CN101783015B - Equipment and method for tracking video - Google Patents
Equipment and method for tracking video Download PDFInfo
- Publication number
- CN101783015B CN101783015B CN 200910077056 CN200910077056A CN101783015B CN 101783015 B CN101783015 B CN 101783015B CN 200910077056 CN200910077056 CN 200910077056 CN 200910077056 A CN200910077056 A CN 200910077056A CN 101783015 B CN101783015 B CN 101783015B
- Authority
- CN
- China
- Prior art keywords
- target
- occurs
- foreground area
- foreground
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 230000007246 mechanism Effects 0.000 claims abstract description 11
- 230000008878 coupling Effects 0.000 claims description 48
- 238000010168 coupling process Methods 0.000 claims description 48
- 238000005859 coupling reaction Methods 0.000 claims description 48
- 230000015572 biosynthetic process Effects 0.000 claims description 40
- 230000008569 process Effects 0.000 claims description 24
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000008859 change Effects 0.000 claims description 10
- 230000013011 mating Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 239000000284 extract Substances 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012217 deletion Methods 0.000 claims description 2
- 230000037430 deletion Effects 0.000 claims description 2
- 238000006467 substitution reaction Methods 0.000 claims description 2
- 238000005352 clarification Methods 0.000 claims 2
- 238000012545 processing Methods 0.000 abstract description 10
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 abstract description 2
- 230000000875 corresponding effect Effects 0.000 description 32
- 238000010586 diagram Methods 0.000 description 6
- 238000003780 insertion Methods 0.000 description 4
- 230000037431 insertion Effects 0.000 description 4
- 230000000295 complement effect Effects 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000007796 conventional method Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Images
Abstract
The invention relates to a method and equipment for tracking video. The method includes the following steps: building up a background model for the current frame, picking up the foreground mask, analyzing the connected domain of the foreground mask to obtain the foreground region queue in the current frame, in which the emerged target queue of a piece of recorded emerged target information is kept; judging whether each foreground region in the foreground region queue contains a single target or a plurality of targets, wherein the foreground regions which contain single target are single-target foreground regions and the foreground regions which contain a plurality of targets are multi-target foreground regions; respectively processing the single-target foreground regions and the multi-target foreground regions through different matching and tracking mechanisms to find the corresponding relationship between each target in the emerged target queue and the entire or local part of the foreground region; and updating the emerged target information in the emerged target queue according to the corresponding relationship. The method and the equipment avoid the problem of adhesion of the adjacent objects caused by the visual angle of the camera lens, illumination and noises.
Description
Technical field
The present invention relates to a kind of video tracking Apparatus and method for.
Background technology
In the intelligent video monitoring field, target is extracted and the coupling tracking is most basic step, and this step can be extracted the information of lowermost layer in the video, and offers other more high-rise processing.The performance of this step directly has influence on the performance of subsequent algorithm, if this step poor performance will become the bottleneck of whole system.
In the conventional method, usually adopt background modeling and foreground extraction technology to extract target in the video, and adopt simple matching technique to follow the tracks of target to occur.But the greatest problem of said method is can't cut apart because the target location, video camera visual angle, and the target adhesion problems that causes of shade.That is to say, existing system usually can misdeem to be a target to the two or more targets that are sticked together, and meets when namely bumping when two targets, causes one of them target to follow the tracks of; Then, when two targets that are sticked together were separated, system again can be with one of them target as emerging target, thereby lost the target information of its front.
Summary of the invention
The invention provides a kind of video tracking Apparatus and method for that can overcome the above problems.
In first aspect, the invention provides a kind of video tracing method, comprise: present frame is carried out background modeling and extracts foreground mask, draw foreground area formation in the present frame by foreground mask being carried out connected domain analysis, wherein, keeping the appearance object queue that target information appears in a record; Judge that each foreground area comprises single target or a plurality of target in the described foreground area formation, comprising single target is respectively single goal foreground area and multi-target foreground zone with the foreground area that comprises a plurality of targets; Adopt different coupling follow-up mechanism to process described single goal foreground area with the multi-target foreground zone respectively, find described occur each target and the integral body in described one prospective zone or local corresponding relation in the object queue; Upgrade the appearance target information that occurs in the object queue according to described corresponding relation.
In second aspect, the invention provides a kind of video tracking equipment, comprise: background modeling and foreground mask extraction module, be used for present frame is carried out background modeling and extracts foreground mask, draw foreground area formation in the present frame by foreground mask being carried out connected domain analysis, wherein, keeping the appearance object queue that target information appears in a record; The target numbers determination module is used for judging that described each foreground area of foreground area formation comprises single target or a plurality of target, and comprising single target is respectively single goal foreground area and multi-target foreground zone with the foreground area that comprises a plurality of targets; The coupling tracking module is used for adopting different coupling follow-up mechanism to process described single goal foreground area with the multi-target foreground zone respectively, finds described occur each target and the integral body in described one prospective zone or local corresponding relation in the object queue; The target information update module is used for upgrading the appearance target information that object queue occurs according to described corresponding relation.
The present invention is on the basis of foreground extraction, adopt position and size information coupling target object, overcome the large defective of operand of existing employing tracking, and the target numbers that further comprises according to foreground area, determine whether to adopt the method for tracking to mate, overcome because the adhesion problems of the adjacent objects that camera visual angle, illumination and noise cause.And the size that system of the present invention can own learning objective need not artificial participation, more is convenient to use.In addition, for a plurality of targets that comprise in the new region, adopt detection algorithm to cut apart, occur from the beginning with regard to adhesion even work as target, also can separate.
Description of drawings
Below with reference to accompanying drawings specific embodiments of the present invention is described in detail, in the accompanying drawings:
Fig. 1 is the block diagram of video tracking equipment according to an embodiment of the invention;
Fig. 2 is the process flow diagram that according to an embodiment of the invention self study is processed; And
Fig. 3 is the actual according to an embodiment of the invention process flow diagram of processing of following the tracks of.
Embodiment
Core concept of the present invention is the camera for fixed viewpoint, add up each position in the display foreground zone of its monitoring and the size of target may occur, and for target newly occurring, judge that according to the target sizes that statistics obtains target newly occurring is single target or multiple goal, then adopts respectively different coupling follow-up mechanism to single target and a plurality of targets.The present invention relates to two treatment schemees, one is the self study treatment scheme, and another is actual tracking treatment scheme, and wherein, the result of self study serves actual tracking.
