CN107358622A - A kind of video information processing method and system based on visualization movement locus - Google Patents
A kind of video information processing method and system based on visualization movement locus Download PDFInfo
- Publication number
- CN107358622A CN107358622A CN201710468885.1A CN201710468885A CN107358622A CN 107358622 A CN107358622 A CN 107358622A CN 201710468885 A CN201710468885 A CN 201710468885A CN 107358622 A CN107358622 A CN 107358622A
- Authority
- CN
- China
- Prior art keywords
- video
- movement locus
- feature
- camera
- tracking target
- 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
- 230000033001 locomotion Effects 0.000 title claims abstract description 99
- 238000012800 visualization Methods 0.000 title claims abstract description 19
- 230000010365 information processing Effects 0.000 title claims abstract description 9
- 238000003672 processing method Methods 0.000 title claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000005611 electricity Effects 0.000 claims 1
- 238000012544 monitoring process Methods 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 230000003068 static effect Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 206010017577 Gait disturbance Diseases 0.000 description 1
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 239000002360 explosive Substances 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000029052 metamorphosis Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30241—Trajectory
Abstract
The present invention relates to a kind of video information processing method and system based on visualization movement locus, wherein method comprises the following steps:Tracking is identified in tracking target in the video gathered according to default identification condition to camera, obtains the movement locus feature of the tracking target;By the video and with the tracking target trajectory characteristic storage in the video into movement locus feature database;The search condition of user's input is received, the search condition includes:First movement locus feature;The the second movement locus feature to match with the first movement locus feature is obtained from the movement locus feature database;The target video corresponding with the second movement locus feature is obtained from the video.The present invention have compressed the data volume of video storage by the above method, and substantially reduce the workload paid a return visit video.
Description
Technical field
It is especially a kind of based at the video information for visualizing movement locus the present invention relates to computer vision treatment technology
Manage method and system.
Background technology
Whole security protection market has had been introduced into general intellectualization times, traffic, the energy, garden, school, building, bank's bag
Including medium-sized and small enterprises, civilian etc. has intelligentized application demand.One of intelligentized important goal is so as to the more matchmakers of Large Copacity
The retrieval and return visit of volume data are more convenient and efficient.Traditional return visit mode be with image header laber (and/or title) and when
Between be used as search condition.
But this mode often still needs and manually checks substantial amounts of video data with actually useful required for finding
Information.Increase then as the burst of data, by manually checking that video data becomes difficult to achieve:In the world 90%
Data are caused in the past few years.And in fact, in over the past thirty years, global data volume about every two years increases by 10
Times, Moore's Law of this rate of rise considerably beyond computer realm.And this speed is with more data acquisitions
Continuing to bring out for instrument increasingly becomes big.Video data is especially true.
Market survey mechanism IHS analysis report shows that 2014, the shipment amount of IP Camera exceeded mould for the first time
Intend camera.Expect 2018, the shipment amount of IP Camera is up to 12,400,000,000, and these estimated cameras are every within 2017
The data of its generation are up to 859TB.In the five-year, data traffic caused by video will account for overall network data traffic
80-90%.Need data to be processed can be more and more, this must have more preferable solution to manage, store these data.
Due to being related to various video analysis, therefore, the analysis to video, decoding, coding and the various functions such as transcoding it is integrated,
And cloud computing, these all will be very important field.Certainly, as the gradual gesture of video-frequency networking rises, with video monitoring
For core security protection industry just towards more high definition, more intelligent, big data the quick evolution in direction.This also causes traditional with the sea of faces
Video clue based on tactics is searched just as looking for a needle in a haystack.
In the data explosion epoch of today, how video is carried out in collection, the links for storing, inquiring about, paying a return visit
Optimization, solve a series of problems that the explosive growth of data volume is brought, turn into people in the industry's problem urgently to be resolved hurrily.
The content of the invention
To solve the above problems, the present invention proposes a kind of video information content processing side based on visualization movement locus
Method and system.
