warning abnormal movement according to different places |
| CN104639897A (en) * | 2015-01-19 | 2015-05-20 | 南阳理工学院 | Distributed camera image processing method |
| CN104820711A (en) * | 2015-05-19 | 2015-08-05 | 深圳久凌软件技术有限公司 | Video retrieval method for figure target in complex scene |
| CN105049381A (en) * | 2015-07-31 | 2015-11-11 | 南京南瑞集团公司 | Method for testing real-time property of electric power multimedia communication system |
| CN105279898A (en) * | 2015-10-28 | 2016-01-27 | 小米科技有限责任公司 | Alarm method and device |
| CN105653690A (en) * | 2015-12-30 | 2016-06-08 | 武汉大学 | Video big data rapid searching method and system constrained by abnormal behavior early-warning information |
| CN105677694A (en) * | 2014-12-05 | 2016-06-15 | 韩华泰科株式会社 | Video recording apparatus supporting smart search and smart search method |
| CN106412715A (en) * | 2016-09-14 | 2017-02-15 | 华为软件技术有限公司 | Information retrieval method, terminal and server |
| US9615064B2 (en) | 2010-12-30 | 2017-04-04 | Pelco, Inc. | Tracking moving objects using a camera network |
| CN106557516A (en) * | 2015-09-29 | 2017-04-05 | 北京国双科技有限公司 | Data push method and device |
| CN106686403A (en) * | 2016-12-07 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Video preview generation method, device, server and system |
| CN107092636A (en) * | 2016-02-17 | 2017-08-25 | 南京三宝弘正视觉科技有限公司 | The retrieval device and method of CCTV images |
| CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技（深圳）有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
| CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
| CN107845103A (en) * | 2017-10-23 | 2018-03-27 | 广东美的制冷设备有限公司 | Alarm method, device and computer-readable recording medium based on texture information |
| CN107886709A (en) * | 2017-11-21 | 2018-04-06 | 北京华油信通科技有限公司 | Information of vehicles processing method and processing device |
| CN108052581A (en) * | 2017-12-08 | 2018-05-18 | 四川金英科技有限责任公司 | A kind of case video studies and judges device |
| CN108090146A (en) * | 2017-12-08 | 2018-05-29 | 四川金英科技有限责任公司 | A kind of case video analysis method and system |
| CN108090149A (en) * | 2017-12-08 | 2018-05-29 | 四川金英科技有限责任公司 | A kind of case video analysis method |
| CN108176049A (en) * | 2017-12-28 | 2018-06-19 | 珠海市君天电子科技有限公司 | A kind of information cuing method, device, terminal and computer readable storage medium |
| CN108256532A (en) * | 2018-01-10 | 2018-07-06 | 武汉斗鱼网络科技有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN108399261A (en) * | 2018-03-13 | 2018-08-14 | 成都蓉兴伟业科技有限公司 | A kind of case and video analysis method based on integration method |
| CN109190584A (en) * | 2018-09-18 | 2019-01-11 | 银河水滴科技（北京）有限公司 | A kind of portable video searching system |
| CN109359213A (en) * | 2018-08-27 | 2019-02-19 | 博康智能信息技术有限公司 | A kind of security protection video intelligent retrieval system and its search method |
| CN109408671A (en) * | 2018-07-23 | 2019-03-01 | 中国联合网络通信集团有限公司 | The searching method and its system of specific objective |
| CN109871783A (en) * | 2019-01-28 | 2019-06-11 | 武汉恩特拉信息技术有限公司 | A monitoring method and monitoring system based on video image |
| CN109871815A (en) * | 2019-02-26 | 2019-06-11 | 新华三技术有限公司 | A kind of method and device of query monitor information |
| WO2019129075A1 (en) * | 2017-12-27 | 2019-07-04 | 中兴通讯股份有限公司 | Video searching method and device and computer readable storage medium |
