CN104766343B - A kind of visual target tracking method based on rarefaction representation - Google Patents
A kind of visual target tracking method based on rarefaction representation Download PDFInfo
- Publication number
- CN104766343B CN104766343B CN201510142274.9A CN201510142274A CN104766343B CN 104766343 B CN104766343 B CN 104766343B CN 201510142274 A CN201510142274 A CN 201510142274A CN 104766343 B CN104766343 B CN 104766343B
- Authority
- CN
- China
- Prior art keywords
- image
- fragment
- value
- template
- target
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a kind of visual target tracking method based on rarefaction representation, belong to technical field of computer vision.The present invention method be：It is primarily based on target image and determines that follow-up tracking processing needs the judgement dictionary used, match dictionary, gray matrix T, then processing is tracked to each picture frame to be tracked, sample multiple first candidate image sample sets, K representative cluster centres are selected by K mean cluster, and its value of the confidence is calculated based on judgement dictionary, sampling center is set based on maximum the value of the confidence, so as to obtain the second candidate image sample set, N number of the value of the confidence highest candidate image is therefrom selected again, sampled based on matching dictionary by fragment the gray matrix of the candidate image, take with gray matrix T-phase like tracking target of the degree highest candidate image as present frame.The present invention is used for field of intelligent monitoring, and to tracking target carriage change, situations such as ambient lighting changes and blocked is with very strong robustness.
Description
Technical field
The invention belongs to computer vision field, and in particular to field of intelligent monitoring, more particularly to a kind of to be based on sparse table
The visual target tracking shown.
Background technology
View-based access control model target following technology (generally refer to based on video either image sequence target following), be
Target object is detected in a series of image, extracted, recognized and tracked, so that the relevant parameter of target object is obtained,
Such as position, speed, yardstick, track；Further handled and analyzed according to tracking result, realize the behavior to target object
Understand, or complete more higher leveled task.This is the hot fields rapidly emerged, belongs to grinding for computer vision field
Study carefully category, be with a wide range of applications and scientific research value.By the evolution of nearly twenty or thirty year, go out both at home and abroad
Various track algorithms, including some classical algorithms and the innovative algorithm based on these algorithms are showed.
It is different according to the philosophy and technique of track algorithm, these track algorithms can be divided into the tracking of discrimination model
With the tracking of generation model.Track algorithm based on discrimination model regards tracking problem as classification problem, especially in list
In target following, tracking problem is regarded as two classification problems, relatively classical grader there are SVM (Support Vector
Machine) grader, Adaboost grader.The algorithm based on grader of more prevalence has CSK, Struct, CT recently
Scheduling algorithm.For the track algorithm based on generation model, the purpose of tracking is to be searched out in neighborhood and target similarity
Maximum region, actually finds the state in the region, i.e. optimum estimation target maximum with target similarity function, wherein
Relatively effective classic algorithm has Kalman filtering, particle filter, more popular recently to have MTT, LSK scheduling algorithms.
Sparse track algorithm is developed in recent years than a kind of relatively rapid emerging track algorithm, belongs to the tracking of generation model
Method.Because algorithm is the final result that is obtained based on a series of ATL, thus for illumination variation, complex environment and
Posture change etc. all has preferable robustness, such as document " X.Mei and H.Ling. " Robust visual tracking
CN 103440645 A using L1 minimization”.12th International Conference on
Computer Vision, Kyoto, Japan, 2009 (1436-1443) " is still, often whole using target due to ATL
Body template is not therefore good to the situation treatment effect of target occlusion as feature.
Above-mentioned algorithm can carry out the real-time tracking of robust in simple scene mostly.But daily regarded unrestricted
It is still a significant challenge that target is tracked in frequency.Illumination, change in size, block, target rotation, complex background etc. are all brought
Difficult factor.Therefore, a stronger track algorithm of robustness how is designed, can be obtained in the case where condition is more harsh
Obtain and preferably show, be one important problem of computer vision field.
The content of the invention
The present invention proposes a kind of Vision Tracking based on rarefaction representation, to tracking target carriage change, ambient light
According to situations such as changing and block, with very strong robustness, and the situation treatment effect to target occlusion can be improved.
