CN108898617A - A kind of tracking and device of target object - Google Patents

A kind of tracking and device of target object Download PDF

Info

Publication number
CN108898617A
CN108898617A CN201810505238.8A CN201810505238A CN108898617A CN 108898617 A CN108898617 A CN 108898617A CN 201810505238 A CN201810505238 A CN 201810505238A CN 108898617 A CN108898617 A CN 108898617A
Authority
CN
China
Prior art keywords
target object
image
location information
photographic device
information
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
Application number
CN201810505238.8A
Other languages
Chinese (zh)
Inventor
吴超
许奕波
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Original Assignee
Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yulong Computer Telecommunication Scientific Shenzhen Co Ltd filed Critical Yulong Computer Telecommunication Scientific Shenzhen Co Ltd
Priority to CN201810505238.8A priority Critical patent/CN108898617A/en
Publication of CN108898617A publication Critical patent/CN108898617A/en
Pending legal-status Critical Current

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/246Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00Image analysis
    • G06T7/20Analysis of motion
    • G06T7/292Multi-camera tracking

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Image Analysis (AREA)

Abstract

This application discloses a kind of tracking of target object and device, this method includes:Determine the characteristic information of target object to be tracked;According to the characteristic information of the target object, the target object is searched from the image that image library includes;According to the target object found, the location information of the target object is determined;According to the location information of the target object, the target object is tracked.In this way, when being tracked to target object, due to that the target object can be searched for from image automatically according to the characteristic information of target object, and, it can be according to the position of the target object automatic positioning target object searched, therefore, compared to existing technologies, the efficiency and accuracy rate for scanning for and positioning to target object can be improved, so as to more efficiently track to target object.