| CN110399525A (en) * | 2019-07-27 | 2019-11-01 | 广州伽利略网络科技有限公司 | A kind of people based on image recognition technology, object motion profile method for quickly retrieving |
| CN110555471A (en) * | 2019-08-26 | 2019-12-10 | 珠海格力电器股份有限公司 | Mobile terminal and target object searching method |
| CN111046209A (en) * | 2019-12-09 | 2020-04-21 | 中国科学院自动化研究所 | Image Clustering Retrieval System |
| CN111741325A (en) * | 2020-06-05 | 2020-10-02 | 咪咕视讯科技有限公司 | Video playback method, device, electronic device, and computer-readable storage medium |
| CN112019789A (en) * | 2019-05-31 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Video playback method and device |
| CN112040325A (en) * | 2020-11-02 | 2020-12-04 | 成都睿沿科技有限公司 | Video playing method and device, electronic equipment and storage medium |
| CN112231515A (en) * | 2020-10-28 | 2021-01-15 | 王志晓 | Mass surveillance video quick retrieval system and retrieval method |
| CN112382032A (en) * | 2020-11-13 | 2021-02-19 | 珠海大横琴科技发展有限公司 | Monitoring method and device, electronic equipment and storage medium |
| CN112866817A (en) * | 2021-01-06 | 2021-05-28 | 浙江大华技术股份有限公司 | Video playback method, device, electronic device and storage medium |
| CN113434573A (en) * | 2021-06-29 | 2021-09-24 | 中国科学院自动化研究所 | Multi-dimensional image retrieval system, method and equipment |
| CN113920489A (en) * | 2021-10-29 | 2022-01-11 | 广州文远知行科技有限公司 | Tracking method and device based on multi-model detection, vehicle and storage medium |
| CN119206586A (en) * | 2024-11-26 | 2024-12-27 | 杭州海康威视数字技术股份有限公司 | Target analysis method and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1635552A (en) * | 2004-12-17 | 2005-07-06 | 山东省科学院情报研究所 | Intelligent audio network system |
| US20050162515A1 (en) * | 2000-10-24 | 2005-07-28 | Objectvideo, Inc. | Video surveillance system |
| CN101281545A (en) * | 2008-05-30 | 2008-10-08 | 清华大学 | A 3D Model Retrieval Method Based on Multi-Feature Correlation Feedback |
| CN101587483A (en) * | 2009-07-10 | 2009-11-25 | 张丛喆 | Information storage/retrival method of video files based on MPEG-7 in monitoring system |
| CN101655860A (en) * | 2009-09-16 | 2010-02-24 | 北京中盾安全技术开发公司 | Video aided analytical method for criminal investigation and case detection and system |
-
2010
- 2010-04-09 CN CN 201010145468 patent/CN101840422A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050162515A1 (en) * | 2000-10-24 | 2005-07-28 | Objectvideo, Inc. | Video surveillance system |
| CN1635552A (en) * | 2004-12-17 | 2005-07-06 | 山东省科学院情报研究所 | Intelligent audio network system |
| CN101281545A (en) * | 2008-05-30 | 2008-10-08 | 清华大学 | A 3D Model Retrieval Method Based on Multi-Feature Correlation Feedback |
| CN101587483A (en) * | 2009-07-10 | 2009-11-25 | 张丛喆 | Information storage/retrival method of video files based on MPEG-7 in monitoring system |
| CN101655860A (en) * | 2009-09-16 | 2010-02-24 | 北京中盾安全技术开发公司 | Video aided analytical method for criminal investigation and case detection and system |
Cited By (84)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419750A (en) * | 2010-09-27 | 2012-04-18 | 北京中星微电子有限公司 | Video retrieval method and system |
| CN103283226B (en) * | 2010-12-30 | 2017-03-15 | 派尔高公司 | Produce method, video camera system and the processing system for video of the metadata associated with frame of video |
| CN103283226A (en) * | 2010-12-30 | 2013-09-04 | 派尔高公司 | Searching recorded video |