The present invention includes two parts, is configured to track the judgement dictionary D of target, matching dictionary A and Gray Moment first
Battle array T, is then searched and tracking mesh based on judgement dictionary D, matching dictionary A and gray matrix T in candidate image in the current frame
The most like candidate image of mark, determines the target image of currently tracked target, its detailed process is：
Step 1：Determine initialisation image and determine the target image of the initialisation image, in this step, generally take
First two field picture of video either image sequence is initialisation image, and determines the target image (histogram of initialisation image
As block), i.e. To Template, can be obtained according to the initialized location of initialisation image manual setting target image (target sizes,
Position coordinates in image).
Step 2：Based on current target image generation judgement dictionary D, matching dictionary A and To Template gray scale attribute matrix T：
In initialisation image, determining distance objective picture centre P1, (preset value, occurrence is according to different processing environments
Rule of thumb set, be usually arranged as 1~10) rectangular area of individual pixel be the sample area of foreground template, it is determined that distance
Target image center P2 (preset value, and P2 is more than P1, occurrence rule of thumb sets according to different processing environments, generally set
The difference for putting P2 and P1 is 1~5) empty set of the sample area of the rectangular area of individual pixel and foreground template be background template
Sample area (i.e. around foreground template sample area three-back-shaped region)；Sample area to foreground template is carried out at random
Sampling, and select Np(preset value, occurrence is rule of thumb set according to different processing environments, and usual value is [30,60])
The individual sampled images equal with target image size are used as foreground template D+；Sample area to background template is adopted at random
Sample, and select Nn(preset value, occurrence is rule of thumb set according to different processing environments, usual value be set to [200,
300]) the individual sampled images equal with target image size are used as background template D-, by foreground template D+With background template D-Constitute
Adjudicate dictionary D；
Based on default rectangular slide window, (size is w*h, and its wide w, high h value are preset value, and occurrence is according to difference
Processing environment rule of thumb set, be generally based on target image size and be configured, for example w could be arranged to target image
The 1/8 of width, 1/16,1/32,1/64 etc., h could be arranged to the 1/8 of target image height, 1/16,1/32,1/64 etc.),
Left and right, upper and lower slide is carried out on target image to sample, and the left and right sampling interval is identical, the sampling interval is identical (usually up and down
May be configured as w/2, up and down the sampling interval may be configured as h/2, naturally it is also possible to carry out other and such as w/4, h/4 etc. be set, depend on
In the fineness requirement of calculating), the fragment collection of target image is obtained, and choosing is concentrated from the fragment based on K mean cluster method
K fragment (K representative fragment) is taken, by K fragment composing training collection and matching dictionary A is obtained, wherein K is K equal
It is worth the general term of clustering method, is preset value, occurrence is rule of thumb set according to different processing environments, usual span is
[50,100], when K mean cluster method described below is calculated, K value can set different value, usual value
Scope is [50,100]；It is provided for the gray matrix T of the gray value of each fragment of the fragment collection of stored target image, the ash
The gray value of each fragment is in degree matrix T：The each point pixel value of fragment cumulative and.
Step 3：Based on build judgement dictionary D, matching dictionary A and gray matrix T, determine initialisation image it is each after
The target location of continuous two field picture, i.e., carry out target following processing to non-first two field picture：
301：The sampling of candidate's particle and the pre- selection of candidate's particle
It is the sampling of candidate's particle first：Current frame image is sampled, and (present treatment process is directly based upon conventional techniques
Completion, the present invention is not construed as limiting, and sampling can be generally completed with particle filter mode, and the number of particles of sampling is specific according to reality
It is general to may be selected 500 or so depending on the situation of border), the first candidate image sample set is obtained, K mean cluster is then based on from first
Candidate samples, which are concentrated, chooses K cluster centre, and calculates the value of the confidence H of each cluster centrec：
Corresponding sparse coefficient is calculated based on formula (1)：
Wherein D (refers specifically to foreground template D for judgement dictionary+(it can also claim foreground template dictionary D+) and background template D-(
Background template dictionary D can be claimed-)), X is some sample (referring specifically to each candidate image in the present invention), can be asked by L1 optimization problems
Sparse coefficient α is obtained, wherein μ is the predetermined coefficient of rarefaction representation formula, and occurrence is rule of thumb set according to different experimental situations
It is fixed.‖.‖1、‖.‖21 norm, 2 norms of correspondence vector are represented respectively.