Description

A kind of tracking and device of target object
Technical field
This application involves target tracking domain more particularly to the trackings and device of a kind of target object.
Background technique
Currently, it is fitted with photographic device in traffic intersection, residential quarters, Administrative Area or other regions, these camera shootings Device can carry out Image Acquisition to the target object in its coverage area.When needing to track a certain target object, Target object can be tracked according to the image that photographic device acquires.
When the image acquired according to photographic device tracks target object, specifically, tracking individuals can basis The target object for needing to track successively is searched whether from multiple images comprising the target object, after finding target object, Tracking individuals may further determine that the location information of target object, and then realize the tracking to target object.
However, when being tracked according to the method for above-mentioned record to target object, due to needing tracking individuals artificially to look into Target object is looked for, and determines the location information of target object, causes the efficiency tracked to target object and accuracy rate lower, To can not effectively be tracked to target object.
Summary of the invention
The embodiment of the present application provides the tracking and device of a kind of target object, carries out for solving to target object When tracking, due to needing the artificially information such as lookup target object and the position for determining target object from image, cause to mesh The efficiency and accuracy rate that mark object is tracked are lower, thus the problem of can not effectively tracking to target object.
In order to solve the above technical problems, what the embodiment of the present application was realized in:
In a first aspect, propose a kind of tracking of target object, including:
Determine the characteristic information of target object to be tracked;
According to the characteristic information of the target object, the target object is searched from the image that image library includes, it is described The image that image library includes carries out Image Acquisition by multiple photographic devices and obtains;
According to the target object found, the location information of the target object is determined;
According to the location information of the target object, the target object is tracked.
With reference to first aspect, in the first possible implementation, it is implemented as:
The multiple photographic device is located at the different location of setting regions, and the multiple photographic device acquired image is covered The setting regions is covered, and, for any position in the setting regions, at least two photographic devices carry out the position Image Acquisition.
With reference to first aspect or the first possible implementation of first aspect, in second of possible implementation In, it is implemented as:According to the characteristic information, the target object is searched from the image that image library includes, including:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, root The target object is searched from the image that described image library includes according to matching result.
With reference to first aspect or second of the first possible implementation of first aspect or first aspect possible Implementation is implemented as in the third possible implementation:
According to the target object found, the location information of the target object is determined, including:
According to the target object found, determine that synchronization carries out Image Acquisition at least to the target object The location information of two photographic devices;
According to the location information of at least two photographic device, the location information of the target object is determined.
With reference to first aspect or second of the first possible implementation of first aspect or first aspect possible The possible implementation of the third of implementation or first aspect is implemented as in the fourth possible implementation:
According to the location information of at least two photographic device, the location information of the target object is determined, including:
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine The distance between the target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two camera shooting The location information of device determines the location information of the target object.
With reference to first aspect or second of the first possible implementation of first aspect or first aspect possible 4th kind of possible implementation of the possible implementation of the third of implementation or first aspect or first aspect, In five kinds of possible implementations, it is implemented as:
According to the location information of the target object, the target object is tracked, including:
According to the location information of the target object, the tracking information of the target object, the tracking information packet are determined Include at least one of trace route and the video of the target object of the target object;
According to the tracking information of the target object, the target object is tracked.
Second aspect proposes a kind of tracking device of target object, including:
First determining module determines the characteristic information of target object to be tracked;
Searching module searches the target according to the characteristic information of the target object from the image that image library includes Object, the image that described image library includes carry out Image Acquisition by multiple photographic devices and obtain;
Second determining module determines the location information of the target object according to the target object found;
Tracking module tracks the target object according to the location information of the target object.
In conjunction with second aspect, in the first possible implementation, it is implemented as:
The multiple photographic device is located at the different location of setting regions, and the multiple photographic device acquired image is covered The setting regions is covered, and, for any position in the setting regions, at least two photographic devices carry out the position Image Acquisition.
In conjunction with the possible implementation of the first of second aspect or second aspect, in second of possible implementation In, it is implemented as:The searching module searches the target according to the characteristic information from the image that image library includes Object, including:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, root The target object is searched from the image that described image library includes according to matching result.
Second in conjunction with the possible implementation of the first of second aspect or second aspect or second aspect is possible Implementation is implemented as in the third possible implementation:
Second determining module determines the location information of the target object according to the target object found, Including:
According to the target object found, determine that synchronization carries out Image Acquisition at least to the target object The location information of two photographic devices;
According to the location information of at least two photographic device, the location information of the target object is determined.
Second in conjunction with the possible implementation of the first of second aspect or second aspect or second aspect is possible The possible implementation of the third of implementation or second aspect is implemented as in the fourth possible implementation:
Second determining module determines the target object according to the location information of at least two photographic device Location information, including:
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine The distance between the target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two camera shooting The location information of device determines the location information of the target object.
Second in conjunction with the possible implementation of the first of second aspect or second aspect or second aspect is possible 4th kind of possible implementation of the possible implementation of the third of implementation or second aspect or second aspect, In five kinds of possible implementations, it is implemented as:
The tracking module tracks the target object according to the location information of the target object, including:
According to the location information of the target object, the tracking information of the target object, the tracking information packet are determined Include at least one of trace route and the video of the target object of the target object;
According to the tracking information of the target object, the target object is tracked.
At least one above-mentioned technical solution that the embodiment of the present application uses can reach following beneficial effect:
Technical solution provided by the embodiments of the present application determines the characteristic information of target object to be tracked;According to the mesh The characteristic information for marking object, searches the target object from the image that image library includes;According to the target pair found As determining the location information of the target object;According to the location information of the target object, to the target object carry out with Track.In this way, when being tracked to target object, due to that can be searched for from image automatically according to the characteristic information of target object The target object, and, it can be according to the position of the target object automatic positioning target object searched, therefore, compared to existing For technology, the efficiency and accuracy rate for scanning for and positioning to target object can be improved, so as to more efficiently right Target object is tracked.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 is a kind of flow diagram of the tracking of target object provided by the embodiments of the present application;