In a first aspect, the invention provides a kind of video information processing method based on visualization movement locus, including,
Tracking target in the video gathered according to default identification condition to camera is identified tracking, obtain it is described with
The movement locus feature of track target;
By the video and with the tracking target trajectory characteristic storage in the video to movement locus feature database
In;
The search condition of user's input is received, the search condition includes:First movement locus feature;
The second movement locus to match with the first movement locus feature is obtained from the movement locus feature database
Feature;
The target video corresponding with the second movement locus feature is obtained from the video.
Tracking target in the video gathered according to default identification condition to camera is identified tracking, described in acquisition
Before the movement locus feature for tracking target, in addition to:
Camera is demarcated so that the image in the video of camera shooting is corresponding with preset electronic map, in advance
If electronic map is used to show the second movement locus feature.
It is, tracking is identified in the tracking target in the video gathered according to default identification condition to camera, obtains
Before the movement locus feature for taking the tracking target, in addition to:
Foreground detection is carried out to the video of camera collection, the background image in the video is removed, the video is entered
Row denoising.
The movement locus feature includes:The shooting area of the camera, the tracking target enter the shooting area
The time in domain, the tracking target leave the time of the shooting area and the movement velocity of the tracking target.
Second aspect, present invention also offers a kind of video information process system based on visualization movement locus, including,
Tracking is identified in processing unit, the tracking target in the video gathered for presetting identification condition to camera,
Obtain the movement locus feature of the tracking target;
Memory cell, by the video and with the tracking target trajectory characteristic storage in the video to motion rail
In mark feature database;
Receiving unit, for receiving the search condition of user's input, the search condition includes:First movement locus is special
Sign;
Retrieval unit, for obtaining what is matched with the first movement locus feature from the movement locus feature database
Second movement locus feature;
Video acquisition unit, regarded for obtaining the target corresponding with the second movement locus feature from the video
Frequently.
The system also includes, and unit is demarcated, for being demarcated to camera so that the image of camera shooting with it is pre-
If electronic map is corresponding, the preset electronic map is used to show the second movement locus feature.
The processing unit is additionally operable to carry out foreground detection to the video of camera collection, removes the background in the video
Image, denoising is carried out to the video.
The movement locus feature includes:The tracking target enters shooting area, the tracking mesh of the camera
Mark enters the time of the shooting area, the tracking target leaves the time of the shooting area and the tracking target
Movement velocity.
The present invention sets condition by studying the movement locus of moving target in video, pay close attention among video with
Track target trajectory feature, qualified video is stored and marked and (extracts the tracking target motion in video
Track characteristic), when paying a return visit video library, set search condition to retrieve corresponding video segment, and recall piece of video
Duan Jinhang is paid a return visit;The data volume of video storage is have compressed by the above method, and substantially reduces workload when video is paid a return visit.
Brief description of the drawings
Fig. 1 is the overall flow schematic diagram of the present invention;
Fig. 2 is the schematic diagram of the searched targets movement locus by characteristic matching in the present invention;
Fig. 3 is the schematic diagram of multiple target different motion tracks in the present invention;
Fig. 4 is the schematic diagram for reducing particular moment camera image in the present invention by target trajectory feature;
Fig. 5 is the schematic diagram that multiple camera pictures of the present invention map to same electronic map.
Embodiment
The principle and feature of the present invention are described below in conjunction with accompanying drawing, the given examples are served only to explain the present invention, and
It is non-to be used to limit the scope of the present invention.
The invention provides a kind of video information processing method based on visualization movement locus, including,
Tracking target in the video gathered according to default identification condition to camera is identified tracking, obtain it is described with
The movement locus feature of track target;
By the video and with the tracking target trajectory characteristic storage in the video to movement locus feature database
In;
The search condition of user's input is received, the search condition includes:First movement locus feature;
The second movement locus to match with the first movement locus feature is obtained from the movement locus feature database
Feature;
The target video corresponding with the second movement locus feature is obtained from the video.
Tracking target from the video in the video gathered according to default identification condition to camera is identified
Tracking, before obtaining the movement locus feature for tracking target, camera is demarcated, using taken by camera
Image reduces the relation in point and image in default map between corresponding points.Establish picture in the image of camera shooting
Vegetarian refreshments and the corresponding relation of the position on map.