Because if a sample has small reconstructed error to mean that the sample is likely to one on foreground template collection
Target., whereas if a sample has small reconstructed error to mean that this sample is likely to background on background template collection.
Therefore, putting for sample can be constructed according to reconstructed error of the sample on reconstructed error and background template collection on foreground template collection
Letter value Hc:
Hc=exp (- εf+εb) (2)
In above formula,It is sample (candidate image) X in foreground template D+On reconstructed error, a+It is
Candidate image X corresponding to cluster centre is based on foreground template D+Sparse coefficient (according to formula (1) calculate solve),It is sample X in background template D_On reconstructed error, α_It is the candidate image X corresponding to cluster centre
Based on foreground template D-Sparse coefficient (according to formula (1) calculate solve).
It is candidate's this sampling of sampled images center to take the maximum cluster centre of the value of the confidence in K cluster centre, is waited based on described
Image pattern sampling center is selected sample obtaining the second candidate image sample set.
Next to that the pre- selection to candidate's particle, the processing mainly by choosing in advance, removes a large amount of departure ratios larger
Candidate's particle, further to reduce candidate's scope.It is processed as：To the second candidate image sample set, according to formula (1) and (2)
Calculate the value of the confidence of each candidate image, then therefrom choose N before the value of the confidence highest (empirical value, span generally may be configured as
[20,60]) individual candidate is as new candidate image, to treat below further processing.The value of the confidence highest is not directly selected herein
One candidate image is allowed for because the reason for blocking as target, and the value of the confidence highest candidate may not be optimal waits
Choosing, need to by below block processing could select optimal candidate.
In view of in follow-up object tracking process, target is possible to be blocked by background, if without blocking processing,
It is possible to that target is treated as background during tracking, so that the tracking result of mistake is caused, therefore, it is necessary to carry out blocking place
Reason so that the present invention also has preferable robustness to circumstance of occlusion, and so-called block is processed as：
Carrying out fragment sampling in the way of sliding window to each new candidate image first (needs to record the coordinate of fragment
Position), the mode of sampling is identical to the sample mode of target image with step 2, and obtained fragment of sampling contains the candidate
Each part of image, matching dictionary A is then based on to each fragment, corresponding sparse coefficient is calculated using formula (1)
βi, it is next based on formulaCalculate each fragment yiReconstructed error εi(subscript i is used to identifying different broken
Piece).Fragment for belonging to background, its reconstructed error can be larger, belongs to the fragment of prospect, and its reconstructed error can be smaller, if
One threshold epsilon0(span is usually [0.3 0.6]), successively come the attribute of each fragment for judging candidate image, that is, works as
εi＞ ε0, illustrate that the fragment belongs to background；Work as εi≤ε0When, illustrate that the fragment belongs to prospect.Then set up one and record every successively
The attribute of individual fragment attribute matrix (for example, it is m*n to define target image or fragment sum corresponding to candidate image,
Wherein m is often capable fragment sum, and n is the fragment sum of each column, then attribute matrix is the two-dimensional matrix of m*n ranks, also may be used certainly
To store successively by row vector or column vector, simply need to limit the storage mode one that target image and candidate image are taken
Cause, so as to realize matching treatment), i.e., when fragment belongs to prospect, 1 is set in the matrix correspondence position value, when belonging to background, its
Value is set to 0, and 0-1 matrix is so set up to each candidate.In the same way to initialisation image (the first frame figure
Picture) in target set up 0-1 matrix as To Template (To Template attribute matrix), then by each candidate and mould
Plate is matched, and one candidate image of matching degree highest is the target image of present frame.If being directly based upon target image institute
Corresponding attribute matrix carries out matched jamming target with the attribute matrix corresponding to candidate image, then can be without life in step 2
Into To Template gray scale attribute matrix T, the corresponding objective attribute target attribute matrix of foregoing description generation target image is based only upon.
Specific reality method is as follows：
To each new candidate image c, the rectangular slide window of a w*h size is set first, using the sliding window in candidate
The enterprising line slip samplings of image c, obtain candidate image c fragment collection, based on matching dictionary A (also referred to as sparse dictionary A), root
Solved according to formula (3) and obtain each fragment yiSparse coefficient vector βi：
The judgement dictionary in formula (1) is replaced with into matching dictionary A, sample corresponds to each fragment.