Fig. 1 is according to the block diagram of video tracking equipment of the present invention.As shown in Figure 1, this equipment comprises background modeling and foreground extracting module, the target numbers determination module, and coupling tracking module, and target information update module, wherein, the coupling tracking module comprises matching module and tracking module.
Keep the appearance object queue that target information appears in a record.
Background modeling and foreground mask extraction module are used for present frame is carried out background modeling and extracts foreground mask, draw foreground area formation in the present frame by foreground mask being carried out connected domain analysis.
The target numbers determination module is used for judging that described each foreground area of foreground area formation comprises single target or a plurality of target, comprises single target and is known as respectively single goal foreground area and multi-target foreground zone with the foreground area that comprises a plurality of targets.
The coupling tracking module is used for adopting different coupling follow-up mechanism to process described single goal foreground area with the multi-target foreground zone respectively, finds the described whole or local corresponding relation that target and described one prospective zone occur respectively occurring in the object queue.
The target information update module is used for upgrading the appearance target information that object queue occurs according to described corresponding relation, the with it information of corresponding appearance target appears in the object queue such as upgrading with one prospective zone or its a part of information, wherein, foreground area or its a part of information can comprise its position and size information; And upgrade simultaneously the supplementary that this target occurs, this supplementary also belongs to and target information occurs, can comprise presenting number of times, losing frame number etc. of target occurring.
Fig. 2 is the process flow diagram that according to an embodiment of the invention self study is processed.
On the one hand, in tracing process, carry out following self study always and process, and learning outcome is served actual tracing process.
As shown in Figure 2, the flow process that self study is processed comprises: at first, the picture frame of inputting is carried out background modeling and extracts foreground mask, foreground mask is carried out connected domain analysis, draw present frame and comprise a plurality of foreground area, namely set up the foreground area formation in the present frame; Then according to the appearance object queue of keeping in the present frame and the foreground area formation that draws, the foreground area in the foreground area formation and the appearance target that occurs in the object queue are mated, draw foreground area and the corresponding relation that target occurs; Upgrade the information that target occurs according to described corresponding relation; Determine to occur whether simple target of target according to the multiframe information that target occurs; Yardstick to the simple target that draws is added up, and draws the yardstick probability model of simple target.The yardstick probability model can be used for aforementioned target numbers determination module to single target or the judgement of a plurality of targets.
Below, the flow process that self study of the present invention is processed is described in detail.
The 201st step, the processing of carrying out background modeling and extracting foreground mask, foreground mask carried out connected domain analysis after, obtain present frame and contain altogether M foreground area, namely set up the foreground area formation of present frame.
In order to record the relevant information of the target that occurred, can keep one in the system and be used for preserving the appearance object queue that target occurs, this formation is initialized as sky, namely do not comprise any target information, the 202nd step of system can be determined foreground area obtained above and the corresponding relation of target occur, and adopt the information updating of foreground area target information to occur in the 203rd step.
The 202nd step, adopt matching algorithm to determine to occur the corresponding relation of target and foreground area, specific algorithm is as follows:
The matching degree of each foreground area in target and the described foreground area formation appears in each that calculate in the current appearance object queue of keeping, and represents with matching value.Can adopt the overlapping area of the rectangular area of rectangular area, place that target occurs and foreground area to draw matching degree; Can draw matching degree according to described overlapping area and the ratio that the rectangular area area of target occurs; Can draw matching degree according to the ratio of the rectangular area area of the rectangular area area that target occurs and foreground area.At last, set up a matching degree matrix with each matching value that target and each foreground area occur.In a further advantageous embodiment, also can utilize the rectangular area of appearance target of prediction and the rectangular area of the foreground area in the present frame to draw matching degree, namely according to the target position in each frame and size information before present frame occurring, can adopt but be not limited to kalman (Kalman) wave filter and set up its parameter model, position and the size of target in present frame appears in prediction, the rectangular area of target in present frame appears in i.e. prediction, then when calculating matching degree, adopt the rectangular area of foreground area in prediction rectangular area that target occurs and the present frame to compare.
After having determined the matching degree of target and each foreground area respectively to occur, can according to but be not limited to following mode and determine corresponding relation:
In the matching degree matrix, find out maximum matching value, think that this maximum matching value corresponding appearance target and foreground area are complementary.Then, all relevant with described coupling foreground area and relevant with the appearance target of described coupling matching degree value are got rid of outside the scope of next time searching maximum matching value, namely from the candidate who seeks maximum matching degree, delete, such as, the matching degree that the appearance target of described coupling foreground area column and described coupling is expert at is set to 0.Maximum matching value is sought in continuation in the matching degree matrix, until do not have the foreground area of coupling and target occurs.
Preferably, a smallest match degree threshold value can be set, think that matching value does not mate less than appearance target and the foreground area of this threshold value.
In the 203rd step, upgrade target information according to the corresponding relation that target and foreground area occur.
The target information that initialization occurs in the object queue is sky; If the current object queue that occurs thinks then that for empty all foreground area all do not have corresponding target;
Target information can comprise position and the size information of target, and presents number of times and lose frame number information.
For target and the foreground area of determining the coupling corresponding relation, with the target information of the foreground area information updating coupling of coupling, and the number of times that presents of target added 1, lose frame number and be set to 0, wherein, described foreground area information can comprise its position and size information.
For there not being foreground area and the target of mating corresponding relation, to occur not having in the object queue frame number of losing of the target of coupling to add 1, do not add to and occur in the object queue as target newly occurring there being the foreground area of coupling in the foreground area formation, and the frame number of losing of this new interpolation target is set to 0, present number of times and be set to 1.If target present number of times greater than its predetermined threshold value, think that this target is a real goal, thereby just it processed in the 204th step below, the 205th step.If target lose frame number greater than its predetermined threshold value, think that this target loses, it is carried out frame losing processes, namely from object queue occurs, delete.
In the 204th step, according to target multiframe information, determine the whether single target that occurs of target.
In the situation that known target information in multiframe can have a lot of methods to judge whether it is the single target that occurs.