| US9615064B2 (en) | 2010-12-30 | 2017-04-04 | Pelco, Inc. | Tracking moving objects using a camera network |
| US9602870B2 (en) | 2011-03-31 | 2017-03-21 | Tvtak Ltd. | Devices, systems, methods, and media for detecting, indexing, and comparing video signals from a video display in a background scene using a camera-enabled device |
| CN103797494A (en) * | 2011-03-31 | 2014-05-14 | 维塔克公司 | Devices, systems, methods, and media for detecting, indexing, and comparing video signals from a video display in a background scene using a camera-enabled device |
| US9860593B2 (en) | 2011-03-31 | 2018-01-02 | Tvtak Ltd. | Devices, systems, methods, and media for detecting, indexing, and comparing video signals from a video display in a background scene using a camera-enabled device |
| CN102543124B (en) * | 2012-01-17 | 2015-09-16 | 中兴通讯股份有限公司 | A kind of system and method provided value added service based on video identification technology |
| WO2013107145A1 (en) * | 2012-01-17 | 2013-07-25 | 中兴通讯股份有限公司 | Video identification technology-based system and method for providing value-added service |
| CN102543125A (en) * | 2012-01-17 | 2012-07-04 | 中兴通讯股份有限公司 | Method and system for providing value-added service based on radio frequency identification technique |
| CN102543124A (en) * | 2012-01-17 | 2012-07-04 | 中兴通讯股份有限公司 | System and method for providing value-added services based on radio frequency identification technology |
| WO2013143465A1 (en) * | 2012-03-27 | 2013-10-03 | 华为技术有限公司 | Video query method, device and system |
| CN103365848A (en) * | 2012-03-27 | 2013-10-23 | 华为技术有限公司 | Method, device and system for inquiring videos |
| CN102663359A (en) * | 2012-03-30 | 2012-09-12 | 博康智能网络科技股份有限公司 | Method and system for pedestrian retrieval based on internet of things |
| CN102663359B (en) * | 2012-03-30 | 2014-04-09 | 博康智能网络科技股份有限公司 | Method and system for pedestrian retrieval based on internet of things |
| CN102665071A (en) * | 2012-05-14 | 2012-09-12 | 安徽三联交通应用技术股份有限公司 | Intelligent processing and search method for social security video monitoring images |
| CN102665071B (en) * | 2012-05-14 | 2014-04-09 | 安徽三联交通应用技术股份有限公司 | Intelligent processing and search method for social security video monitoring images |
| CN102819578A (en) * | 2012-07-24 | 2012-12-12 | 武汉大千信息技术有限公司 | Suspected target analyzing system and method by video investigation |
| CN102819578B (en) * | 2012-07-24 | 2015-01-21 | 武汉大千信息技术有限公司 | Suspected target analyzing system and method by video investigation |
| CN103778159A (en) * | 2012-10-26 | 2014-05-07 | 苏州千视通信科技有限公司 | Video detection process based on video abstraction and video retrieval |
| CN103020198A (en) * | 2012-11-30 | 2013-04-03 | 杭州易尊数字科技有限公司 | Method for searching target in video |
| CN102999622A (en) * | 2012-11-30 | 2013-03-27 | 杭州易尊数字科技有限公司 | Method for searching target in videos based on database |
| CN103150375A (en) * | 2013-03-11 | 2013-06-12 | 浙江捷尚视觉科技有限公司 | Quick video retrieval system and quick video retrieval method for video detection |
| CN103198110A (en) * | 2013-03-28 | 2013-07-10 | 广州中国科学院软件应用技术研究所 | Method and system for rapid video data characteristic retrieval |
| CN103324682B (en) * | 2013-05-31 | 2017-06-06 | 百度在线网络技术（北京）有限公司 | It is a kind of that the method and device of video is searched for based on picture |
| CN104216938A (en) * | 2013-05-31 | 2014-12-17 | 三星Sds株式会社 | Video search apparatus and method |