Meanwhile the map electronization of relevant range is formed into preset electronic map, by described in preset electronic map denotation
The movement locus of target is tracked, in order to which user observes the movement locus feature of tracking target.Meanwhile can also in preset electronic
Different grades of forbidden zone is set on figure, the search condition whether swarmed into the factors such as forbidden zone by tracking target and be used as in S3.
Foreground detection is carried out to the video of camera collection, the background image in the video is removed, the video is entered
Row denoising.Static constant background parts in the video of camera collection are removed, are extracted comprising in limited information
Hold, the object observed some non-safety monitorings also filters, specifically can by setting pixel gray value scope,
More than or less than gray value threshold value pixel as noise remove.
The movement locus of target can be played sequentially in time in map afterwards.Clicking on arbitrary trajectory can play at that time
Corresponding video.Time, time departure can also be swarmed into, swarm into section, speed by setting, track characteristic, whether there are personnel
Required track is retrieved in aggregation etc., finds corresponding video clips by track.
Present invention also offers a kind of video information process system based on visualization movement locus, including,
Tracking is identified in processing unit, the tracking target in the video gathered for presetting identification condition to camera,
Obtain the movement locus feature of the tracking target;
Memory cell, for by the video and with the tracking target trajectory characteristic storage in the video to fortune
In dynamic rail mark feature database;
Receiving unit, for receiving the search condition of user's input, the search condition includes:First movement locus is special
Sign;
Retrieval unit, for obtaining what is matched with the first movement locus feature from the movement locus feature database
Second movement locus feature;
Video acquisition unit, regarded for obtaining the target corresponding with the second movement locus feature from the video
Frequently.
The system also includes, and unit is demarcated, for being demarcated to camera so that the image of camera shooting with it is pre-
If electronic map is corresponding, the preset electronic map is used to show the second movement locus feature.
The processing unit is additionally operable to carry out foreground detection to the video of camera collection, removes the background in the video
Image, denoising is carried out to the video.Foreground detection is carried out to the video of camera collection, removes the back of the body in the video
Scape image, denoising is carried out to the video.Remove static constant background parts, extraction in the video of camera collection
Go out to include the content of limited information.The object observed some non-safety monitorings also filters, specifically can be by setting
Put pixel gray value scope, more than or less than gray value threshold value pixel as noise remove.
The movement locus feature includes, and the tracking target enters shooting area, the tracking mesh of the camera
Mark enters the time of the shooting area, the tracking target leaves the time of the shooting area and the tracking target
Movement velocity.
Effect after the present invention is implemented is as follows:Due in monitored picture, most of moment is all identical, actionless
Picture, during playback, there can be substantial amounts of unimportant video segment, for unessential video, it is possible to straight
Connect and skip;Even when video stores, set certain condition that directly without storage, the partial video is reduced into unnecessary number
According to yield.
If doing selection target feature when play back afterwards carries out image recognition processing, due to the disposal ability of system
It is limited, stand-by period when user inquires about every time can be increased.Method mentioned in the present invention regards simultaneously when video recording
The identifying processing of frequency, when playback, it is only necessary to condition is set on map, does the simple fortune for judging that target can be found
Dynamic rail mark, the retrieval for realizing video by movement locus play back.
When multiple cameras be present, multiple cameras can be mapped on same map simultaneously.Thing
Conditional information retrieval can be carried out to all cameras on a map when retrieval playback afterwards.
Area to be monitored can be monitored using single or multiple cameras in the present invention, its operation principle is identical.
Video frequency searching and return visit of the single camera based on visualization track editor:In the two-dimensional video that any camera obtains
In, the feature such as position, shape, profile and the color that can obtain putting at any time on either objective by tracking system
Information, the species ownership of target is may determine that based on appearance information, and is understood based on time and space (position) information can
The movement locus of target.Such as Fig. 2, shown in Fig. 3.
What each track and a target were closely related, and each target is that possess own shape, profile and color etc.
Feature.The present invention realizes the processing to tracking target trajectory feature in the following way:
Static display:The multi-frame video of a period of time is passed through the simple track of a width by the present invention by way of in Fig. 2
Figure shows, and the present invention adds the more information on target in itself on the diagram, and the color of track can be target
Color (body color or integral color), the thickness of track can react the size of target, and this to a certain extent
Thickness can change with the change of target sizes, and the time of the appearing and subsiding of target can also be marked in corresponding track
Both ends.