Consider that the same state of target between consecutive frame that occur has continuity, a kind of mode is for to judge according to the intensity of variation that the information of target in consecutive frame occurs whether its state has continuity and determine that this target occurs and whether is simple target.
And satisfy the size that successional target information comprises target, and the position, the information such as speed, wherein, the size of target can be target width, object height, perhaps target area.And for adopting minimum boundary rectangle to describe the situation of target, described target width/highly/area is the width// area of the minimum boundary rectangle in target place.
A kind of embodiment is as follows:
Adopt target width or changing value highly and predetermined threshold value comparison in adjacent two frames, if greater than threshold value, think that then the unexpected variation of size has occured target, thinks that its state does not have continuity, thereby think that it is not a simple target, but the merging of target or has separately occured.Only have when target in all consecutive frames the marked change of size occurs not all, think that just target has continuity, be simple target.
A kind of more excellent embodiment judges for the method that adopts position and size information to combine whether the dbjective state of adjacent two frames has continuity.That is to say, adopt the rectangle width of same target in consecutive frame, height and central point are determined the degree of its state variation, determine whether it has continuity.
A kind of position and size information simply utilized determines whether target has successional mode and be: adopt absolute value and the predetermined threshold value of the area difference of target in adjacent two frames to compare, if greater than threshold value, then thinking does not have continuity, otherwise thinks to have continuity.
A kind of concrete compute mode is as follows: hypothetical target corresponding rectangle frame in adjacent two frames is respectively R
1(cx1, cy1, w1, h1) and R
2(cx2, cy2, w2, h2), cx1 wherein, cx2 is respectively the horizontal ordinate of the central point of two rectangle frames, cy1, cy2 is respectively the ordinate of the central point of two rectangle frames, w1, w2 are respectively the width of two rectangle frames, h1, h2 is respectively the height of two rectangle frames, and the distance between the central point of these two rectangle frames is dis=sqrt ((cx1-cx2) so
2+ (cy1-cy2)
2).Thus, can define intensity of variation is:
Wherein, sqrt is extracting operation, and min is for getting the medium and small value computing of two numbers, and max is for getting large value computing in two numbers, and exp is for taking from right exponent arithmetic, and DR and SR are default constant, and the better span of DR is [0.3,3], and the better span of SR is [0.5,2].Adopt intensity of variation obtained above and threshold ratio, if at intensity of variation described in certain consecutive frame greater than threshold value, think that then state does not have continuity, it or not simple target, if all less than threshold value, think then that state has continuity at intensity of variation described in all frames, it is simple target.
In another example, the information of target in present frame that also can obtain with the target information prediction of each frame of front, and adopt the information of forecasting and the real information of target in present frame that obtain to judge relatively whether its state has continuity, and then judge whether this target is same object.A kind of decision procedure is according to target information in each frame before present frame, adopts kalman (Kalman) wave filter to set up the target information model, and the information of target of prediction in next frame.Then judge the continuity of information of forecasting and the current real information of target, and then judge whether target is simple target.
In addition, also can determine whether target is simple target according to the overall variation degree of target multiframe information.A kind of mode for the standard of calculating target multiframe information and threshold ratio, if greater than threshold value, then think not to be simple target, otherwise, think simple target.
In the 205th step, the target scale statistical module is added up the yardstick of simple target according to the simple target result of determination, obtains the yardstick probability model of diverse location place simple target.
The yardstick of target can be for the width of target, highly, girth or area, be used for weighing the big or small degree of target.
According to the projective transformation principle, same target pixel size of diverse location in image is different, therefore, need to be the probability model of each different target scale of position statistics, referred to as the yardstick probability model, this model description the probability distribution of yardstick of this position target.
A kind of simple method is to be target scale probability model of each pixels statistics.But the defective of the method is that the data volume of operand and storage is all larger.A kind of better method is at first being divided into image different subregions, and simple mode is for to be divided into respectively P with image along the horizontal and vertical direction, Q part, thus it is regional that image-region is divided into P * Q one's share of expenses for a joint undertaking.Can certainly adopt the mode that is not five equilibrium to divide subregion.Be different subregions, adopt the probability model of this this target information of location of Information Statistics that falls into this regional target.Judge whether target falls into this regional mode and can select, and judges whether the central point of this target falls into this zone, if fall into, thinks that then target falls into this zone.
Above-mentioned probability model also has a variety of selections, such as the mode that can be adopted as a Gauss model of every sub regions statistics.But, because the target in the image may comprise a plurality ofly, such as existing people, vehicle is arranged again, therefore, adopt a Gauss model can not react the different big or small of different target.A kind of more effective mode is for adopting gauss hybrid models to carry out probability statistics.The mode of statistics target scale probability distribution can also be selected the mode of the histogram distribution of statistical yardstick.
Adopt to divide subregion and adopt gauss hybrid models to carry out the embodiment of probability statistics as follows:
At first, whole image is divided into a plurality of zonules, is GMM model of each zonule initialization.Secondly, with simple target in multiframe information width and highly form one group of parameter, this parameter group is inserted the GMM model of this target's center pixel zonule of living in.
If this GMM model is not also set up gaussian kernel, then set up a gaussian kernel for this initialized GMM model, the average of this gaussian kernel is this parameter group, and setting its covariance matrix value is default value, and setting its weight is 1.
If there has been gaussian kernel in this GMM model, then to judge and insert parameter value and the mahalanobis distance at this gaussian kernel center and the relation of predetermined threshold value, the size of described threshold value and zonule is relevant.If the minimum mahalanobis distance of all gaussian kernel and insertion parameter value is less than threshold value in this GMM model, then think and insert parameter value and this gaussian kernel coupling, adopt and insert average and the covariance matrix value that parameter value upgrades this gaussian kernel, and the weight of this gaussian kernel is added 1; If the minimum mahalanobis distance of all gaussian kernel and insertion parameter value is greater than threshold value in this GMM model, think that then this insertion parameter value does not meet any existing gaussian kernel, then a newly-built gaussian kernel in this GMM model, and set its average and be this insertion parameter value, its covariance matrix is default value, and setting its weight is 1.
Further, the maximum number that can set gaussian kernel in the GMM model is U, and U is that the number that may occur the object yardstick in the scene adds 1, and such as occurring car and truck two class yardsticks in the scene, the value of then setting U is 3.Thereby, when in the GMM model, needing a newly-built gaussian kernel, if existing gaussian kernel number has reached limit value U in this GMM model, then delete first the gaussian kernel of its weight minimum, and then with newly-built gaussian kernel as new gaussian kernel.