Fig. 2 is the flow diagram of the tracking of another target object provided by the embodiments of the present application;
Fig. 3 is a kind of structural schematic diagram of the tracking device of target object provided by the embodiments of the present application;
Fig. 4 is the structural schematic diagram of the tracking device of another target object provided by the embodiments of the present application.
Specific embodiment
In the prior art, it when being tracked to target object, is usually artificially shot from photographic device by tracking individuals To image in search target object, after finding target object, artificially target object is positioned, thus realize pair The tracking of target object.However, this artificial lookup and the mode speed being positioned manually are slower, tend to malfunction, or loses Target object is leaked, causes the efficiency tracked to target object and accuracy rate relatively low, thus cannot be effectively to target pair As being tracked.
In view of this, the embodiment of the present application provides the tracking and device of a kind of target object, this method includes:Really The characteristic information of fixed target object to be tracked;According to the characteristic information of the target object, from the image that image library includes The target object is searched, the image that described image library includes carries out Image Acquisition by multiple photographic devices and obtains;According to lookup The target object arrived, determines the location information of the target object;According to the location information of the target object, to described Target object is tracked.
Compared with prior art, the tracking of target object provided by the embodiments of the present application at least may be implemented following to have Beneficial effect:
(1) target object can be automatically searched for from image, is searched according to the characteristic information of target object to be tracked Suo Sudu is fast, high-efficient, and not easy to make mistakes;
(2) after finding target object, target object can be positioned automatically according to the target object found, And the accuracy rate of positioning is higher;
(3) position of the target object obtained according to positioning, can accurately track target object.
Based on above-mentioned 3 points, due to that can automatically search for and position target object according to the characteristic information of target object, Therefore, effectively target object can be tracked.
Technical scheme is clearly and completely retouched below with reference to the application specific embodiment and corresponding attached drawing It states.Obviously, the described embodiments are only a part but not all of the embodiments of the present application.Based in the application Embodiment, every other embodiment obtained by those of ordinary skill in the art without making creative efforts, It shall fall in the protection scope of this application.
The executing subject of the embodiment of the present application can be the server being made of one or more computer, the server Multiple photographic device acquired images can be managed, and these images can be analyzed and processed, determine mesh to be tracked Object is marked, and target object is positioned, is tracked.Wherein, the multiple photographic device may be constructed a cluster, common right Setting regions carries out Image Acquisition, and the setting regions can be Administrative Area, be also possible to residential area, can also be other Region, the multiple photographic device are distributed in the different location of the setting regions, and, for same position, at least there is two A photographic device carries out Image Acquisition to it, in order to which the subsequent server positions target object to be tracked.
Target object to be tracked can be people, be also possible to vehicle, can also be other target objects, for example, school bag, Clothing etc., no longer illustrates one by one here.
Technical solution provided by the embodiments of the present application can be applied to the various monitoring systems tracked to target object System, for example, target vehicle can be tracked in the security monitoring of traffic, it, can be to mesh in the security monitoring of factory Mark personnel or target product track, and in public security system, can track to target suspect, etc. here also no longer It illustrates one by one.
The tracking that the embodiment of the present application carries out target object can be the real-time tracking carried out to target object, for example, It, can be using technical solution provided by the embodiments of the present application to the target after monitoring target person in a certain cell Personnel carry out real-time tracking;It is also possible to the historical trace carried out to target object, to obtain the historical path of target object, example Such as, it in the history image of some traffic intersection, determines whether target vehicle occurs, if occurring, tracks the target vehicle, To obtain the target vehicle in the history planning driving path of the traffic intersection.
Below in conjunction with attached drawing, the technical scheme provided by various embodiments of the present application will be described in detail.
Fig. 1 is a kind of flow diagram of the tracking of target object provided by the embodiments of the present application.The method is such as It is lower described.
Step 102:Determine the characteristic information of target object to be tracked.
In a step 102, when needing to track a certain target object, target object to be tracked can be determined Characteristic information.
In the embodiment of the present application, the characteristic information of target object to be tracked can be the image of the target object, can also To be the information such as the color, shape, size of the target object.For example, target object to be tracked is suspect, it is possible to The image of the suspect is got from public security system or by other means, which can be considered as the feature letter of suspect Breath, alternatively, can also according to information such as the macroscopic features (such as height, colour of skin etc.) of the image zooming-out suspect of suspect, and The information such as the macroscopic features by suspect are considered as the characteristic information of suspect.
For another example target object to be tracked is suspected vehicles, it is possible to from the witness of the suspected vehicles or logical It crosses other modes and determines the information such as the color, shape, license plate number of the vehicle, these information can be considered as the feature of the suspected vehicles Information.
After the characteristic information for determining target object to be tracked, step 104 can be executed.
Step 104:According to the characteristic information of the target object, the target pair is searched from the image that image library includes As.
At step 104, after the characteristic information for determining target object to be tracked, can according to the characteristic information, The target object is searched from the image of image library.
In the embodiment of the present application, the image for including in described image library can carry out Image Acquisition by multiple photographic devices and obtain It arrives.Wherein, the multiple photographic device can form a cluster, and be mounted on setting regions (can be Administrative Area, can also To be a certain residential area, can also be other regions) different location, using the multiple photographic device to the setting area Domain carries out Image Acquisition.
It should be noted that different photographic devices can be to the setting area for the multiple photographic device Different location in domain carries out Image Acquisition, and the image of the multiple photographic device acquisition can cover the setting regions.This Outside, it is positioned for the ease of the subsequent position to target object, the multiple photographic device is installed in the setting regions When, it needs to guarantee, for any position in the setting regions, there are at least two photographic devices to carry out figure to the position Acquisition.
In the embodiment of the present application, the multiple photographic device can carry out Image Acquisition to the setting regions in real time, , can be by image transmitting into described image library after collecting image, and the multiple camera shooting is filled by described image library Acquired image is set to be managed collectively.
In this way, after the characteristic information for determining target object to be tracked, it can be according to this feature information, from described image The target object is searched in library.
When searching the target object from the image that image library includes, may include:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, root The target object is searched from the image that described image library includes according to matching result.
