CN110472551A - A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy - Google Patents
A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy Download PDFInfo
- Publication number
- CN110472551A CN110472551A CN201910735847.7A CN201910735847A CN110472551A CN 110472551 A CN110472551 A CN 110472551A CN 201910735847 A CN201910735847 A CN 201910735847A CN 110472551 A CN110472551 A CN 110472551A
- Authority
- CN
- China
- Prior art keywords
- camera
- character image
- display screen
- display
- main
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
Abstract
The invention discloses a kind of across mirror method for tracing for improving accuracy, comprising: receives the character image that user chooses, carries out feature identification to the character image and obtain corresponding people information；The camera for currently collecting character image corresponding with people information is defined as main camera, the picture signal that main camera acquires is shown in the main screen region of the first display screen；Centered on main camera, other cameras in addition to main camera in preset range are defined as from camera, and the character image acquired from camera is shown to the vice screen region of the first display screen again；It calls whole cameras to be tracked according to people information, and shows the mobile conduct with the matched character image of people information on a second display.The present invention shows different interfaces by the way that how each display screen is arranged, and carries out man-machine interactively, is corrected in real time according to character image collected, error correction, forms more accurately character image walking path, tracks accuracy by the promotion of multiple solutions multi-angle of view.
Description
Technical field
The present invention relates to facial image identification technology field more particularly to it is a kind of improve accuracy across mirror method for tracing,
Electronic equipment and storage medium.
Background technique
With the development of society, being applied in various industries of more and more extensively being sent out of video monitoring, number of cameras is also got over
Come huger, this brings stern challenge to traditional video monitoring.In safety-security area, the face based on monitoring camera is known
Universal application has been obtained in other technology, and suspect is found by face recognition technology, and the case successfully arrested also when
There is generation.But recognition of face is there is also certain drawback, for example face is deliberately blocked, can not photograph situations such as front of people and also can
Face is caused to fail.Across mirror tracer technique can be used as the important supplement of face recognition technology, clearly shoot people to that can not obtain
The pedestrian of face be continuously tracked across camera, enhances the space-time expending of data.
Across mirror tracer technique has proposed for a long time at present, and core technology therein is substantially to be identified again using ReID personnel
Technology, the company of other artificial intelligent video analysis, which has, studies related algorithm in in-depth, but due to the limitation of its core technology
Property, there is a problem of that universal accuracy is not high, so never actual scene is really applied to, so these enterprises also one
Directly making great efforts the deep accuracy grinding technology, tracking with raising across mirror.
Summary of the invention
For overcome the deficiencies in the prior art, chasing after across mirror for accuracy is improved one of the objects of the present invention is to provide a kind of
Track method, the problem of can solve prior art poor accuracy.
The problem of second object of the present invention is to provide a kind of electronic equipment, can solve prior art poor accuracy.
The third object of the present invention is the problem of providing a kind of storage medium, can solve prior art poor accuracy.
An object of the present invention is implemented with the following technical solutions:
A kind of across mirror method for tracing improving accuracy, includes the following steps:
Receiving step: receiving any character image that user chooses, and carries out feature identification acquisition to the character image and corresponds to
People information；
First display step: by the camera for currently collecting character image corresponding with the people information define based on take the photograph
As head, the picture signal that main camera acquires is shown in the main screen region of the first display screen；
Second display step: centered on the main camera, by the whole in addition to main camera in preset range
Other cameras are defined as from camera, and the character image acquired from camera is shown to the vice screen area of the first display screen again
Domain；
Third shows step: calling whole cameras to be tracked according to people information, and shows on a second display
With the mobile conduct of the matched character image of people information.
Preferably, further include following steps:
Extraction step: extract that each camera institute is collected to show that third is shown again with the matched character image of people information
Screen；
Screening step: it receives user and chooses specific character image on third display screen again, according to the specific figure map
As screening out and the unmatched character image of particular persons image.
Preferably, the second display screen also shows the corresponding location information in each camera position.
Preferably, the location information includes longitude and latitude.
Preferably, in the first display step, when collecting the camera of character image corresponding with people information as from taking the photograph
When as head, the first display screen carries out warning note, and updating should be main camera from camera.