Further, in order to upgrade faster, namely forget target component in the past, can be before each frame be processed, the weight with all already present gaussian kernel becomes original α doubly first, i.e. w
N+1=α * w
n, carry out again above-mentioned processing, wherein α has determined the speed forgotten, it is 0 to 1 constant, w
N+1Be the weight of the gaussian kernel of present frame, w
nWeight for the gaussian kernel of former frame.
Further, in order to get rid of the interference of noise, more excellent mode is that the GMM model that further above-mentioned study is drawn is processed with filtering noise before yardstick probability model obtained above is used for actual the tracking.A kind of mode is as follows: in the definition GMM model normalized weight of each gaussian kernel be this gaussian kernel weight divided by all gaussian kernel weights in the model with, if normalized weight greater than setting threshold, such as 5%, thinks that then this gaussian kernel is effective; Otherwise, think that the occurrence frequency of the corresponding target of this gaussian kernel is too little, do not consider, namely this gaussian kernel is invalid, deletes from mixture model.
By above-mentioned processing, obtain the gauss hybrid models of diverse location place simple target, then described gauss hybrid models is applied in the actual tracking processing.
Fig. 3 is the actual according to an embodiment of the invention process flow diagram of processing of following the tracks of.
On the other hand, carrying out simultaneously actual tracking processes.
As shown in Figure 3, at first foreground mask is carried out connected domain analysis, draw present frame and comprise a plurality of foreground area, namely set up the foreground area formation in the present frame; Then the learning outcome that draws according to self study, namely the yardstick probability model of the simple target at diverse location place is judged in the foreground area formation to comprise single target or a plurality of target in each foreground area; According to judged result, respectively simple target is adopted different coupling follow-up mechanism with multiple goal, adopt matching algorithm to determine to occur the corresponding relation of target and described foreground area to the single goal foreground area, adopt track algorithm to determine to occur the corresponding relation of the regional area of target and described foreground area to multi-target foreground zone, final updating target information and with its output.
Below, actual flow process of following the tracks of of the present invention is described in detail.
The 301st step, adopt the foreground extraction technology to obtain foreground mask, and and then adopt connected domain analysis method to obtain foreground area;
Keeping one object queue occurs and target information occurs with preservation;
In the 302nd step, determine to comprise in the foreground area single target or a plurality of target according to the yardstick information of each foreground area.
The simplest a kind of mode is to adopt yardstick and the predetermined threshold value mode relatively of foreground area, if the yardstick of foreground area, thinks then that this foreground area is the single goal zone less than threshold value, otherwise, think the multiple goal zone.
A kind of more excellent decision method is, judges that according to the simple target yardstick probability model that yardstick and the learning process of foreground area obtains foreground area comprises single target or a plurality of target.
A kind of feasible method is input in the simple target yardstick probability model obtained above for the yardstick with foreground area, and the yardstick that obtains foreground area meets the probability of simple target yardstick probability model.If described probability, thinks then that target is not single target less than threshold value, otherwise, think that target is single target.
For the method that adopts gauss hybrid models as the yardstick probability model, better mode is for only containing a target in the supposition one prospective zone, the yardstick input information of this foreground area in the GMM model at this place, target position, is found the minimum mahalanobis distance of each effective gaussian kernel of yardstick information and gauss hybrid models.If this distance, thinks then that current foreground area only comprises the target of the corresponding yardstick of this gaussian kernel less than threshold value; Otherwise, think that current region comprises a plurality of targets.
The 303rd step, different coupling follow-up mechanism is adopted respectively in single goal foreground area and multi-target foreground zone, that is, the single goal foreground area is adopted matching algorithm, track algorithm is adopted in the multi-target foreground zone.
So-called matching algorithm is made foreground area as a whole exactly, determines the corresponding relation of target in the whole and object queue of the foreground area that obtains; And track algorithm is not then made foreground area as a wholely, but adopts topography's range searching algorithm, determines to be arranged in the regional area image the most close with target object queue on the foreground area.
In the 303-1 step, the single goal foreground area is handled as follows:
Each the matching degree of target and each single goal foreground area occurs in the calculating present frame.Can adopt the overlapping area of the rectangular area of rectangular area that target occurs and foreground area to draw matching degree; Or draw matching degree according to the ratio of the area in described overlapping area and target rectangle zone; Or draw matching degree according to the ratio of target area and region area.At last, set up a matching degree matrix with each target and each regional matching value.
After having determined the matching degree of target and each single goal foreground area respectively to occur, can according to but be not limited to following mode and determine the single goal foreground area and the corresponding relation of target occurs:
In the matching degree matrix, find out maximum matching value, think that this maximum matching value corresponding appearance target and foreground area are complementary.Then, all matching degree value relevant with described coupling foreground area and that be correlated with described coupling target are got rid of outside the scope of next time searching maximum matching value, namely from the candidate who seeks maximum matching degree, delete, such as, the matching degree that described coupling foreground area column and described coupling target are expert at is set to 0.Maximum matching value is sought in continuation in the matching degree matrix, until do not have foreground area and the target of coupling.
Preferably, a smallest match degree threshold value can be set, think that matching value does not mate less than target and the foreground area of this threshold value.
In the 303-2 step, appearance target and the multi-target foreground zone of not mating is handled as follows:
Adopt track algorithm to determine the appearance target of not mating and the corresponding relation in multi-target foreground zone.Tracking has a lot of prior aries, preferably, can adopt mean shift (mean shift) or particle filter (Particle Filter) algorithm.This foreground area is regional as mother, and search for therein the subregion that mates most with each target.Preferably, the target sizes of current location can be attached in the mean shift searching algorithm and go.After finding the coupling subregion, the information of this mother zone of deletion and employing coupling subregion is come more fresh target from the foreground area formation.Then, unmatched residue foreground area is carried out connected domain analysis in should the mother zone, find the rectangular area that wherein comprises and it is added in the foreground area formation as new foreground area, add simultaneously, adopt the single goal decision method in the 302nd step to judge that this foreground area is single goal foreground area or multi-target foreground zone.