Specifically, can to include in described image library image carry out characteristic information extraction, wherein can according to The characteristic information for the image for including in the feature information extraction described image library of the target object of tracking.For example, mesh to be tracked The characteristic information for marking object is color, it is possible to the color of each of described image library image is extracted, for another example to The characteristic information of the target object of tracking is the image of target object, it is possible to extract each of described image library figure The image for the object for including as in.That is, being extracted in the embodiment of the present application to the image for including in described image library Obtained characteristic information, can be corresponding with the characteristic information of target object to be tracked.
It, can be by the spy of target object to be tracked after the characteristic information for the image for including in extracting described image library Reference breath is matched with the characteristic information extracted, searched from the image that described image library includes according to matching result described in Target object.
For example, if the characteristic information of target object to be tracked is image, it is possible to using image processing techniques, The image is matched with the image of the object extracted from described image library, if successful match (for example, two images 60%) similarity is greater than, then the corresponding object of the image of successful match can be determined as the target object.
For another example if the characteristic information of target object to be tracked is color, it is possible to by the RGE value of the color It is matched with the rgb value for the color extracted, if successful match (for example, the difference of two rgb values is less than 50), can be incited somebody to action The corresponding object of the color of successful match is determined as the target object.
It should be noted that being adopted in the embodiment of the present application due to carrying out image to any position in the setting regions The number at least two of the photographic device of collection, therefore, after the target object is found in the image in described image library, packet The number at least two of image containing the target object, and, at least two images come from least two photographic devices for this.
In addition, it is contemplated that target object may change in the position of different moments, it include the target object therefore At least two images can be synchronization to the target object carry out Image Acquisition obtain, be also possible to when different It carves and target object progress Image Acquisition is obtained, wherein collected at least two image in synchronization The number at least two of image.
For example, one, which shares 4 images A, B, C and D, includes the target object, 4 images after finding target object It is respectively from photographic device a, b, c and d, then, image A and B can be respectively by photographic device a and photographic device b in the mornings 10 points carry out Image Acquisition to target object and obtain;Image C and D can be respectively by photographic device c and photographic device d in the mornings ten Thirty carries out Image Acquisition to target object and obtains.
In the method based on above-mentioned record after searching the target object in the image that described image library includes, it can hold Row step 106.
Step 106:According to the target object found, the location information of the target object is determined.
It in step 106, can be according to looking into after target object to be tracked being found in the image from described image library The target object found determines the location information of the target object.
In the embodiment of the present application, according to the target object found, the location information of the target object is determined, it can To include:
According to the target object found, determines and Image Acquisition is carried out extremely to the target object in synchronization The location information of few two photographic devices;
According to the location information of at least two photographic device, the location information of the target object is determined.
Specifically, it after finding target image, may further determine that obtain the multiple images where target object.? When determining the location information of target object, it can determine which image is collected at synchronization from this multiple images 's.Wherein, in the multiple images where target object, at least there are two images is collected in synchronization.
After determining at least two images that synchronization collects, it can determine and collect from described image library The photographic device (acquired image can be stored according to different photographic devices in described image library) of at least two image, And further determine that the location information for collecting the photographic device of at least two image in the setting regions, wherein by When multiple photographic devices are installed in the setting regions, the location information of each photographic device has been had recorded, it therefore, can According to the location information for recording determining at least two photographic device.
In the embodiment of the present application, the location information of photographic device can be geographical location information, be also possible to specific height Spend information, or with the distance between some landmark building information etc..
Determine that synchronization carries out at least two of Image Acquisition to the target object in the method based on above-mentioned record After the location information of photographic device, the location information of the target object can be determined according to the location information, thus realization pair The tracking of the target object.
For example, A and B scheme after finding target object in image A, B, C and D for two that synchronization collects Picture, C and D are two images that synchronization collects, wherein image A is collected by photographic device a, and image B is by imaging Device b is collected, and image C is collected by photographic device c, and image D is collected by photographic device d, it is possible to determine The location information of photographic device a and the location information of photographic device b, according to the location information of photographic device a and photographic device b Location information determines the location information of target object, can also determine the location information of photographic device c and the position of photographic device d Information determines the location information of target object according to the location information of the location information of photographic device c and photographic device d.
In the embodiment of the present application, according to the location information of at least two photographic device, the target object is determined Location information may include:
Determine depth of field when at least two photographic device carries out Image Acquisition;
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine The distance between the target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two camera shooting The location information of device determines the location information of the target object.
Specifically, the location information of target object can be determined based on double methods for taking the photograph positioning, wherein double sides for taking the photograph positioning Method be according to synchronization to target object carry out Image Acquisition two photographic devices the depth of field, two photographic devices all In the case where can carrying out Image Acquisition to target object, the crosspoint of two depth of field distances can be considered as the position of the target object It sets, target object and two photographic devices can be considered as three vertex of triangle, the principle based on trigonometric function, according to two The depth of field of the distance between photographic device and two photographic devices, can be calculated target object and two photographic devices it Between distance.
For example, the distance between photographic device a and photographic device b are L1, it is known that the depth of field of photographic device a is L2, camera shooting The depth of field of device b is that L3, L2 and L3 can be numberical range.Since photographic device a and photographic device b can be to target objects Figure acquisition is carried out, it is therefore contemplated that target object is within the scope of the depth of field L2 of photographic device a, also in the scape of photographic device b Within the scope of deep L3, the crosspoint of L2 and L3 can be considered as the position of the target object, the target object and photographic device a and camera shooting It may be constructed unique triangle between device b.According to the three sides of a triangle L1, L2 and L3, the original based on trigonometric function Reason, can determine target object and the distance between photographic device a and photographic device b.
Double principles for taking the photograph positioning based on above-mentioned record obtain adopting target object progress image in synchronization determining After the location information of at least two photographic devices of collection, if it is determined that the number of obtained photographic device is 2, then can direct root According to the depth of field of the distance between the two photographic devices and the two photographic devices, obtained based on the method determination of above-mentioned record The distance between target object and the two photographic devices.
If it is determined that the number of obtained photographic device is greater than 2, then two of them photographic device can be randomly selected, according to The depth of field of the distance between two photographic devices chosen and two photographic devices is obtained based on the method determination of above-mentioned record The distance between target object and the two photographic devices.