Further according toCalculate each fragment yiReconstructed error εi, and based on reconstructed error εiWith presetting
Threshold epsilon0Magnitude relationship the property value of each fragment is set, then the property value of each fragment is sequentially recorded in attribute matrix Sc
In.
If being directly based upon the attribute matrix corresponding to target image to be matched with the attribute matrix corresponding to candidate image
Target is tracked, then directly by N number of attribute matrix ScMatching treatment is carried out with objective attribute target attribute matrix S respectively, matching degree highest is taken
Attribute matrix ScCorresponding candidate image is the target image of present frame.
Meanwhile, the present invention is also based on the phase of the gray matrix and the gray matrix corresponding to new candidate image of target
The target image of present frame is tracked like degree.It is specifically processed as, i.e., firstly the need of in step 2, based on initialisation image
Target image determines To Template gray scale attribute matrix T (gray value of each fragment of stored target image successively), is then hiding
In gear processing, in addition it is also necessary to which for each new candidate image, one gray matrix F is setc, the candidate image c's new for depositing is every
The gray value of individual fragment, in order to simplify calculating, the attribute matrix S based on each candidate imagecTo its gray matrix FcIt is normalized
Processing, that is, work as ScIn property value be 0 when, then by FcThe value of middle correspondence position is set to 0；Work as ScIn property value be 1 when, Fc
The value of middle correspondence position be the cumulative of the gray value of correspondence fragment, i.e. each point pixel value of the fragment with.Finally, take and gray scale
Gray matrix F most like matrix TcCorresponding new candidate image c as present frame target image.
Further, the similarity L of candidate image and target image can be calculated according to formula (4)c：
M for target image (To Template gray scale attribute matrix T) gray value summation a little, i.e., by calculated value normalizing
Change.Represent candidate image c gray matrix FcEach element, TijRepresent To Template gray scale attribute matrix T each element.Through
Similarity that above formula tried to achieve is crossed in the range of [0,1], similarity L in all candidates is found outcA maximum candidate, should
Candidate image and the matching degree highest of target image, therefore, can using the candidate image as present frame tracking target (target figure
Picture).
In order to keep the real-time that tracking is handled, it is determined that after the target image of complete present frame, setting renewal to handle, it has
Body updates processing mode：
Target image based on present frame, according to step 2 to foreground template D+, background template D-, matching dictionary A and target
Template attributes matrix S or To Template gray scale attribute matrix T are updated；
Or, the target image based on present frame matches dictionary A and gray matrix T according to step 2 pair and is updated；And
And every 5-10 frames, the target image based on present frame, the sample area according to step 2 in background template carries out stochastical sampling,
The individual sampled images equal with target image size of N ' are selected, background template D is added to-In, and delete background template D-In from work as
Previous frame interval time most long individual sampled images of N ', wherein 1≤N '≤Nn(during tracking below, tracking environmental is not
Disconnected change, tracking object variations are little, but background is changed greatly, therefore a consideration cycle place can be updated to background template
Reason)；Further, the target image of present frame can also be added to foreground template D+In, and delete foreground template D+In from work as
Previous frame interval time most long sampled images.
In summary, by adopting the above-described technical solution, the beneficial effects of the invention are as follows：Tracking targeted attitude is become
Change, situations such as ambient lighting changes and blocked can improve the situation processing effect to target occlusion with very strong robustness
Really.
Brief description of the drawings
The present invention will illustrate by embodiment and with reference to the appended drawing, wherein：
Fig. 1 is the processing procedure schematic diagram of the specific embodiment of the invention；
Fig. 2 is the foreground template (positive template) of the specific embodiment of the invention, the sampling signal of background template (negative norm plate)
Figure；
Fig. 3 obtains exemplary plot for the fragment of the specific embodiment of the invention.
Embodiment
To make the object, technical solutions and advantages of the present invention clearer, with reference to embodiment and accompanying drawing, to this hair
It is bright to be described in further detail.