Continued to adopt the 303rd step that the remaining foreground area of not mating in target and the foreground area formation was processed, until do not find appearance target and the foreground area of new correspondence, finished for the 303rd step and process.
Disposal route to the multi-target foreground zone also can adopt following method, be to obtain the GMM model during tracking module is processed according to self study to rebulid the foreground area formation, and so that in the newly-established foreground area formation each zone comprise simple target, then adopt the matching algorithm in 303-1 step that target is mated tracking, concrete execution in step is as follows.
At first determine the target numbers that all foreground area in the foreground area formation comprise in width and short transverse, this need to all be handled as follows each foreground area in all foreground area:
Suppose that the maximum target number that the one prospective zone comprises at Width is M, the maximum target number that comprises in short transverse is N;
Calculate successively (
,
), m=1 wherein, 2...M; N=1,2...N with its substitution Gauss model, draws the matching degree of each foreground area and GMM model, wherein w
iBe the width of i foreground area, h
iBe its height.In the matching degree result of each foreground area and GMM model, find out m corresponding to maximum matching degree and n, be respectively m
MaxAnd n
Max, think that this foreground area comprises m at Width
MaxIndividual target comprises n in short transverse
MaxIndividual target.
If m
MaxAnd n
MaxIn any one greater than 1, then this foreground area is divided equally according to Width and short transverse and is m
Max* n
MaxIndividual rectangle.With this m
Max* n
MaxIndividual rectangle adds the foreground area formation to as new foreground area, and deletes the former foreground area of being divided equally.
If m
MaxAnd n
MaxBe 1 all, then it does not processed.
Then, adopt matching process in 303-1 step to determine to occur the corresponding relation of single goal foreground area in target and the new foreground area formation.
The 304th step is according to the corresponding relation renewal target information of above-mentioned the 303rd appearance target that obtains of step with foreground area.
The target information that initialization occurs in the object queue is sky; If the current object queue that occurs thinks then that for empty all foreground area all do not have corresponding target;
Target information can comprise position and the size information of target, and presents number of times and lose frame number information.
For target and the foreground area of determining the coupling corresponding relation, use the target information of the foreground area information updating coupling of coupling, and the number of times that presents of target is added 1, lose frame number and be set to 0.
For there not being foreground area and the target of mating corresponding relation, will occur not having in the object queue frame number of losing of the target of coupling to add 1.
Do not adopt following method to process to mating foreground area: only not comprise a target if mate foreground area, then it is added to as fresh target and object queue occurs, and the frame number of losing of this new interpolation target is set to 0, present number of times and be set to 1; Otherwise, adopt algorithm of target detection that described zone is analyzed, each target that is wherein comprised is also added it to and object queue occurred, and the frame number of losing of this new interpolation target is set to 0, presents number of times and is set to 1.Algorithm of target detection can be any prior art, such as pedestrian detection algorithm, vehicle detecting algorithm etc.
If target lose frame number greater than its predetermined threshold value, think that this target loses, it is carried out frame losing processes, namely from object queue occurs, delete.
Because the coupling foreground area after processing through above-mentioned matching tracking method all only comprises a target, overcome by shade, the problem of the foreground object adhesion that noise causes has improved the effect of tracking and matching, has improved prior art.By the top description of reality being followed the tracks of processing, should be appreciated that in actual tracing process, can move simultaneously self-learning module, and self-learning module is constantly updated actual tracking and matching module by upgrading the yardstick probability model, improves constantly system performance.And above-mentioned mechanism does not need manual intervention, fully automatically finishes, and has very high practical value.
Obviously, under the prerequisite that does not depart from true spirit of the present invention and scope, the present invention described here can have many variations.Therefore, the change that all it will be apparent to those skilled in the art that all should be included within the scope that these claims contain.The present invention's scope required for protection is only limited by described claims.
Claims (24)
1. video tracing method comprises:
Present frame is carried out background modeling and extracts foreground mask, draw foreground area formation in the present frame by foreground mask being carried out connected domain analysis, wherein, keeping the appearance object queue that target information appears in a record;
Judge that each foreground area comprises single target or a plurality of target in the described foreground area formation, comprising single target is respectively single goal foreground area and multi-target foreground zone with the foreground area that comprises a plurality of targets;
Adopt different coupling follow-up mechanism to process described single goal foreground area with the multi-target foreground zone respectively, find the described whole or local corresponding relation that target and described foreground area occur respectively occurring in the object queue;
Upgrade the appearance target information that occurs in the object queue according to described corresponding relation;
Carry out described foreground area according to the yardstick information of foreground area and comprise single target or the judgement of a plurality of targets;
The yardstick probability model that meets according to yardstick information and the foreground area of foreground area carries out described foreground area and comprises single target or the judgement of a plurality of targets, described yardstick probability model is to judge that according to the described target information that occurs this target occurs and whether is the single target that occurs, and then the described single yardstick that target occurs added up obtains;
Describedly judge according to target information occurring whether the single step that target occurs comprises for it:
Whether have continuity and judge to have constantly continuity if this target occurs according to the information of target in multiframe occurring, think that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs; Or
By judging according to the information change degree of target in consecutive frame occurring whether its state has continuity, thereby determine whether this target occurs is the single target that occurs, wherein, if this state that target occurs has continuity, determine that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs.
2. method according to claim 1, wherein, by judging according to the information change degree of target in consecutive frame occurring whether its state has continuity, thereby determine whether this target occurs is that the single step that target occurs comprises:
Suppose that a rectangle frame that target correspondence in adjacent two frames occurs is respectively R
1(cx1, cy1, w1, h1) and R
2(cx2, cy2, w2, h2), cx1 wherein, cx2 is respectively the horizontal ordinate of the central point of two rectangle frames, cy1, cy2 is respectively the ordinate of the central point of two rectangle frames, w1, w2 are respectively the width of two rectangle frames, h1, h2 is respectively the height of two rectangle frames, and the distance between the central point of these two rectangle frames is dis=sqrt ((cx1-cx2)
2+ (cy1-cy2)
2); Defining described information change degree is
Wherein, sqrt is extracting operation, and min is for getting the medium and small value computing of two numbers, and max is for getting large value computing in two numbers, and exp is for taking from right exponent arithmetic, and DR and SR are default constant,
Described information change degree and predetermined threshold are compared, if described information change degree is greater than described threshold value, think that then this state that target occurs does not have continuity, it or not simple target, if and in described information change degree less than described threshold value, thinking that then this state that target occurs has continuity, is simple target.