The second object of the present invention samples following technical scheme and realizes:
A kind of electronic equipment including memory, processor and stores the meter that in memory and can be executed by processor
Calculation machine program, the computer program realize following steps when being executed by processor:
Receiving step: receiving any character image that user chooses, and carries out feature identification acquisition to the character image and corresponds to
People information；
First display step: by the camera for currently collecting character image corresponding with the people information define based on take the photograph
As head, the picture signal that main camera acquires is shown in the main screen region of the first display screen；
Second display step: centered on the main camera, by the whole in addition to main camera in preset range
Other cameras are defined as from camera, and the character image acquired from camera is shown to the vice screen area of the first display screen again
Domain；
Third shows step: calling whole cameras to be tracked according to people information, and shows on a second display
With the mobile conduct of the matched character image of people information.
Preferably, computer program also executes the following steps:
Extraction step: extract that each camera institute is collected to show that third is shown again with the matched character image of people information
Screen；
Screening step: it receives user and chooses specific character image on third display screen again, according to the specific figure map
As screening out and the unmatched character image of particular persons image.
Preferably, the second display screen also shows the corresponding location information in each camera position.
Preferably, in the first display step, when collecting the camera of character image corresponding with people information as from taking the photograph
When as head, the first display screen carries out warning note, and updating should be main camera from camera.
The third object of the present invention samples following technical scheme and realizes:
A kind of storage medium, is stored thereon with the computer program that can be executed by processor, and the computer program is located
It manages when device executes and realizes such as one of the object of the invention described in any item across mirror methods.
Compared with prior art, the beneficial effects of the present invention are:
The present invention shows different functions by the way that how each display screen is arranged, and carries out man-machine interactively, manually according to being acquired
Character image correct in real time, error correction, form more accurately character image walking path, chased after by the promotion of multiple solutions multi-angle of view
Track accuracy.
Detailed description of the invention
Fig. 1 is a kind of flow chart across mirror method for tracing for improving accuracy of the present invention.
Specific embodiment
In the following, being described further in conjunction with attached drawing and specific embodiment to the present invention:
As shown in Figure 1, the present invention provides a kind of across mirror method for tracing for improving accuracy comprising following steps:
S1: receiving any character image that user chooses, and carries out feature identification to the character image and obtains corresponding personage
Information；
The present invention needs to be applied to multiple cameras, these cameras are already installed on each position, that is to say that the present invention needs
These cameras are borrowed, acquire character image by these cameras.Camera carries out Image Acquisition to be responsible for region,
Its image acquired is sent to backstage, by manually being selected, clicks required character image.
S2: the camera for currently collecting character image corresponding with the people information is defined as main camera, will be led
The picture signal of camera acquisition is shown in the main screen region of the first display screen；
In step sl, user picks out the corresponding camera of character image, then definition is main camera, in the first display
The main screen region of screen shows the camera acquired image.Main screen region is, for example, the central location of display screen, certainly may be used
To be arranged in other positions.
In the first display step, when the camera for collecting character image corresponding with people information is from camera,
First display screen carries out warning note, and updating should be main camera from camera.When subsequent since the personage tracked is mobile,
Collect the corresponding character image of the personage next time is not necessarily current main camera, at this point, if other cameras
It collects by the character image, then the first display screen is prompted, such as the image that the camera acquires is on the first display screen
The modes such as automatic bounce, user's discovery collect the character image by other cameras, then can switch and take the photograph based on the camera
As head.
S3: centered on the main camera, by all other cameras in addition to main camera in preset range
It is defined as from camera, and the character image acquired from camera is shown to the vice screen region of the first display screen again；
Based on described in previous step, in whole field tracing process, main camera and can switch from camera,
Current main camera can also become from camera in subsequent.Vice screen region is, for example, the peripheral position of the first display screen,
Its display size can be set to smaller than main screen region.
Entire first display screen interface is all covered by the real time monitoring picture of camera, divides main screen and vice screen again in interface,
User mainly passes through main screen and selectes tracking personnel, and can be automatically adjusted Angular Trackong according to the movement of personnel.Sub-control
Screen mainly shows the camera real-time video on main empty screen periphery, if the suspect in main screen goes to any one vice screen
In, vice screen will pop up warning note, after administrative staff confirm, can set main screen for the sub-control screen, main screen before
It is automatically set as vice screen, and so on, realize the real-time tracing to suspect.