Referring to Fig. 1, for actual current frame image, whether be first frame, if the first frame, then if first determining whether present frame
Need according to the target image information in the first frame that (position of target in the picture, the information such as size (length and width are respectively W, H) is carried
It is preceding obtain) ask for the present invention tracking needed for judgement dictionary (foreground template and background template), matching dictionary and its
Its information, be specifically：For the first two field picture, the sample area first shown in figure two carries out palette sample, obtained positive and negative
Template is used as training set.Positive template is to pass through upper and lower, left and right translation 1-5 in the target location indicated with central rectangular frame
Some images of the mode stochastical sampling of pixel, then choose N by way of K mean clusterpIndividual cluster centre is used as positive template
(foreground template).Negative norm plate is some images of being sampled in the relatively remote position in position of distance mark, equal also with K
The method of value cluster chooses NnIndividual image (i.e. in a back-shaped region of distance objective center certain distance, equally return by size
One turns to W*H), these sampled images are used as negative norm plate (background template).
Also need to calculate simultaneously and obtain matching dictionary A and gray matrix T in the first frame, i.e., be by the broken of To Template
Piece, which is obtained, carries out correspondence calculating, and its method is：The rectangular slide window of a w*h size is set first, using the sliding window in target
It is left and right on image, upper and lower enter line slip sampling, the left and right sampling interval be w/2, up and down the sampling interval be h/2, if target image
Height and width be respectively H and W, then number of samples is [W/ (w/2) -1] * [H/ (h/2) -1] (as shown in figure 3, its number of samples is
8*8).It is same that these fragments are asked for into K most representational fragments first with K mean cluster method, then by row heap
The mode put piles column vector composing training collection, utilizes approximatioss (such as convex method of relaxation) generation judgement dictionary A.For target mould
Plate gray scale attribute matrixFor each point in T, a local fragment of target image all correspond to
Gray value.
If present frame is not the first two field picture, the target location for estimating present frame is needed (to determine the target figure of present frame
Picture).Current frame image is sampled first with particle filter mode, more candidate images is obtained and is used as the first candidate
Image pattern set, then chooses K cluster centre using K mean cluster, is calculated according to formula (1) and (2) in each cluster
The value of the confidence of the heart, regard a maximum cluster centre of the value of the confidence as candidate's sampling center.Then according to the sampling center again
A number of candidate image is obtained as the second candidate image sample set in particle filter mode.Calculate and the second candidate is schemed
As the value of the confidence of each candidate image in sample set, 20 candidates are taken before the value of the confidence highest as new candidate image.
Each in the candidate image new to 20, the mode obtained according to fragment in the first frame obtains fragment, to every
One fragment, utilizes the reconstructed error ε for matching dictionary A and asking each fragmenti, work as εi＞ ε0, illustrate that the fragment belongs to background；When
εi≤ε0When, illustrate that the fragment belongs to prospect.By the fragment in attribute matrix ScThe value of correspondence position is set to 1.By repeating to count
Calculate, for each candidate image, its corresponding attribute matrix S can be obtainedc.Then asked with gray matrix T in the first frame
Take method similar, ask for the gray matrix of each candidate imageIt is but different with the first frame here
It is to need to combine attribute matrix Sc, it is the normalizing of corresponding points in gray matrix when the property value that certain in attribute matrix is put is 0
Ashing angle value is also 0, and when property value is 1, Normalized Grey Level value is constant.Reference picture 3, so that the total number of fragment is 8*8 as an example,
Its corresponding attribute matrix Sc, To Template gray scale attribute matrix T and new candidate image gray matrix FcIt is then 8*8's
Two-dimensional matrix, if the property value of the fragment of (3,4) is 0, then attribute matrix ScMiddle S34Value be 0, and gray matrix FcMiddle F34
Value be also 0, if the property value of the fragment of (4,2) is 1, then attribute matrix ScMiddle S42Value be 1, and gray matrix FcIn
F42Value the summation tried to achieve is added by each point pixel value of fragment (4,2).
The similarity of candidate and template is calculated finally according to formula (4), will wherein one candidate image of similarity highest
Foreground template, background template, matching dictionary A and target mould are updated as the target image of present frame, and using the target image
Plate gray scale attribute matrix T.