3. method according to claim 1, wherein, the described target information that occurs is information in the multiframe of target before present frame to occur according to this, predict that the target information of target in present frame appears in this that obtain; And/or
The described target information that occurs comprises yardstick information and/or positional information and/or the velocity information that target occurs.
4. method according to claim 1, wherein, the described single yardstick that target occurs is added up the step that obtains the yardstick probability model comprise:
Image-region is divided into a plurality of subregions, and respectively according to the single yardstick that target occurs that occurs in every sub regions, statistics draws and singlely on this subregion the yardstick probability model that target meets occurs.
5. method according to claim 1, wherein, described yardstick probability model is gauss hybrid models.
6. according to claim 1 or 4 described methods, wherein, according to the yardstick information of foreground area, and the yardstick probability model that meets of foreground area carries out, and described foreground area comprises single target or the determining step of a plurality of targets comprises:
The single yardstick probability model that target occurs with its place subregion of yardstick input information of foreground area, calculate the probability that it meets described yardstick probability model, and judge that according to the described probability that meets this foreground area comprises single target or comprises a plurality of targets.
7. according to claim 4 or 5 described methods, wherein, according to the yardstick information of foreground area, and the yardstick probability model that meets of foreground area carries out, and described foreground area comprises single target or the determining step of a plurality of targets comprises:
Gauss hybrid models with its place subregion of yardstick input information of each foreground area, find out the minimum mahalanobis distance of each gaussian kernel of described yardstick information and each gauss hybrid models, if described distance is less than threshold value, judge that then this subregion only comprises single target, otherwise think that described foreground area comprises a plurality of targets.
8. method according to claim 7, wherein, described gaussian kernel is effective gaussian kernel, whether effectively step is as follows to judge in the gauss hybrid models gaussian kernel:
The normalized weight of gaussian kernel is that the weight of this gaussian kernel is divided by all gaussian kernel weight sums in this gauss hybrid models, if the normalized weight of described gaussian kernel, thinks then that this gaussian kernel is effective greater than predetermined threshold value in the definition gauss hybrid models.
9. method according to claim 1, wherein, the step that adopts different coupling follow-up mechanism to process to described single goal foreground area and multi-target foreground zone respectively comprises:
For each single goal foreground area, it is mated with the described target that respectively occurs that occurs in the object queue as a whole, determine to occur the corresponding relation of target and described foreground area; And/or
For each multi-target foreground zone, search for described the appearance within it and target respectively occurs in the object queue, determine to occur the corresponding relation of the regional area of target and described foreground area.
10. method according to claim 9, wherein, described coupling step comprises:
According to the overlapping area that target area and foreground area occur, or according to described overlapping area and the ratio that the target area area occurs, or according to the ratio that target area area and foreground area area occur, obtain occurring the matching degree matrix of target and foreground area;
Target and foreground area appear according to described matching degree matrix matching.
11. method according to claim 10, wherein, the step of coupling target and foreground area comprises:
In described matching degree matrix, search maximum matching degree value, think and mate between the target that has maximum matching value and the zone, and will be relevant with described matching area and with described coupling target all relevant matching degree value get rid of outside seek scope next time, repeat and above-mentionedly search the step of maximum matching value until do not have zone and the target of coupling.
12. method according to claim 1 wherein, target information occurs and also comprises and present number of times, lose frame number, the step that the appearance target information in the object queue appears in described renewal comprises:
With appearance target information corresponding to the foreground area information updating of correspondence, and this number of times that presents that target occurs added 1, lose frame number and be set to 0;
To not exist the frame number of losing of the appearance target of corresponding foreground area to add 1, the foreground area that do not exist correspondence target to occur is added to and object queue occurred as target newly occurring, and the described new frame number of losing that target occurs is set to 0, present number of times and be set to 1;
If there is target present number of times greater than predetermined threshold value, judge that this target occurs is real goal; If there is target lose frame number greater than predetermined threshold value, then it is deleted from object queue occurs.
13. method according to claim 10, wherein, the described target area that occurs is according to the information of target in multiframe before occurring, prediction obtain this target area of target in present frame appears.
14. method according to claim 9 is described for each multi-target foreground zone, searches for described the appearance within it target respectively to occur in the object queue, the step of corresponding relation of determining to occur the regional area of target and described foreground area comprises:
Search the subregion that target is mated most occurs with described in described foreground area, and the foreground area at the described coupling subregion of deletion place target information occurs with the information updating of mating subregion from the foreground area formation;
The remaining area that does not mate in the described matching area is carried out connected domain analysis, find after the foreground area that wherein comprises and with it and add in the foreground area formation as new foreground area, and further judge that according to the yardstick probability model each foreground area comprises single target or a plurality of target in the described foreground area formation.
15. method according to claim 14 also comprises:
The zone that comprises single target of coupling is not added to as fresh target and object queue occurred, and target detection is carried out in the zone that comprises a plurality of targets of coupling not, obtain its each target that comprises and each target added to object queue occurring.
16. method according to claim 1 wherein, finds the step of the corresponding relation of the regional area that target and described multi-target foreground zone occur to comprise:
Set up a new foreground area formation according to yardstick probability model and described foreground area formation, so that each zone only comprises simple target in the new foreground area formation, adopt matching algorithm that it is followed the tracks of to described simple target.
17. method according to claim 16, wherein, the step of setting up new foreground area formation comprises:
Image-region is divided into a plurality of subregions along the horizontal and vertical direction, adds up the single yardstick probability model that target occurs on every sub regions;
Suppose that the maximum target number that the one prospective zone comprises at Width is M, the maximum target number that comprises in short transverse is N;
Calculate successively
M=1 wherein, 2...M; N=1,2...N is with the described yardstick probability model of the described foreground area of its substitution place subregion, draw the probability of the described yardstick probability model of this region conforms, wherein wi is the width in i zone, and hi is its height, find out maximum and meet m corresponding to probability and n, be designated as respectively m
MaxAnd n
Max, think that this foreground area comprises m at Width
MaxIndividual target comprises n in short transverse
MaxIndividual target;
If m
MaxAnd n
MaxIn any one greater than 1, then should be divided into m according to Width and short transverse in the zone
Max* n
MaxIndividual rectangle is with this m
Max* n
MaxIndividual rectangle adds new foreground area formation to as new zone, and deletes the former foreground area of being divided equally;
If m
MaxAnd n
MaxAll be 1, then this zone directly added in the new foreground area formation.