It, can be according at least two camera shooting after at a distance from determining target object between at least two photographic devices The location information of device determines the location information of the target object.
For example, the distance between photographic device a and photographic device b be 3 meters, between target object and photographic device a away from From being 4 meters, the distance between photographic device b is 5 meters, if the location information of photographic device a is the position for building 2 meters apart from certain It sets, then the location information of target object can be the position apart from 6 meters of the building.
It should be noted that if being greater than in number of the synchronization to the photographic device that target object carries out Image Acquisition 2, then, it can determine that the multiple positions for obtaining target object are believed based on the method for above-mentioned record with any two of them for one group Breath, multiple location informations are mutually corrected, the location information of more accurately target object is obtained.
And above-mentioned record method, after the location information for determining target object, step 108 can be executed.
Step 108:According to the location information of the target object, the target object is tracked.
It in step 108, can be right according to the location information of target object after determining the location information of target object Target object is tracked.
In the embodiment of the present application, according to the location information of the target object, the target object is tracked, it can be with Including:
According to the location information of the target object, the tracking information of the target object, the tracking information packet are determined Include at least one of trace route and the video of the target object of the target object;
According to the tracking information of the target object, the target object is tracked.
Specifically, the tracking letter for being tracked to target object can be determined according to the location information of target object Breath, it can also both include mesh that the tracking information, which can be the trace route of target object, be also possible to the video of target object, The trace route of object is marked, and includes the video of target object.
The trace route of target object can be determined in the following manner and be obtained:If to target object carry out in real time with Track, then, in the setting regions for being equipped with photographic device, in the content by being recorded in step 102 and step 104 After really searching target object, the location information of target object can be determined according to the method that step 106 is recorded, and record the position Confidence breath.Later, the target object can be continued searching in real-time acquired image in described image library, in this way, being based on The content that above-mentioned steps 106 are recorded can determine in real time obtains the location information of the target object, and records.By the position of record Information is together in series according to the sequencing of time, so that it may obtain the trace route of target object.
If it is the historical trace to target object, to determine the history trace route of target object, it is possible to from institute The content stated and obtain history image in image library, and recorded based on above-mentioned steps 102 and step 104, is searched for from history image Target object, after searching target object, the method recorded based on above-mentioned steps 106 can determine to obtain target object not These location informations are together in series by location information in the same time, the history trace route of available target object.
The video of the target object can be determined in the following manner and be obtained:If to target object carry out in real time with Track, then, in the setting regions for being equipped with photographic device, in the content by being recorded in step 102 and step 104 After really searching target object, the image comprising target object can be extracted.Later, it can be acquired in real time in described image library The image relay arrived is continuous to search for the target object, and the image zooming-out comprising the target object collected in real time is come out. In this way, the image comprising target object extracted can be synthesized according to chronological order, the video of target object is obtained.
If it is the historical trace to target object, to obtain the history video of target object, it is possible to be based on above-mentioned The content that step 102 and step 104 are recorded, searches for target object from the history image in described image library, is searching target After object, all images comprising target object are extracted, these images are synthesized according to chronological order, obtain target object History video.
After obtaining the above-mentioned tracking information of target object, target object can be tracked.
It should be noted that in practical applications, especially when carrying out real-time tracking to target object, if from described Target object is searched in image library, then, it can also be according to further extracting target pair from the image comprising target object The characteristic information of elephant, so as to the characteristic information that improves target object, according to the characteristic information after improving preferably to target pair As scanning for and tracking.
For example, target object to be tracked is suspect, suspicion is searched from described image library according to the image of suspect After doubting people, it can be disliked according to information such as clothing, the appearance for further extracting suspect in the image comprising the suspect with improving The characteristic information of people is doubted, in this way, preferably can scan for and track to suspect according to the characteristic information after improving.
In addition, if target object is searched in described image library, then, it can also be in the picture to the target object It is marked, in order to quickly recognize target object from image.It, can also be in video in the video for determining target object Middle emphasis marks target object, in this way, can more intuitively be tracked according to the video of target object to target object.
Fig. 2 is the flow diagram of the tracking of another target object provided by the embodiments of the present application.
In Fig. 2, when tracking to target object, the characteristic information of target object is determined, for example, it may be determined that target The information such as image, color, the shape of object.After determining the characteristic information of target object, it can be searched from the image of image library Rope target object, wherein image in image library can (N be natural number, and is greater than 1) a photographic device and carries out image by N It collecting, multiple photographic devices may be mounted at different location in setting regions, to any position in setting regions, until There are two photographic devices less and Image Acquisition is carried out to the position.
Specific searching method may refer to the content of the record of above-mentioned steps 104, and description is not repeated herein.
After searching target object, it can determine and at least two of Image Acquisition is carried out to target object in synchronization Photographic device, according to the location information of at least two photographic devices, double methods for taking the photograph positioning based on the record of above-mentioned steps 106, Determine the location information of target object.
It, can be according to the location information, based in the record of above-mentioned steps 108 after determining the location information of target object Hold and further determine that the trace route and video of target object, according to determining trace route and video to target object carry out with Track.
Technical solution provided by the embodiments of the present application determines the characteristic information of target object to be tracked;According to the mesh The characteristic information for marking object, searches the target object from the image that image library includes;According to the target pair found As determining the location information of the target object;According to the location information of the target object, to the target object carry out with Track.In this way, when being tracked to target object, due to that can be searched for from image automatically according to the characteristic information of target object The target object, and, it can be according to the position of the target object automatic positioning target object searched, therefore, compared to existing For technology, the efficiency and accuracy rate for scanning for and positioning to target object can be improved, so as to more efficiently right Target object is tracked.
It is above-mentioned that this specification specific embodiment is described.Other embodiments are in the scope of the appended claims It is interior.In some cases, the movement recorded in detail in the claims or step can be come according to the sequence being different from embodiment It executes and desired result still may be implemented.In addition, process depicted in the drawing not necessarily require show it is specific suitable Sequence or consecutive order are just able to achieve desired result.In some embodiments, multitasking and parallel processing be also can With or may be advantageous.