Claims (9)
1. a kind of visual target tracking method based on rarefaction representation, it is characterised in that comprise the following steps：
Step 1：Determine initialisation image and determine the target image of the initialisation image；
Step 2：Based on current target image generation foreground template D+, background template D-, matching dictionary A and To Template gray scale category
Property matrix T：
In the initialisation image, the rectangular area of P1 pixel of distance objective picture centre adopting for foreground template is determined
Sample region, the empty set for determining the rectangular area of P2 pixel of distance objective picture centre and the sample area of foreground template is the back of the body
The sample area of scape template, wherein P1, P2 a preset value, and P2 is more than P1；Sample area to foreground template is adopted at random
Sample, and select NpThe individual sampled images equal with target image size are used as foreground template D+；Sample area to background template is entered
Row stochastical sampling, and select NnThe individual sampled images equal with target image size are used as background template D-；
Based on default rectangular slide window, left and right, upper and lower slide is carried out on target image and is sampled, and sampling interval phase up and down
Together, the left and right sampling interval is identical, obtains the fragment collection of target image, and concentrate choosing from the fragment based on K mean cluster method
K fragment is taken, by the K fragment composing training collection and matching dictionary A is obtained；And fragment collection is calculated based on matching dictionary A
Each fragment yiCorresponding sparse coefficient βi, subscript i is used to identify different fragments, and is based on formulaMeter
Calculate fragment yiReconstructed error εi；If εiMore than predetermined threshold value ε0, then fragment y is setiProperty value be 0, be otherwise provided as 1；
The To Template gray scale attribute matrix T of the gray value of each fragment of the fragment collection of stored target image successively is provided for,
The gray value of each fragment is in the matrix T：The each point pixel value of fragment cumulative and；
Step 3：Determine the target location of each follow-up two field picture of initialisation image：
301：Current frame image is sampled, the first candidate image sample set is obtained, is waited based on K mean cluster from described first
This concentration of sampling chooses K cluster centre, and calculates the value of the confidence H of each cluster centrec；Take the value of the confidence in K cluster centre
Maximum cluster centre is candidate's this sampling of sampled images center, is sampled based on the candidate image specimen sample center
Second candidate image sample set, and calculate the value of the confidence H that the second candidate samples concentrate each candidate samplesc, take the value of the confidence highest
Top n candidate image is used as new candidate image；The first candidate image sample set with it is each in the second candidate image sample set
The size of image pattern is consistent with target image；
The value of the confidence HcCalculation formula beCalculate the value of the confidence H of each cluster centrec, prospect weight
Structure errorWherein a+Represent that the candidate image X corresponding to cluster centre is based on foreground template D+Sparse system
Number；Background reconstruction errorWherein a-Represent that the candidate image X corresponding to cluster centre is based on background mould
Plate D-Sparse coefficient；
302：Based on sample mode is slided with the fragment collection identical that target image is obtained in step 2, obtain new candidate image c's
Fragment collection, and each fragment y is calculated based on matching dictionary AiCorresponding sparse coefficient βi, subscript i be used for identify different fragments,
And based on formulaCalculate fragment yiReconstructed error εiIf, εiMore than predetermined threshold value ε0, then fragment y is seti
Property value be 0, be otherwise provided as 1；
303：Set a property matrix Sc, the attribute of each fragment for depositing new candidate image c successively, setting gray matrix Fc,
For the gray value for each fragment for depositing new candidate image c successively, the gray value of the fragment is each point pixel value of fragment
It is cumulative and, and based on attribute matrix ScTo gray matrix FcValue be adjusted：If ScIn property value be 0, then by FcIn
The value of correspondence position is set to 0；
304：Take the gray matrix F most like with To Template gray scale attribute matrix TcCorresponding new candidate image c is as current
The target image of frame.
2. the method as described in claim 1, it is characterised in that in the step 304, calculate To Template gray matrix T with
Gray matrix FcSimilarity LcFormula beWherein, M represents gray matrix T each elements
Summation, the element position of i and j representing matrixs.
3. method as claimed in claim 1 or 2, it is characterised in that the step 3 also includes 305：Target based on present frame
Image, according to step 2 to foreground template D+, background template D-, matching dictionary A and To Template gray scale attribute matrix T carry out more
Newly.