18. method according to claim 1, wherein, described yardstick information comprises the width that target area or foreground area occur, highly, and area, the combination of one or more in all long messages.
19. method according to claim 9 wherein, for each multi-target foreground zone, is searched for described the appearance within it and target respectively occurred in the object queue, the step of corresponding relation of determining to occur the regional area of target and described foreground area comprises:
Target detection is carried out in described multi-target foreground zone, obtain wherein respectively occurring the regional area at target place, adopt matching algorithm to determine itself and the corresponding relation that target occurs to described regional area.
20. a video tracking equipment comprises:
Background modeling and foreground mask extraction module, be used for present frame is carried out background modeling and extracts foreground mask, draw foreground area formation in the present frame by foreground mask being carried out connected domain analysis, wherein, keeping the appearance object queue that target information appears in a record;
The target numbers determination module is used for judging that described each foreground area of foreground area formation comprises single target or a plurality of target, and comprising single target is respectively single goal foreground area and multi-target foreground zone with the foreground area that comprises a plurality of targets;
The coupling tracking module is used for adopting different coupling follow-up mechanism to process described single goal foreground area with the multi-target foreground zone respectively, finds the described whole or local corresponding relation that target and described foreground area occur respectively occurring in the object queue;
The target information update module is used for upgrading the appearance target information that object queue occurs according to described corresponding relation;
Described target numbers determination module comprises:
The simple target determination module is used for judging according to the described target information that occurs whether it is the single target that occurs;
The target scale statistical module obtains described yardstick probability model for the described single yardstick that target occurs is added up;
Described simple target determination module, be used for whether having continuity and judging to have constantly continuity if this target occurs according to the information of target in multiframe occurring, think that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs; Or
Be used for by judging in the information change degree of consecutive frame whether its state has continuity according to target occurring, thereby determine whether this target occurs is the single target that occurs, wherein, if this state that target occurs has continuity, determine that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs;
Described target scale statistical module is used for image-region is divided into a plurality of subregions, and respectively according to the single yardstick that target occurs that occurs in every sub regions, statistics draws and singlely on this subregion the yardstick probability model that target meets occurs.
21. equipment according to claim 20, wherein, described target numbers determination module, be used for the single yardstick probability model that target occurs with its place subregion of yardstick input information of foreground area, calculate the probability that it meets described yardstick probability model, and judge that according to the described probability that meets this foreground area comprises single target or comprises a plurality of targets.
22. equipment according to claim 20, wherein, described coupling tracking module comprises:
The object matching module is used for for each single goal foreground area, and it is mated with the described target that respectively occurs that occurs in the object queue as a whole, determines to occur the corresponding relation of target and described foreground area; And/or
Target tracking module is used for for each multi-target foreground zone, searches for described the appearance within it target respectively to occur in the object queue, determines to occur the corresponding relation of the regional area of target and described foreground area.
23. equipment according to claim 20, wherein, target information occurring also comprises and presents number of times, loses frame number, described target information update module, be used for corresponding appearance target information corresponding to foreground area information updating, and this number of times that presents that target occurs added 1, lose frame number and be set to 0; Or
The frame number of losing for the appearance target that will not have corresponding foreground area adds 1, the foreground area that do not exist correspondence target to occur is added to and object queue occurred as target newly occurring, and the described new frame number of losing that target occurs is set to 0, present number of times and be set to 1; Or
Be used for if there is target present number of times greater than predetermined threshold value, judge that this target occurs is real goal; If there is target lose frame number greater than predetermined threshold value, then it is deleted from object queue occurs.
24. a video tracing method comprises:
Keep one and object queue occurs, the described object queue that occurs comprises and one or morely target occurs and clarification of objective information respectively occurs;
Obtain the foreground area formation of present frame, described foreground area formation comprises the characteristic information of one or more foreground area and each foreground area;
Judge that each foreground area in the described foreground area formation is to comprise the single single goal foreground area that target occurs, still comprise a plurality of multi-target foreground zones that target occurs;
For each single goal foreground area, it is mated with the described target that respectively occurs that occurs in the object queue as a whole, for each multi-target foreground zone, search for described the appearance within it and target respectively occurs in the object queue;
Upgrading the described appearance target that occurs in the object queue according to coupling and Search Results reaches and clarification of objective information respectively occurs;
Described characteristic information comprises yardstick information, positional information, the velocity information of target;
Judge that each foreground area in the described foreground area formation is to comprise the single single goal foreground area that target occurs, comprise that still a plurality of multi-target foreground zones that target occurs are specially:
Carry out described foreground area according to the yardstick information of foreground area and comprise single target or the judgement of a plurality of targets;
The yardstick probability model that meets according to yardstick information and the foreground area of foreground area carries out described foreground area and comprises single target or the judgement of a plurality of targets, described yardstick probability model is to judge that according to the described target information that occurs this target occurs and whether is the single target that occurs, and then the described single yardstick that target occurs added up obtains;