| CN103324682A (en) * | 2013-05-31 | 2013-09-25 | 百度在线网络技术（北京）有限公司 | Video searching method and device based on images |
| CN103366573A (en) * | 2013-07-10 | 2013-10-23 | 中兴智能交通（无锡）有限公司 | Vehicle running information tracking method and system based on cloud computing |
| CN103500230A (en) * | 2013-10-25 | 2014-01-08 | 苏州千视通信科技有限公司 | Video retrieval method based on sample image |
| CN104185032B (en) * | 2014-02-26 | 2018-05-11 | 无锡天脉聚源传媒科技有限公司 | A kind of video frequency identifying method and system |
| CN104185032A (en) * | 2014-02-26 | 2014-12-03 | 无锡天脉聚源传媒科技有限公司 | Video identification method and system |
| CN103870569B (en) * | 2014-03-13 | 2017-05-10 | 北方信息控制集团有限公司 | Colorful animal image retrieval method based on content and colorful animal image retrieval system based on content |
| CN103870569A (en) * | 2014-03-13 | 2014-06-18 | 北方信息控制集团有限公司 | Colorful animal image retrieval method based on content and colorful animal image retrieval system based on content |
| CN103955494B (en) * | 2014-04-18 | 2017-11-03 | 大唐联智信息技术有限公司 | Searching method, device and the terminal of destination object |
| CN103955494A (en) * | 2014-04-18 | 2014-07-30 | 大唐联智信息技术有限公司 | Searching method and device of target object and terminal |
| CN103942337B (en) * | 2014-05-08 | 2017-08-18 | 北京航空航天大学 | A Video Search System Based on Image Recognition and Matching |
| CN103942337A (en) * | 2014-05-08 | 2014-07-23 | 北京航空航天大学 | Video search system based on image recognition and matching |
| CN104539304A (en) * | 2014-11-28 | 2015-04-22 | 广东小天才科技有限公司 | Method, device and terminal for warning abnormal movement according to different places |
| CN105677694A (en) * | 2014-12-05 | 2016-06-15 | 韩华泰科株式会社 | Video recording apparatus supporting smart search and smart search method |
| CN104639897A (en) * | 2015-01-19 | 2015-05-20 | 南阳理工学院 | Distributed camera image processing method |
| CN104639897B (en) * | 2015-01-19 | 2016-04-20 | 南阳理工学院 | A Distributed Camera Image Processing Method |
| CN104820711A (en) * | 2015-05-19 | 2015-08-05 | 深圳久凌软件技术有限公司 | Video retrieval method for figure target in complex scene |
| CN105049381A (en) * | 2015-07-31 | 2015-11-11 | 南京南瑞集团公司 | Method for testing real-time property of electric power multimedia communication system |
| CN105049381B (en) * | 2015-07-31 | 2018-03-02 | 南京南瑞集团公司 | A kind of method of testing of the real-time of electric power multimedia communications system |
| CN106557516A (en) * | 2015-09-29 | 2017-04-05 | 北京国双科技有限公司 | Data push method and device |
| US9953506B2 (en) | 2015-10-28 | 2018-04-24 | Xiaomi Inc. | Alarming method and device |
| CN105279898A (en) * | 2015-10-28 | 2016-01-27 | 小米科技有限责任公司 | Alarm method and device |
| CN105653690B (en) * | 2015-12-30 | 2018-11-23 | 武汉大学 | The video big data method for quickly retrieving and system of abnormal behaviour warning information constraint |
| CN105653690A (en) * | 2015-12-30 | 2016-06-08 | 武汉大学 | Video big data rapid searching method and system constrained by abnormal behavior early-warning information |
| CN107092636A (en) * | 2016-02-17 | 2017-08-25 | 南京三宝弘正视觉科技有限公司 | The retrieval device and method of CCTV images |
| CN107315755A (en) * | 2016-04-27 | 2017-11-03 | 杭州海康威视数字技术股份有限公司 | The orbit generation method and device of query object |
| CN106412715A (en) * | 2016-09-14 | 2017-02-15 | 华为软件技术有限公司 | Information retrieval method, terminal and server |
| CN106686403A (en) * | 2016-12-07 | 2017-05-17 | 腾讯科技（深圳）有限公司 | Video preview generation method, device, server and system |