As shown in figure 4, it can also show the additional of movement locus feature for tracking target trajectory feature static display
Information:It is presented on for the information that can not be directly marked on track in additional additional areas, these additional information can be with
Including (:The representative just list for all targets being currently displayed on trajectory diagram, track moment point is corresponding where current mouse
Picture (and with the movement of mouse change) of the respective objects at that moment, can also allow target corresponding to any track
Dynamic auto broadcasting.
Dynamic is edited:For electronic map displaying track, can by actual scene to safety monitoring region in make
Limited with time restriction, space, i.e., time and limitation spatially be set to whether specific region allows access into,;And pass through
Method that both above-mentioned modes mix filters to movement locus feature, that is, search out including time-to-violation limitation,
The tracking target trajectory feature of space limitation, and call return visit accordingly video.Specifically, space limitation can by
Safety monitoring region, which is set, to be counted the mode such as door or the limitation of other spaces and realizes), one or several track is selected, then allows and is
System plays target corresponding to this several tracks while merges the video segment of (together with background) in one scenario online, so has
The contrast of fast positioning and different target action beneficial to abnormal operation.Can also provide a 3-D view for this operation makes
User can control on a timeline each target start present the time, it might even be possible to compress path length on a timeline
Realize the rapid preview of some targets.It can also generate two-dimensional video for the result of both above operation and preserved.
In addition to by the working method in the corresponding one piece of region of single camera and its preset electronic map, the present invention may be used also
Camera network is formed by multiple shootings, and video monitoring processing is carried out to one piece of plane domain or non-planar area:
1) for video frequency searching of the plane multi-cam based on visualization track editor and return visit:
As shown in figure 5, when the camera that moving target overlaps by two visuals field, unified motion is formed on map
Track, in the multi-cam network that multiple cameras monitor a unified plane domain, by mapped system, all targets
Track may map in the preset electronic map of this plane, so as to form the unification that target is moved on preset electronic map
Movement locus.
2) for video frequency searching of the three-dimensional multi-cam based on visualization track editor and return visit:
If multi-cam network is not one plane domain of monitoring, but monitors on-plane surface such as a building
It region, then can be integrated into an aggregate map in map conflation to the approximately the same plane of each floor, and represent each floor
Between join domain can be connected by the stair or elevator stretched, equally can be by the way of above.
The track of moving target can have more applications in video.Event rules are based on using trace information, with expansion
The syntax analysis device of exhibition is identified to events of interest, so as to provide a complete Activity recognition framework.Iing is proposed will motion
Track or metamorphosis apply to the user interface of application program, user interface is had more more rich dynamic effects and skill
Art effect.In the two patents, as video concentration above, the actual simply implicit springboard instrument in track.Phase
Instead, in a multi-cam network monitoring system, based on the topological relation between camera, using the side of artificial sequential access
Formula, it is intended to construct the complete multi-cam complete active video of any moving target and the motion rail of entirety is formed on GIS figures
Mark.Track may be utilized for stumbling during line judges is taken action with the exception of automatic detection moving target.
The track of any moving target changes, even either in two-dimensional video space still in preset electronic map space
Three-dimensional world coordinate space, many kinetic characteristics of the target are really reflected, so on the one hand can be utilized to mesh
Target moves the abnormal operation that target into edlin, on the other hand can be excavated by track.Since automatic track can be done
Arrange, that copies the analysis to track to judge, and the multiple information of correspondence target is added on trace information, and (for example target disappears
Lose the time, color, size even target image etc.), the manually trace information to multiple target in single or multiple cameras
Intuitively edited the video information required to look up quickly to lock.
The foregoing is only presently preferred embodiments of the present invention, be not intended to limit the invention, it is all the present invention spirit and
Within principle, any modification, equivalent substitution and improvements made etc., it should be included in the scope of the protection.