S4: whole cameras are called to be tracked according to people information, and display and people information on a second display
The mobile conduct of matched character image.Second display screen also shows the corresponding location information in each camera position.Simultaneously
It can also show the information such as time.Association spatially is carried out by the time point that different cameras occur, forms concrete action
Track.
Second display screen is map screen, for showing the distributing position of camera.Location information includes longitude and latitude.First
The character image of personage is tracked needed for the main screen display of display screen, then the geographical location pair where the corresponding camera of the main screen
It should be the current geographical location of tracking personage.According to the movement of personnel, the corresponding camera of main screen can change, that is, map screen
On can also easily obtain the location information of current persons, so as to show mobile conduct.
The entire interface of second display screen can use dark-coloured map for background, and the position table of camera is superimposed on map
Feelings are divided by different patterns.Be supplied to usertracking result once with two select buttons of video relationship line, if chosen
Tracking result once, will show that the history for the personnel of being tracked captures record in the left side at interface, while be highlighted in map pair
Video camera label answered etc..History video recording can be opened and grab fearness comparison diagram by clicking each camera.If chosen
Video relationship line, the camera that can be passed through the personnel of being tracked in map are suitable according to the time by way of line
Sequence is attached, to form the personnel in the conduct of entire tracing process.
Above-mentioned steps can realize that personage is tracked in across camera lens help, further include that steps are as follows further:
S5: extract that each camera institute is collected to show third display screen again with the matched character image of people information；
S6: it receives user and chooses specific character image on third display screen again, screened out according to the specific character image
With the unmatched character image of particular persons image.
Third design of LED is approximation screen, and major function is the accuracy that auxiliary improves tracking target, is passed through
Artificial access appropriate guarantees the continuity of tracking result, reduces the rate of false alarm of system.Can also by flexible setting identify with
It, to adapt to different application environments.
The interface integrally uses the look & feel with the first display screen always, by black background and white font, highlights
Body matter.Interface upper left shows the threshold values of current template, and is adjusted the input frame of threshold values according to the actual situation.
Upper right portion shows the template picture for being currently used in tracking, and the picture list for the history template having used.Interface
Other picture lists captured that lower half portion is demonstrated largely in threshold range, if the user find that current template have it is different
Chang Shi can reselect template in these standby pictures, be chosen by way of double-click, as new current tracking target
Template, the originally picture in current template will be moved into history template.
The present invention realizes a kind of new application method across mirror tracer technique, and by more pictures, the mode of multi-angle of view is very
Big degree improves the accuracy of tracking；Across mirror tracking is realized by the way of three screen of a machine, is respectively as follows: map screen and is shown
Camera position and track, the first display screen show that the real-time tracing video of camera, approximation screen show current tracking mould
Plate and approximation picture；Map interface is designed to show across the relation line between the mirror tracking result tracked and video.By multiple
It selects the mode of frame to control display content, designs across mirror tracking interface in real time, target person is tracked, interface is put by centre
Camera video recording where setting target person, surrounding shows the monitoring camera of periphery camera, as the movement of personnel can switch
The monitor video in middle position and peripheral position, design approximation is checked and selection interface, the mesh that can be tracked with real time inspection
It marks on a map the approximate result picture of piece and periphery, and supports the flexible replacement of the customized and template of threshold values.
The present invention also provides a kind of electronic equipment, including memory, processor and storage in memory and can be located
The computer program that device executes is managed, the computer program realizes following steps when being executed by processor:
Receiving step: receiving any character image that user chooses, and carries out feature identification acquisition to the character image and corresponds to
People information；
First display step: by the camera for currently collecting character image corresponding with the people information define based on take the photograph
As head, the picture signal that main camera acquires is shown in the main screen region of the first display screen；
Second display step: centered on the main camera, by the whole in addition to main camera in preset range
Other cameras are defined as from camera, and the character image acquired from camera is shown to the vice screen area of the first display screen again
Domain；
Third shows step: calling whole cameras to be tracked according to people information, and shows on a second display
With the mobile conduct of the matched character image of people information；
Extraction step: extract that each camera institute is collected to show that third is shown again with the matched character image of people information
Screen；
Screening step: it receives user and chooses specific character image on third display screen again, according to the specific figure map
As screening out and the unmatched character image of particular persons image.
A kind of storage medium is also provided, the computer program that can be executed by processor, the computer journey are stored thereon with
Across mirror method as described in the present invention is realized when sequence is executed by processor.