| CN107291910A (en) * | 2017-06-26 | 2017-10-24 | 图麟信息科技（深圳）有限公司 | A kind of video segment structuralized query method, device and electronic equipment |
| CN107845103A (en) * | 2017-10-23 | 2018-03-27 | 广东美的制冷设备有限公司 | Alarm method, device and computer-readable recording medium based on texture information |
| CN107886709A (en) * | 2017-11-21 | 2018-04-06 | 北京华油信通科技有限公司 | Information of vehicles processing method and processing device |
| CN108090146A (en) * | 2017-12-08 | 2018-05-29 | 四川金英科技有限责任公司 | A kind of case video analysis method and system |
| CN108090149A (en) * | 2017-12-08 | 2018-05-29 | 四川金英科技有限责任公司 | A kind of case video analysis method |
| CN108052581A (en) * | 2017-12-08 | 2018-05-18 | 四川金英科技有限责任公司 | A kind of case video studies and judges device |
| WO2019129075A1 (en) * | 2017-12-27 | 2019-07-04 | 中兴通讯股份有限公司 | Video searching method and device and computer readable storage medium |
| CN108176049A (en) * | 2017-12-28 | 2018-06-19 | 珠海市君天电子科技有限公司 | A kind of information cuing method, device, terminal and computer readable storage medium |
| CN108176049B (en) * | 2017-12-28 | 2021-05-25 | 珠海豹好玩科技有限公司 | Information prompting method, device, terminal and computer readable storage medium |
| CN108256532A (en) * | 2018-01-10 | 2018-07-06 | 武汉斗鱼网络科技有限公司 | Image processing method, device, electronic equipment and storage medium |
| CN108399261A (en) * | 2018-03-13 | 2018-08-14 | 成都蓉兴伟业科技有限公司 | A kind of case and video analysis method based on integration method |
| CN109408671A (en) * | 2018-07-23 | 2019-03-01 | 中国联合网络通信集团有限公司 | The searching method and its system of specific objective |
| CN109359213A (en) * | 2018-08-27 | 2019-02-19 | 博康智能信息技术有限公司 | A kind of security protection video intelligent retrieval system and its search method |
| CN109190584A (en) * | 2018-09-18 | 2019-01-11 | 银河水滴科技（北京）有限公司 | A kind of portable video searching system |
| CN109871783A (en) * | 2019-01-28 | 2019-06-11 | 武汉恩特拉信息技术有限公司 | A monitoring method and monitoring system based on video image |
| CN109871783B (en) * | 2019-01-28 | 2021-05-07 | 武汉恩特拉信息技术有限公司 | A monitoring method and monitoring system based on video image |
| CN109871815A (en) * | 2019-02-26 | 2019-06-11 | 新华三技术有限公司 | A kind of method and device of query monitor information |
| CN109871815B (en) * | 2019-02-26 | 2021-07-20 | 新华三技术有限公司 | Method and device for inquiring monitoring information |
| CN112019789A (en) * | 2019-05-31 | 2020-12-01 | 杭州海康威视数字技术股份有限公司 | Video playback method and device |
| CN110399525A (en) * | 2019-07-27 | 2019-11-01 | 广州伽利略网络科技有限公司 | A kind of people based on image recognition technology, object motion profile method for quickly retrieving |
| CN110555471A (en) * | 2019-08-26 | 2019-12-10 | 珠海格力电器股份有限公司 | Mobile terminal and target object searching method |
| CN111046209A (en) * | 2019-12-09 | 2020-04-21 | 中国科学院自动化研究所 | Image Clustering Retrieval System |
| CN111741325A (en) * | 2020-06-05 | 2020-10-02 | 咪咕视讯科技有限公司 | Video playback method, device, electronic device, and computer-readable storage medium |
| CN112231515A (en) * | 2020-10-28 | 2021-01-15 | 王志晓 | Mass surveillance video quick retrieval system and retrieval method |
| CN112040325B (en) * | 2020-11-02 | 2021-01-29 | 成都睿沿科技有限公司 | Video playing method and device, electronic equipment and storage medium |