Fig. 3 is a kind of structural schematic diagram of the tracking device of target object provided by the embodiments of the present application.It is described to include:The One determining module 31, searching module 32, the second determining module 33 and tracking module 34, wherein:
First determining module 31, determines the characteristic information of target object to be tracked;
Searching module 32 searches the mesh according to the characteristic information of the target object from the image that image library includes Object is marked, the image that described image library includes carries out Image Acquisition by multiple photographic devices and obtains;
Second determining module 33 determines the location information of the target object according to the target object found;
Tracking module 34 tracks the target object according to the location information of the target object.
Optionally, the multiple photographic device is located at the different location of setting regions, and the multiple photographic device collects Image cover the setting regions, and, for any position in the setting regions, at least two photographic devices are to described Position carries out Image Acquisition.
Optionally, the searching module 12 searches the mesh according to the characteristic information from the image that image library includes Object is marked, including:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, root The target object is searched from the image that described image library includes according to matching result.
Optionally, second determining module 33 determines the target object according to the target object found Location information, including:
According to the target object found, determine that synchronization carries out Image Acquisition at least to the target object The location information of two photographic devices;
According to the location information of at least two photographic device, the location information of the target object is determined.
Optionally, second determining module 33, according to the location information of at least two photographic device, determine described in The location information of target object, including:
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine The distance between the target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two camera shooting The location information of device determines the location information of the target object.
Optionally, the tracking module 34, according to the location information of the target object, to the target object carry out with Track, including:
According to the location information of the target object, the tracking information of the target object, the tracking information packet are determined Include at least one of trace route and the video of the target object of the target object;
According to the tracking information of the target object, the target object is tracked.
Fig. 4 is the structural schematic diagram of the tracking device of another target object provided by the embodiments of the present application.
As shown in figure 4, the tracking device of target object may include:Processor 402 and channel interface 401, optionally, including Memory 403.
Channel interface 401, processor 402 and memory 403 can be connected with each other by 404 system of bus.Bus 404 can To be ISA (Industry Standard Architecture, industry standard architecture) bus, PCI (Peripheral Component Interconnect, Peripheral Component Interconnect standard) bus or EISA (Extended Industry Standard Architecture, expanding the industrial standard structure) bus etc..The bus can be divided into address bus, data/address bus, control always Line etc..Only to be indicated with a four-headed arrow in Fig. 4, it is not intended that an only bus or a type of convenient for indicating Bus.
Optionally, including memory 403, for storing program.Specifically, program may include program code, the journey Sequence code includes computer operation instruction.Memory 403 may include read-only memory and random access memory, and to processing Device 402 provides instruction and data.Memory 403 may comprising high-speed random access memory (Random-Access Memory, RAM), it is also possible to further include nonvolatile memory (non-volatile memory), for example, at least 1 magnetic disk storage.
Processor 402 optionally, executes the program that memory 403 is stored, and specifically use for performing the following operations The operation below executing:
Determine the characteristic information of target object to be tracked;
According to the characteristic information of the target object, the target object is searched from the image that image library includes, it is described The image that image library includes carries out Image Acquisition by multiple photographic devices and obtains;
According to the target object found, the location information of the target object is determined;
According to the location information of the target object, the target object is tracked.
The tracking device of the above-mentioned target object as disclosed in the embodiment of the present application Fig. 1 and embodiment illustrated in fig. 2 executes Method can be applied in processor 402, or be realized by processor 402.Processor 402 may be a kind of ic core Piece, the processing capacity with signal.During realization, each step of the above method can pass through the hardware in processor 402 Integrated logic circuit or software form instruction complete.Above-mentioned processor 402 can be general processor, including center Processor (Central Processing Unit, CPU), network processing unit (Network Processor, NP) etc.;It can be with It is digital signal processor (Digital Signal Processor, DSP), specific integrated circuit (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hardware components.It can be with Realize or execute disclosed each method, step and the logic diagram in the embodiment of the present application.General processor can be micro- place Reason device or the processor are also possible to any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present application Hardware decoding processor can be embodied directly in and execute completion, or in decoding processor hardware and software module combination hold Row is completed.Software module can be located at random access memory, flash memory, read-only memory, programmable read only memory or electrically erasable In the storage medium for writing this fields such as programmable storage, register maturation.The storage medium is located at memory 403, processor 402 read the information in memory 403, in conjunction with the step of its hardware completion above method.
The embodiment of the present application also proposed a kind of computer readable storage medium, the computer-readable recording medium storage one A or multiple programs, the one or more program include instruction, and the instruction is when by the portable electronic including multiple application programs When equipment executes, method that the portable electronic device can be made to execute Fig. 1 and/or embodiment illustrated in fig. 2.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more, The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates, Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one The step of function of being specified in a box or multiple boxes.
In a typical configuration, calculating equipment includes one or more processors (CPU), input/output interface, net Network interface and memory.
Memory may include the non-volatile memory in computer-readable medium, random access memory (RAM) and/or The forms such as Nonvolatile memory, such as read-only memory (ROM) or flash memory (flash RAM).Memory is computer-readable medium Example.
Computer-readable medium includes permanent and non-permanent, removable and non-removable media can be by any method Or technology come realize information store.Information can be computer readable instructions, data structure, the module of program or other data. The example of the storage medium of computer includes, but are not limited to phase change memory (PRAM), static random access memory (SRAM), moves State random access memory (DRAM), other kinds of random access memory (RAM), read-only memory (ROM), electric erasable Programmable read only memory (EEPROM), flash memory or other memory techniques, read-only disc read only memory (CD-ROM) (CD-ROM), Digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape magnetic disk storage or other magnetic storage devices Or any other non-transmission medium, can be used for storage can be accessed by a computing device information.As defined in this article, it calculates Machine readable medium does not include temporary computer readable media (transitory media), such as the data-signal and carrier wave of modulation.
It should also be noted that, the terms "include", "comprise" or its any other variant are intended to nonexcludability It include so that the process, method, commodity or the equipment that include a series of elements not only include those elements, but also to wrap Include other elements that are not explicitly listed, or further include for this process, method, commodity or equipment intrinsic want Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including described want There is also other identical elements in the process, method of element, commodity or equipment.
The above description is only an example of the present application, is not intended to limit this application.For those skilled in the art For, various changes and changes are possible in this application.All any modifications made within the spirit and principles of the present application are equal Replacement, improvement etc., should be included within the scope of the claims of this application.