It will be apparent to those skilled in the art that can make various other according to the above description of the technical scheme and ideas
Corresponding change and deformation, and all these changes and deformation all should belong to the protection scope of the claims in the present invention
Within.
Claims (10)
1. a kind of across mirror method for tracing for improving accuracy, which comprises the steps of:
Receiving step: receiving any character image that user chooses, and carries out feature identification to the character image and obtains corresponding people
Object information；
First display step: by the camera for currently collecting character image corresponding with the people information define based on image
Head shows the picture signal that main camera acquires in the main screen region of the first display screen；
Second display step: centered on the main camera, by preset range in addition to main camera all other
Camera is defined as from camera, and the character image acquired from camera is shown to the vice screen region of the first display screen again；
Third shows step: calling whole cameras to be tracked according to people information, and display and people on a second display
The mobile conduct of the character image of object information matches.
2. across mirror method as described in claim 1, which is characterized in that further include following steps:
Extraction step: extract that each camera institute is collected to show third display screen again with the matched character image of people information；
Screening step: receiving user and choose specific character image on third display screen again, is sieved according to the specific character image
Except with the unmatched character image of particular persons image.
3. across mirror method as described in claim 1, which is characterized in that the second display screen also shows that each camera institute is in place
Set corresponding location information.
4. across mirror method as claimed in claim 3, which is characterized in that the location information includes longitude and latitude.
5. across mirror method as described in claim 1, which is characterized in that in the first display step, believe when collecting with personage
When the camera for ceasing corresponding character image is from camera, the first display screen carries out warning note, and updates and should be from camera
Main camera.
6. a kind of electronic equipment including memory, processor and stores the calculating that in memory and can be executed by processor
Machine program, which is characterized in that the computer program realizes following steps when being executed by processor:
Receiving step: receiving any character image that user chooses, and carries out feature identification to the character image and obtains corresponding people
Object information；
First display step: by the camera for currently collecting character image corresponding with the people information define based on image
Head shows the picture signal that main camera acquires in the main screen region of the first display screen；
Second display step: centered on the main camera, by preset range in addition to main camera all other
Camera is defined as from camera, and the character image acquired from camera is shown to the vice screen region of the first display screen again；
Third shows step: calling whole cameras to be tracked according to people information, and display and people on a second display
The mobile conduct of the character image of object information matches.
7. electronic equipment as claimed in claim 6, which is characterized in that computer program also executes the following steps:
Extraction step: extract that each camera institute is collected to show third display screen again with the matched character image of people information；
Screening step: receiving user and choose specific character image on third display screen again, is sieved according to the specific character image
Except with the unmatched character image of particular persons image.
8. electronic equipment as claimed in claim 6, which is characterized in that the second display screen also shows that each camera institute is in place
Set corresponding location information.
9. electronic equipment as claimed in claim 6, which is characterized in that in the first display step, believe when collecting with personage
When the camera for ceasing corresponding character image is from camera, the first display screen carries out warning note, and updates and should be from camera
Main camera.