| CN112040325A (en) * | 2020-11-02 | 2020-12-04 | 成都睿沿科技有限公司 | Video playing method and device, electronic equipment and storage medium |
| CN112382032A (en) * | 2020-11-13 | 2021-02-19 | 珠海大横琴科技发展有限公司 | Monitoring method and device, electronic equipment and storage medium |
| CN112866817A (en) * | 2021-01-06 | 2021-05-28 | 浙江大华技术股份有限公司 | Video playback method, device, electronic device and storage medium |
| CN113434573A (en) * | 2021-06-29 | 2021-09-24 | 中国科学院自动化研究所 | Multi-dimensional image retrieval system, method and equipment |
| CN113920489A (en) * | 2021-10-29 | 2022-01-11 | 广州文远知行科技有限公司 | Tracking method and device based on multi-model detection, vehicle and storage medium |
| CN119206586A (en) * | 2024-11-26 | 2024-12-27 | 杭州海康威视数字技术股份有限公司 | Target analysis method and electronic device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101840422A (en) | Intelligent video retrieval system and method based on target characteristic and alarm behavior | |
| Sun et al. | TBE-Net: A three-branch embedding network with part-aware ability and feature complementary learning for vehicle re-identification | |
| US10282616B2 (en) | Visual data mining | |
| US10007862B2 (en) | System and method for suspect search | |
| DeMenthon et al. | Video retrieval using spatio-temporal descriptors | |
| US10248726B2 (en) | Object search by description | |
| CN101848377B (en) | Device and method for intelligent linkage of multi-video recording device based on cloud computing and mass video searching | |
| CN101663676B (en) | Method and system for indexing and searching objects of interest across a plurality of video streams | |
| CN108062349A (en) | Video frequency monitoring method and system based on video structural data and deep learning | |
| CN107169106B (en) | Video retrieval method, device, storage medium and processor | |
| WO2008115674A2 (en) | Method and system for indexing and searching objects of interest across a plurality of video streams | |
| Màrmol et al. | QuickSpot: a video analytics solution for on-street vacant parking spot detection | |
| CN112861673A (en) | False alarm removal early warning method and system for multi-target detection of surveillance video | |
| CN117173217A (en) | Video multi-target tracking method based on multi-scale channel feature aggregation | |
| CN101354787A (en) | A method for extracting features of target motion trajectory in intelligent visual surveillance retrieval | |
| CN111666263A (en) | Method for realizing heterogeneous data management in data lake environment | |
| Feris et al. | Case study: IBM smart surveillance system | |
| Ji et al. | News videos anchor person detection by shot clustering | |
| Zhao et al. | Learning representative features for robot topological localization | |
| DeMenthon et al. | Video retrieval of near-duplicates using κ-nearest neighbor retrieval of spatio-temporal descriptors | |
| Le et al. | Surveillance video indexing and retrieval using object features and semantic events | |
| CN116451103A (en) | Situation element recommendation method based on label | |
| Moses et al. | A classified study on semantic analysis of video summarization | |
| Rathod et al. | A computer vision approach to vehicle detection, classification, and tracking from UAV data for Indian traffic analysis | |
| Zhang et al. | Multi-scale visualization based on sketch interaction for massive surveillance video data |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20100922 |