4. method as claimed in claim 1 or 2, it is characterised in that the step 3 also includes 305：Target based on present frame
Image, matches dictionary A and gray matrix T according to step 2 pair and is updated；And every 5-10 frames, the target based on present frame
Image, carries out stochastical sampling, N ' is individual equal with target image size adopts for selection according to step 2 in the sample area of background template
Sampled images, are added to background template D-In, and delete background template D-In from present frame interval time most long individual sample graphs of N '
Picture, wherein 1≤N '≤Nn。
5. method as claimed in claim 4, it is characterised in that the step 305 also includes, every 5-10 frames, by present frame
Target image be added to foreground template D+In, and delete foreground template D+In from the most long sampling of present frame interval time
Image.
6. the method as described in claim 1, it is characterised in that in the step 2, P1 value is 1~10, P2 and P1 difference
It is worth for 1~5.
7. the method as described in claim 1, it is characterised in that the initialisation image is the of video image or image sequence
One two field picture.
8. the method as described in claim 1, it is characterised in that left when entering line slip sampling based on default rectangular slide window
The right sampling interval is w/2, and the sampling interval is h/2 up and down, and wherein w represents the width of rectangular slide window, and h represents rectangular slide window
It is high.
9. the method as described in claim 1, it is characterised in that in the step 301, sampled, obtained based on particle filter
Take the first candidate image sample set and the second candidate image sample set.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510142274.9A CN104766343B (en) | 2015-03-27 | 2015-03-27 | A kind of visual target tracking method based on rarefaction representation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510142274.9A CN104766343B (en) | 2015-03-27 | 2015-03-27 | A kind of visual target tracking method based on rarefaction representation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104766343A CN104766343A (en) | 2015-07-08 |
| CN104766343B true CN104766343B (en) | 2017-08-25 |
Family
ID=53648148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510142274.9A Active CN104766343B (en) | 2015-03-27 | 2015-03-27 | A kind of visual target tracking method based on rarefaction representation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104766343B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105354307B (en) * | 2015-11-06 | 2021-01-15 | 腾讯科技（深圳）有限公司 | Image content identification method and device |
| CN105513093B (en) * | 2015-12-10 | 2018-02-16 | 电子科技大学 | A kind of method for tracking target represented based on low-rank matrix |
| CN105718894A (en) * | 2016-01-22 | 2016-06-29 | 孟玲 | Sewage treatment device with stable tracking function |
| CN105718910A (en) * | 2016-01-22 | 2016-06-29 | 孟玲 | Battery room with combination of local and global characteristics |
| CN106373144A (en) * | 2016-08-22 | 2017-02-01 | 湖南挚新科技发展有限公司 | Image target relative position determining method and system |
| CN106355604B (en) * | 2016-08-22 | 2019-10-18 | 杭州保新科技有限公司 | Tracking image target method and system |
| CN107123130B (en) * | 2017-03-06 | 2019-12-10 | 华南理工大学 | Kernel correlation filtering target tracking method based on superpixel and hybrid hash |
| CN107273919B (en) * | 2017-05-27 | 2020-07-07 | 南京理工大学 | Hyperspectral unsupervised classification method for constructing generic dictionary based on confidence |
| CN107368785A (en) * | 2017-06-16 | 2017-11-21 | 浙江万里学院 | The video target tracking method of multinuclear local restriction |
| CN109313709A (en) * | 2017-12-29 | 2019-02-05 | 深圳配天智能技术研究院有限公司 | A kind of measure of similarity, device and storage device |
| CN112513870A (en) * | 2018-08-08 | 2021-03-16 | 索博客科技有限公司 | System and method for detecting, tracking and counting human objects of interest with improved altimetry |
| CN110276348B (en) * | 2019-06-20 | 2022-11-25 | 腾讯科技（深圳）有限公司 | Image positioning method, device, server and storage medium |
| CN111274966B (en) * | 2020-01-20 | 2022-06-03 | 临沂大学 | Long-term visual tracking method and device based on structured model |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440645A (en) * | 2013-08-16 | 2013-12-11 | 东南大学 | Target tracking algorithm based on self-adaptive particle filter and sparse representation |