Claims (8)
- A kind of 1. video information processing method based on visualization movement locus, it is characterised in that including:Tracking is identified in tracking target in the video gathered according to default identification condition to camera, obtains the tracking mesh Target movement locus feature;By the video and with the tracking target trajectory characteristic storage in the video into movement locus feature database;The search condition of user's input is received, the search condition includes:First movement locus feature;The the second movement locus feature to match with the first movement locus feature is obtained from the movement locus feature database;The target video corresponding with the second movement locus feature is obtained from the video.
- 2. the video information processing method according to claim 1 based on visualization movement locus, it is characterised in that in root Tracking is identified in tracking target in the video gathered according to default identification condition to camera, obtains the fortune of the tracking target Before dynamic track characteristic, in addition to:Camera is demarcated so that the image in the video of camera shooting is corresponding with preset electronic map, presets electricity Sub- map is used to show the second movement locus feature.
- 3. the video information processing method according to claim 2 based on visualization movement locus, it is characterised in that in root Tracking is identified in tracking target in the video gathered according to default identification condition to camera, obtains the fortune of the tracking target Before dynamic track characteristic, in addition to:Foreground detection is carried out to the video of camera collection, the background image in the video is removed, the video is gone Make an uproar processing.
- 4. the video information processing method based on visualization movement locus according to claim any one of 1-3, its feature It is, the movement locus feature includes:The shooting area of the camera, the tracking target enter the shooting area Time, the tracking target leave the time of the shooting area and the movement velocity of the tracking target.
- A kind of 5. video information process system based on visualization movement locus, it is characterised in that the system includes,Tracking is identified in processing unit, the tracking target in the video gathered for presetting identification condition to camera, obtains The movement locus feature of the tracking target;Memory cell, for by the video and with the tracking target trajectory characteristic storage in the video to motion rail In mark feature database;Receiving unit, for receiving the search condition of user's input, the search condition includes:First movement locus feature;Retrieval unit, for obtaining match with the first movement locus feature second from the movement locus feature database Movement locus feature;Video acquisition unit, for obtaining the target video corresponding with the second movement locus feature from the video.
- 6. the video information process system according to claim 5 based on visualization movement locus, it is characterised in that described System also includes:Unit is demarcated, for being demarcated to camera so that the image of camera shooting is relative with default preset electronic map Should, the preset electronic map is used to show the second movement locus feature.
- 7. the video information process system according to claim 6 based on visualization movement locus, it is characterised in that described Processing unit is additionally operable to carry out foreground detection to the video of camera collection, the background image in the video is removed, to described Video carries out denoising.
- 8. according to any described video information process systems based on visualization movement locus of claim 5-7, its feature exists In the movement locus feature includes:The shooting area of the camera, it is described tracking target enter the shooting area when Between, it is described tracking target leave the shooting area time and it is described tracking target movement velocity.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710468885.1A CN107358622A (en) | 2017-06-19 | 2017-06-19 | A kind of video information processing method and system based on visualization movement locus |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710468885.1A CN107358622A (en) | 2017-06-19 | 2017-06-19 | A kind of video information processing method and system based on visualization movement locus |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107358622A true CN107358622A (en) | 2017-11-17 |
Family
ID=60272319
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710468885.1A Pending CN107358622A (en) | 2017-06-19 | 2017-06-19 | A kind of video information processing method and system based on visualization movement locus |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107358622A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969644A (en) * | 2018-09-28 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Personnel trajectory tracking method, device and system |