Describedly judge according to target information occurring whether the single step that target occurs comprises for it:
Whether have continuity and judge to have constantly continuity if this target occurs according to the information of target in multiframe occurring, think that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs; Or
By judging according to the information change degree of target in consecutive frame occurring whether its state has continuity, thereby determine whether this target occurs is the single target that occurs, wherein, if this state that target occurs has continuity, determine that then this target occurs is the single target that occurs, otherwise, think that it is not the single target that occurs.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910077056 CN101783015B (en) | 2009-01-19 | 2009-01-19 | Equipment and method for tracking video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910077056 CN101783015B (en) | 2009-01-19 | 2009-01-19 | Equipment and method for tracking video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101783015A CN101783015A (en) | 2010-07-21 |
| CN101783015B true CN101783015B (en) | 2013-04-24 |
Family
ID=42523001
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910077056 Active CN101783015B (en) | 2009-01-19 | 2009-01-19 | Equipment and method for tracking video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101783015B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102163280B (en) * | 2011-04-12 | 2012-09-26 | 华中科技大学 | Method for identifying, tracking and converting target based on confidence degree and multi-frame judgement |
| CN102340620B (en) * | 2011-10-25 | 2013-06-19 | 重庆大学 | Mahalanobis-distance-based video image background detection method |
| CN104200493B (en) * | 2014-09-05 | 2017-02-01 | 武汉大学 | Similarity measurement based real-time target tracking algorithm |
| CN105118072A (en) * | 2015-08-19 | 2015-12-02 | 西华大学 | Method and device for tracking multiple moving targets |
| CN106355603B (en) * | 2016-08-29 | 2019-10-22 | 深圳市商汤科技有限公司 | Human body tracing method and human body tracking device |
| CN106780555A (en) * | 2016-12-01 | 2017-05-31 | 中科唯实科技（北京）有限公司 | A kind of sane motion target tracking method of high speed |
| CN107392936B (en) * | 2017-06-09 | 2020-06-05 | 广东光阵光电科技有限公司 | Target tracking method based on meanshift |
| CN110717361A (en) * | 2018-07-13 | 2020-01-21 | 长沙智能驾驶研究院有限公司 | Vehicle parking detection method, preceding vehicle start reminding method and storage medium |
| CN109410243A (en) * | 2018-10-16 | 2019-03-01 | 中电科新型智慧城市研究院有限公司 | Based on the overlapping multi-object tracking method with template matching in region |
| CN110517288B (en) * | 2019-07-23 | 2021-11-02 | 南京莱斯电子设备有限公司 | Real-time target detection tracking method based on panoramic multi-path 4k video images |
| CN111539993B (en) * | 2020-04-13 | 2021-10-19 | 中国人民解放军军事科学院国防科技创新研究院 | Space target visual tracking method based on segmentation |
| CN112989997A (en) * | 2021-03-11 | 2021-06-18 | 中国科学技术大学 | 3D target detection method and system based on multi-information fusion |
| CN112907636B (en) * | 2021-03-30 | 2023-01-31 | 深圳市优必选科技股份有限公司 | Multi-target tracking method and device, electronic equipment and readable storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6556708B1 (en) * | 1998-02-06 | 2003-04-29 | Compaq Computer Corporation | Technique for classifying objects within an image |
| CN1738426A (en) * | 2005-09-09 | 2006-02-22 | 南京大学 | Video motion goal division and track method |
| CN101339664A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Object tracking method and system |
-
2009
- 2009-01-19 CN CN 200910077056 patent/CN101783015B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6556708B1 (en) * | 1998-02-06 | 2003-04-29 | Compaq Computer Corporation | Technique for classifying objects within an image |
| CN1738426A (en) * | 2005-09-09 | 2006-02-22 | 南京大学 | Video motion goal division and track method |
| CN101339664A (en) * | 2008-08-27 | 2009-01-07 | 北京中星微电子有限公司 | Object tracking method and system |
Non-Patent Citations (6)
| Title |
|---|
| A Probabilistic Exclusion Principle for Tracking Multiple Objects;John Maccormick et al;《International Journal of Computer Vision》;20001231;第39卷(第1期);全文 * |
| John Maccormick et al.A Probabilistic Exclusion Principle for Tracking Multiple Objects.《International Journal of Computer Vision》.2000,第39卷(第1期),全文. |
| 一种基于背景模型的运动目标检测与跟踪算法;刘亚 等;《信息与控制》;20020831;第31卷(第4期);全文 * |
| 刘亚 等.一种基于背景模型的运动目标检测与跟踪算法.《信息与控制》.2002,第31卷(第4期),全文. |
| 视频图像实时多目标跟踪方法;韩广良 等;《光子学报》;20081130;第37卷;全文 * |
| 韩广良 等.视频图像实时多目标跟踪方法.《光子学报》.2008,第37卷全文. |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101783015A (en) | 2010-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101783015B (en) | Equipment and method for tracking video | |
| CN115601374B (en) | Chromosome image segmentation method | |
| Niknejad et al. | On-road multivehicle tracking using deformable object model and particle filter with improved likelihood estimation | |
| CN101141633B (en) | Moving object detecting and tracing method in complex scene | |
| CN102509078B (en) | Fire detection device based on video analysis | |
| CN101729872B (en) | Video monitoring image based method for automatically distinguishing traffic states of roads | |
| CN102289948B (en) | Multi-characteristic fusion multi-vehicle video tracking method under highway scene | |
| CN109447018A (en) | A kind of road environment visual perception method based on improvement Faster R-CNN | |
| CN105469425A (en) | Video condensation method | |
| CN102073851A (en) | Method and system for automatically identifying urban traffic accident | |
| CN104303193A (en) | Clustering-based object classification | |
| WO2023065395A1 (en) | Work vehicle detection and tracking method and system | |
| CN103034862A (en) | Road snow and rain state automatic identification method based on feature information classification | |
| CN104063885A (en) | Improved movement target detecting and tracking method | |
| CN106934817B (en) | Multi-attribute-based multi-target tracking method and device | |
| CN101980245B (en) | Adaptive template matching-based passenger flow statistical method | |
| CN103971386A (en) | Method for foreground detection in dynamic background scenario | |
| Setchell | Applications of computer vision to road-traffic monitoring | |
| CN105654508A (en) | Monitoring video moving target tracking method based on self-adaptive background segmentation and system thereof | |
| CN105844229A (en) | Method and system for calculating passenger crowdedness degree | |
| CN113763427B (en) | Multi-target tracking method based on coarse-to-fine shielding processing | |
| CN110889421A (en) | Target detection method and device | |
| CN112132071A (en) | Processing method, device and equipment for identifying traffic jam and storage medium | |
| CN113255634A (en) | Vehicle-mounted mobile terminal target detection method based on improved Yolov5 | |
| CN113744316A (en) | Multi-target tracking method based on deep neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171221 Address after: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee after: Zhongxing Technology Co., Ltd. Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee before: Beijing Vimicro Corporation |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee after: Mid Star Technology Limited by Share Ltd Address before: 100083 Haidian District, Xueyuan Road, No. 35, the world building, the second floor of the building on the ground floor, No. 16 Patentee before: Zhongxing Technology Co., Ltd. |