Claims (12)

1. a kind of tracking of target object, which is characterized in that including:
Determine the characteristic information of target object to be tracked;
According to the characteristic information of the target object, the target object, described image are searched from the image that image library includes The image that library includes carries out Image Acquisition by multiple photographic devices and obtains;
According to the target object found, the location information of the target object is determined;
According to the location information of the target object, the target object is tracked.
2. the method as described in claim 1, which is characterized in that
The multiple photographic device is located at the different location of setting regions, and the multiple photographic device acquired image covers institute Setting regions is stated, and, for any position in the setting regions, at least two photographic devices carry out image to the position Acquisition.
3. method according to claim 2, which is characterized in that according to the characteristic information, from the image that image library includes The target object is searched, including:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, according to The target object is searched from the image that described image library includes with result.
4. method as claimed in claim 3, which is characterized in that according to the target object found, determine the target The location information of object, including:
According to the target object found, determine that synchronization carries out at least two of Image Acquisition to the target object The location information of photographic device;
According to the location information of at least two photographic device, the location information of the target object is determined.
5. method as claimed in claim 4, which is characterized in that according to the location information of at least two photographic device, really The location information of the fixed target object, including:
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine described in The distance between target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two photographic device Location information, determine the location information of the target object.
6. method as claimed in claim 5, which is characterized in that according to the location information of the target object, to the target Object is tracked, including:
According to the location information of the target object, determine that the tracking information of the target object, the tracking information include institute State at least one of trace route and the video of the target object of target object;
According to the tracking information of the target object, the target object is tracked.
7. a kind of tracking device of target object, which is characterized in that including:
First determining module determines the characteristic information of target object to be tracked;
Searching module searches the target object according to the characteristic information of the target object from the image that image library includes, The image that described image library includes carries out Image Acquisition by multiple photographic devices and obtains;
Second determining module determines the location information of the target object according to the target object found;
Tracking module tracks the target object according to the location information of the target object.
8. device as claimed in claim 7, which is characterized in that
The multiple photographic device is located at the different location of setting regions, and the multiple photographic device acquired image covers institute Setting regions is stated, and, for any position in the setting regions, at least two photographic devices carry out image to the position Acquisition.
9. device as claimed in claim 8, which is characterized in that the searching module, according to the characteristic information, from image library The target object is searched in the image for including, including:
Extract the characteristic information for the image for including in described image library;
The characteristic information for the image for including in the characteristic information of the target object and described image library is matched, according to The target object is searched from the image that described image library includes with result.
10. device as claimed in claim 9, which is characterized in that second determining module, according to the target found Object determines the location information of the target object, including:
According to the target object found, determine that synchronization carries out at least two of Image Acquisition to the target object The location information of photographic device;
According to the location information of at least two photographic device, the location information of the target object is determined.
11. device as claimed in claim 10, which is characterized in that second determining module is taken the photograph according to described at least two As the location information of device, the location information of the target object is determined, including:
According to the distance between the depth of field of at least two photographic device and at least two photographic device, determine described in The distance between target object and at least two photographic device;
According to the distance between the target object and at least two photographic device and at least two photographic device Location information, determine the location information of the target object.
12. device as claimed in claim 11, which is characterized in that the tracking module, according to the position of the target object Information tracks the target object, including:
According to the location information of the target object, determine that the tracking information of the target object, the tracking information include institute State at least one of trace route and the video of the target object of target object;
According to the tracking information of the target object, the target object is tracked.
CN201810505238.8A 2018-05-24 2018-05-24 A kind of tracking and device of target object Pending CN108898617A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201810505238.8A CN108898617A (en) 2018-05-24 2018-05-24 A kind of tracking and device of target object