10. a kind of storage medium is stored thereon with the computer program that can be executed by processor, which is characterized in that the calculating
Machine program realizes across mirror method as described in any one in claim 1-5 when being executed by processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735847.7A CN110472551A (en) | 2019-08-09 | 2019-08-09 | A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910735847.7A CN110472551A (en) | 2019-08-09 | 2019-08-09 | A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110472551A true CN110472551A (en) | 2019-11-19 |
Family
ID=68510495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910735847.7A Pending CN110472551A (en) | 2019-08-09 | 2019-08-09 | A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110472551A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112437278A (en) * | 2020-11-23 | 2021-03-02 | 杭州海康威视数字技术股份有限公司 | Cooperative monitoring system, device and method |
| CN112989896A (en) * | 2019-12-18 | 2021-06-18 | 广东毓秀科技有限公司 | Cross-lens tracking method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101803385A (en) * | 2007-09-23 | 2010-08-11 | 霍尼韦尔国际公司 | Dynamic tracking of intruders across a plurality of associated video screens |
| CN104581060A (en) * | 2014-12-25 | 2015-04-29 | 深圳市华宝电子科技有限公司 | Network flow management method and device for multiple channels of vehicle monitoring videos of mobile phone |
| CN106101613A (en) * | 2015-12-29 | 2016-11-09 | 广东中星电子有限公司 | The interlocked display method of multiple monitoring screens and system |
| CN106295598A (en) * | 2016-08-17 | 2017-01-04 | 北京大学 | A kind of across photographic head method for tracking target and device |
| CN107666590A (en) * | 2016-07-29 | 2018-02-06 | 华为终端（东莞）有限公司 | A kind of target monitoring method, camera, controller and target monitor system |
| CN108986158A (en) * | 2018-08-16 | 2018-12-11 | 新智数字科技有限公司 | A kind of across the scene method for tracing identified again based on target and device and Computer Vision Platform |
-
2019
- 2019-08-09 CN CN201910735847.7A patent/CN110472551A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101803385A (en) * | 2007-09-23 | 2010-08-11 | 霍尼韦尔国际公司 | Dynamic tracking of intruders across a plurality of associated video screens |
| CN104581060A (en) * | 2014-12-25 | 2015-04-29 | 深圳市华宝电子科技有限公司 | Network flow management method and device for multiple channels of vehicle monitoring videos of mobile phone |
| CN106101613A (en) * | 2015-12-29 | 2016-11-09 | 广东中星电子有限公司 | The interlocked display method of multiple monitoring screens and system |
| CN107666590A (en) * | 2016-07-29 | 2018-02-06 | 华为终端（东莞）有限公司 | A kind of target monitoring method, camera, controller and target monitor system |
| CN106295598A (en) * | 2016-08-17 | 2017-01-04 | 北京大学 | A kind of across photographic head method for tracking target and device |
| CN108986158A (en) * | 2018-08-16 | 2018-12-11 | 新智数字科技有限公司 | A kind of across the scene method for tracing identified again based on target and device and Computer Vision Platform |
Non-Patent Citations (1)
| Title |
|---|
| 齐力: "《公共安全大数据技术与应用》", 31 December 2017 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112989896A (en) * | 2019-12-18 | 2021-06-18 | 广东毓秀科技有限公司 | Cross-lens tracking method |
| CN112437278A (en) * | 2020-11-23 | 2021-03-02 | 杭州海康威视数字技术股份有限公司 | Cooperative monitoring system, device and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109117827B (en) | Video-based method for automatically identifying wearing state of work clothes and work cap and alarm system | |
| CN106821694B (en) | A kind of mobile blind guiding system based on smart phone | |
| US8285006B2 (en) | Human face recognition and user interface system for digital camera and video camera | |
| CN109690624A (en) | Automatic scene calibration method for video analysis | |
| CN105160297B (en) | Masked man's event automatic detection method based on features of skin colors | |
| CN108200334B (en) | Image shooting method and device, storage medium and electronic equipment | |
| CN109145708B (en) | Pedestrian flow statistical method based on RGB and D information fusion | |
| CN109087261B (en) | Face correction method based on unlimited acquisition scene | |
| US20110069173A1 (en) | System and method for automatic camera hand-off using location measurements | |
| CN107240124A (en) | Across camera lens multi-object tracking method and device based on space-time restriction | |
| CN101095149A (en) | Image comparison | |
| CN113052876B (en) | Video relay tracking method and system based on deep learning | |
| CN110414381A (en) | Tracing type face identification system | |
| CN105022999A (en) | Man code company real-time acquisition system | |
| EP3973446A1 (en) | Forensic video exploitation and analysis tools | |
| CN112183472A (en) | Method for detecting whether test field personnel wear work clothes or not based on improved RetinaNet | |
| CN110472551A (en) | A kind of across mirror method for tracing, electronic equipment and storage medium improving accuracy | |
| CN106682652B (en) | Structure surface disease inspection and analysis method based on augmented reality | |
| CN110969045B (en) | Behavior detection method and device, electronic equipment and storage medium | |
| WO2023207276A1 (en) | Area location update method, security and protection system, and computer-readable storage medium | |
| CN108921212A (en) | A kind of image matching method, mobile terminal and computer readable storage medium | |
| CN107784649A (en) | Plug test remote alarming system and method based on image recognition | |
| CN111340848A (en) | Object tracking method, system, device and medium for target area | |
| CN115273208A (en) | Track generation method, system and device and electronic equipment | |
| CN115116127A (en) | Fall detection method based on computer vision and artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191119 |