CN111385522A (en) * | 2018-12-27 | 2020-07-07 | 杭州海康威视系统技术有限公司 | Moving object display method, device and system and electronic equipment |
CN111405382A (en) * | 2019-06-24 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Video abstract generation method and device, computer equipment and storage medium |
CN111784730A (en) * | 2020-07-01 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Object tracking method and device, electronic equipment and storage medium |
CN112773262A (en) * | 2019-11-08 | 2021-05-11 | 珠海市一微半导体有限公司 | Security control method based on sweeping robot, sweeping robot and chip |
CN113949842A (en) * | 2021-03-31 | 2022-01-18 | 紫光智云(江苏)物联网科技有限公司 | Suspected target track tracking and positioning system |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609548A (en) * | 2012-04-19 | 2012-07-25 | 李俊 | Video content retrieval method and system based on moving objects |
CN106296657A (en) * | 2016-07-28 | 2017-01-04 | 三峡大学 | A kind of method video camera being carried out Fast Calibration based on geometrical principle |
CN106446002A (en) * | 2016-08-01 | 2017-02-22 | 三峡大学 | Moving target-based video retrieval method for track in map |
-
2017
- 2017-06-19 CN CN201710468885.1A patent/CN107358622A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102609548A (en) * | 2012-04-19 | 2012-07-25 | 李俊 | Video content retrieval method and system based on moving objects |
CN106296657A (en) * | 2016-07-28 | 2017-01-04 | 三峡大学 | A kind of method video camera being carried out Fast Calibration based on geometrical principle |
CN106446002A (en) * | 2016-08-01 | 2017-02-22 | 三峡大学 | Moving target-based video retrieval method for track in map |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110969644A (en) * | 2018-09-28 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Personnel trajectory tracking method, device and system |
CN110969644B (en) * | 2018-09-28 | 2023-12-01 | 杭州海康威视数字技术股份有限公司 | Personnel track tracking method, device and system |
CN111385522A (en) * | 2018-12-27 | 2020-07-07 | 杭州海康威视系统技术有限公司 | Moving object display method, device and system and electronic equipment |
CN111405382A (en) * | 2019-06-24 | 2020-07-10 | 杭州海康威视系统技术有限公司 | Video abstract generation method and device, computer equipment and storage medium |
CN112773262A (en) * | 2019-11-08 | 2021-05-11 | 珠海市一微半导体有限公司 | Security control method based on sweeping robot, sweeping robot and chip |
CN111784730A (en) * | 2020-07-01 | 2020-10-16 | 杭州海康威视数字技术股份有限公司 | Object tracking method and device, electronic equipment and storage medium |
CN111784730B (en) * | 2020-07-01 | 2024-05-03 | 杭州海康威视数字技术股份有限公司 | Object tracking method and device, electronic equipment and storage medium |
CN113949842A (en) * | 2021-03-31 | 2022-01-18 | 紫光智云(江苏)物联网科技有限公司 | Suspected target track tracking and positioning system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107358622A (en) | A kind of video information processing method and system based on visualization movement locus | |
D'Orazio et al. | A semi-automatic system for ground truth generation of soccer video sequences | |
US8614741B2 (en) | Method and apparatus for intelligent and automatic sensor control using multimedia database system | |
CN104093001B (en) | Online dynamic video compression method | |
US8818038B2 (en) | Method and system for video indexing and video synopsis | |
US8107680B2 (en) | Monitoring an environment | |
US8027512B2 (en) | Method and software program for searching image information | |
US7428314B2 (en) | Monitoring an environment | |
US20070058842A1 (en) | Storage of video analysis data for real-time alerting and forensic analysis | |
CN101918989A (en) | Video surveillance system with object tracking and retrieval | |
CN101281593A (en) | Method and system for researching intelligent video monitoring case | |
CN106295598A (en) | A kind of across photographic head method for tracking target and device | |
Lai et al. | Video summarization of surveillance cameras | |
WO2020236949A1 (en) | Forensic video exploitation and analysis tools | |
CN102693292B (en) | Method for processing and rapidly retrieving inland ship videos based on RFID | |
Yao et al. | Object based video synopsis | |
CN112464757A (en) | High-definition video-based target real-time positioning and track reconstruction method | |
CN107704609B (en) | Video content retrieval method and device, computer-readable storage medium and terminal | |
CN103279493A (en) | Intelligent mass surveillance video analysis system | |
CN111277745A (en) | Target person tracking method and device, electronic equipment and readable storage medium | |
Cheatle | Media content and type selection from always-on wearable video | |
Neiswanger et al. | Unsupervised detection and tracking of arbitrary objects with dependent dirichlet process mixtures | |
van den Hengel et al. | Searching in space and time: a system for forensic analysis of large video repositories | |
Sumiya et al. | A Spatial User Interface for Browsing Video Key Frames | |
AU2004233448B2 (en) | Monitoring an environment |
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: 20171117 |
|
RJ01 | Rejection of invention patent application after publication |