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201810505238.8A CN108898617A (en) 2018-05-24 2018-05-24 A kind of tracking and device of target object

Publications (1)

Publication Number Publication Date
CN108898617A true CN108898617A (en) 2018-11-27

Family

ID=64343766

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201810505238.8A Pending CN108898617A (en) 2018-05-24 2018-05-24 A kind of tracking and device of target object

Country Status (1)

Country Link
CN (1) CN108898617A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110198411A (en) * 2019-05-31 2019-09-03 努比亚技术有限公司 Depth of field control method, equipment and computer readable storage medium during a kind of video capture
CN110977950A (en) * 2019-11-12 2020-04-10 长沙长泰机器人有限公司 Robot grabbing and positioning method
CN111860345A (en) * 2020-07-22 2020-10-30 海尔优家智能科技(北京)有限公司 Method and device for determining object position, storage medium and electronic device

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101701814A (en) * 2009-11-04 2010-05-05 中兴通讯股份有限公司 Method for judging spatial position of target by linkage of multi-cameras and system thereof
WO2012124852A1 (en) * 2011-03-14 2012-09-20 (주)아이티엑스시큐리티 Stereo camera device capable of tracking path of object in monitored area, and monitoring system and method using same
CN103377471A (en) * 2012-04-16 2013-10-30 株式会社理光 Method and device for object positioning, and method and device for determining optimal camera pair
CN103400371A (en) * 2013-07-09 2013-11-20 河海大学 Multi-camera synergistic monitoring equipment and method
CN105933650A (en) * 2016-04-25 2016-09-07 北京旷视科技有限公司 Video monitoring system and method
CN106813649A (en) * 2016-12-16 2017-06-09 北京远特科技股份有限公司 A kind of method of image ranging localization, device and ADAS
CN106878666A (en) * 2015-12-10 2017-06-20 杭州海康威视数字技术股份有限公司 The methods, devices and systems of destination object are searched based on CCTV camera
CN107423674A (en) * 2017-05-15 2017-12-01 广东数相智能科技有限公司 A kind of looking-for-person method based on recognition of face, electronic equipment and storage medium

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101701814A (en) * 2009-11-04 2010-05-05 中兴通讯股份有限公司 Method for judging spatial position of target by linkage of multi-cameras and system thereof
WO2012124852A1 (en) * 2011-03-14 2012-09-20 (주)아이티엑스시큐리티 Stereo camera device capable of tracking path of object in monitored area, and monitoring system and method using same
CN103377471A (en) * 2012-04-16 2013-10-30 株式会社理光 Method and device for object positioning, and method and device for determining optimal camera pair
CN103400371A (en) * 2013-07-09 2013-11-20 河海大学 Multi-camera synergistic monitoring equipment and method
CN106878666A (en) * 2015-12-10 2017-06-20 杭州海康威视数字技术股份有限公司 The methods, devices and systems of destination object are searched based on CCTV camera
CN105933650A (en) * 2016-04-25 2016-09-07 北京旷视科技有限公司 Video monitoring system and method
CN106813649A (en) * 2016-12-16 2017-06-09 北京远特科技股份有限公司 A kind of method of image ranging localization, device and ADAS
CN107423674A (en) * 2017-05-15 2017-12-01 广东数相智能科技有限公司 A kind of looking-for-person method based on recognition of face, electronic equipment and storage medium

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110198411A (en) * 2019-05-31 2019-09-03 努比亚技术有限公司 Depth of field control method, equipment and computer readable storage medium during a kind of video capture
CN110198411B (en) * 2019-05-31 2021-11-02 努比亚技术有限公司 Depth of field control method and device in video shooting process and computer readable storage medium
CN110977950A (en) * 2019-11-12 2020-04-10 长沙长泰机器人有限公司 Robot grabbing and positioning method
CN110977950B (en) * 2019-11-12 2021-05-25 长沙长泰机器人有限公司 Robot grabbing and positioning method
CN111860345A (en) * 2020-07-22 2020-10-30 海尔优家智能科技(北京)有限公司 Method and device for determining object position, storage medium and electronic device

Similar Documents

Publication Publication Date Title
CN101689394B (en) Method and system for video indexing and video synopsis
US8879894B2 (en) Pixel analysis and frame alignment for background frames
CN111091091A (en) Method, device and equipment for extracting target object re-identification features and storage medium
CN108388879A (en) Mesh object detection method, device and storage medium
CN112166459A (en) Three-dimensional environment modeling based on multi-camera convolver system
CN101582171B (en) Method and device for creating depth maps
Hinz Detection and counting of cars in aerial images
CN108898617A (en) A kind of tracking and device of target object
CN109086734A (en) The method and device that pupil image is positioned in a kind of pair of eye image
CN111311475A (en) Detection model training method and device, storage medium and computer equipment
CN107832331A (en) Generation method, device and the equipment of visualized objects
CN109101929A (en) A kind of pedestrian counting method and device
CN109102026A (en) A kind of vehicle image detection method, apparatus and system
CN108668096A (en) Management method, device and the video recording equipment of video data
CN114120301A (en) Pose determination method, device and equipment
CN115493612A (en) Vehicle positioning method and device based on visual SLAM
Gloudemans et al. So you think you can track?
CN112446361A (en) Method and equipment for cleaning training data
CN110457998B (en) Image data association method and apparatus, data processing apparatus, and medium
CN110223320B (en) Object detection tracking method and detection tracking device
CN111008294B (en) Traffic image processing and image retrieval method and device
CN110763203A (en) Positioning method and device of urban component and vehicle-mounted mobile measurement system
CN109800685A (en) The determination method and device of object in a kind of video
CN111488771B (en) OCR hooking method, device and equipment
CN114913470A (en) Event detection method and device

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: 20181127

RJ01 Rejection of invention patent application after publication