| CN103544483A (en) * | 2013-10-25 | 2014-01-29 | 合肥工业大学 | United target tracking method based on local sparse representation and system thereof |
-
2015
- 2015-03-27 CN CN201510142274.9A patent/CN104766343B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103440645A (en) * | 2013-08-16 | 2013-12-11 | 东南大学 | Target tracking algorithm based on self-adaptive particle filter and sparse representation |
| CN103544483A (en) * | 2013-10-25 | 2014-01-29 | 合肥工业大学 | United target tracking method based on local sparse representation and system thereof |
Non-Patent Citations (3)
| Title |
|---|
| Multiple instance learning tracking method with local sparse representation;Chengjun Xie，Jieqing Tan，Peng Chen，Jie Zhang，Lei He;《IET Computer Vision》;20130513;第7卷(第5期);320-334 * |
| Robust Object Tracking via Sparsity-based Collaborative Model;Wei Zhong,Huchuan Lu,Ming-Hsuan Yang;《2012 IEEE Conference on Computer Vision and Pattern Recognition》;20120726;第3-4页 * |
| 基于稀疏表示的目标跟踪算法;钟伟;《中国优秀硕士学位论文全文数据库》;20130815(第8期);第17-26页，3.2-3.3节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104766343A (en) | 2015-07-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104766343B (en) | A kind of visual target tracking method based on rarefaction representation | |
| CN109949341B (en) | Pedestrian target tracking method based on human skeleton structural features | |
| CN105956582B (en) | A kind of face identification system based on three-dimensional data | |
| WO2020108362A1 (en) | Body posture detection method, apparatus and device, and storage medium | |
| CN103207898B (en) | A kind of similar face method for quickly retrieving based on local sensitivity Hash | |
| CN109815850A (en) | Iris segmentation and localization method, system, device based on deep learning | |
| CN108805040A (en) | It is a kind of that face recognition algorithms are blocked based on piecemeal | |
| CN104881671B (en) | A kind of high score remote sensing image Local Feature Extraction based on 2D Gabor | |
| CN106980843B (en) | The method and device of target following | |
| CN102982323B (en) | Gait recognition method fast | |
| Lu et al. | Saliency modeling from image histograms | |
| CN107066969A (en) | A kind of face identification method | |
| CN107633226A (en) | A kind of human action Tracking Recognition method and system | |
| CN104123554B (en) | SIFT image characteristic extracting methods based on MMTD | |
| CN106874942B (en) | Regular expression semantic-based target model rapid construction method | |
| CN103996046A (en) | Personnel recognition method based on multi-visual-feature fusion | |
| CN112950477A (en) | High-resolution saliency target detection method based on dual-path processing | |
| CN106529441B (en) | Depth motion figure Human bodys' response method based on smeared out boundary fragment | |
| CN108446642A (en) | A kind of Distributive System of Face Recognition | |
| Goyal et al. | An improved local binary pattern based edge detection algorithm for noisy images | |
| Niu et al. | Automatic localization of optic disc based on deep learning in fundus images | |
| Gao et al. | Robust ROI localization based on image segmentation and outlier detection in finger vein recognition | |
| CN105825215B (en) | It is a kind of that the instrument localization method of kernel function is embedded in based on local neighbor and uses carrier | |
| CN108154513A (en) | Cell based on two photon imaging data detects automatically and dividing method | |
| CN108876776B (en) | Classification model generation method, fundus image classification method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210513 Address after: No.3, 11th floor, building 6, no.599, shijicheng South Road, Chengdu hi tech Zone, China (Sichuan) pilot Free Trade Zone, Chengdu, Sichuan 610041 Patentee after: Houpu clean energy Co.,Ltd. Address before: 611731, No. 2006, West Avenue, Chengdu hi tech Zone (West District, Sichuan) Patentee before: University of Electronic Science and Technology of China |
|
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: No.3, 11th floor, building 6, no.599, shijicheng South Road, Chengdu hi tech Zone, China (Sichuan) pilot Free Trade Zone, Chengdu, Sichuan 610041 Patentee after: Houpu clean energy (Group) Co.,Ltd. Address before: No.3, 11th floor, building 6, no.599, shijicheng South Road, Chengdu hi tech Zone, China (Sichuan) pilot Free Trade Zone, Chengdu, Sichuan 610041 Patentee before: Houpu clean energy Co.,Ltd. |