CN106485732B - A kind of method for tracking target of video sequence - Google Patents

A kind of method for tracking target of video sequence Download PDF

Info

Publication number
CN106485732B
CN106485732B CN201610813832.4A CN201610813832A CN106485732B CN 106485732 B CN106485732 B CN 106485732B CN 201610813832 A CN201610813832 A CN 201610813832A CN 106485732 B CN106485732 B CN 106485732B
Authority
CN
China
Prior art keywords
target
context model
formula
space
time
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
Application number
CN201610813832.4A
Other languages
Chinese (zh)
Other versions
CN106485732A (en
Inventor
杨欣
张芹兰
夏斯军
刘冬雪
周大可
张鹏
高菊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Nanjing University of Aeronautics and Astronautics
Original Assignee
Nanjing University of Aeronautics and Astronautics
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Nanjing University of Aeronautics and Astronautics filed Critical Nanjing University of Aeronautics and Astronautics
Priority to CN201610813832.4A priority Critical patent/CN106485732B/en
Publication of CN106485732A publication Critical patent/CN106485732A/en
Application granted granted Critical
Publication of CN106485732B publication Critical patent/CN106485732B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/10Image acquisition modality
    • G06T2207/10016Video; Image sequence
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06TIMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00Indexing scheme for image analysis or image enhancement
    • G06T2207/20Special algorithmic details
    • G06T2207/20081Training; Learning

Landscapes

  • Image Analysis (AREA)

Abstract

本发明公开了一种视频序列的目标跟踪方法,首先对目标图像进行归一化处理;接着根据初始帧的目标位置,提取目标的时空上下文信息,构建时空上下文模型,建立时空上下文模型与目标位置置信图的关系,从而进行目标跟踪;然后采用遮挡机制判定是否更新时空上下文模型的学习率,利用更新的学习率更新时空上下文模型;最后根据目标跟踪过程中前后帧之间的时空显著性建立尺度更新过程。本发明利用时空信息出发,结合遮挡处理机制和时空显著性对目标进行跟踪,可以有效提高目标跟踪鲁棒性与实时性。

The invention discloses a target tracking method for a video sequence. First, the target image is normalized; then according to the target position of the initial frame, the space-time context information of the target is extracted, a space-time context model is constructed, and the space-time context model and the target position are established. Then, the occlusion mechanism is used to determine whether to update the learning rate of the spatiotemporal context model, and the updated learning rate is used to update the spatiotemporal context model. Finally, a scale is established according to the spatiotemporal saliency between the frames before and after the target tracking process. update process. Based on the spatiotemporal information, the invention tracks the target in combination with the occlusion processing mechanism and the spatiotemporal saliency, which can effectively improve the robustness and real-time performance of the target tracking.

Description

A kind of method for tracking target of video sequence
Technical field
The invention belongs to computer visions, digital image processing field, in particular to a kind of target of video sequence with Track method.
Background technique
Target following is one of hot research topic of field of machine vision, be widely used in human-computer interaction, video with The fields such as track, navigation, while being also the basis of the follow-up works such as target identification, Activity recognition in video, therefore target following has Wide application prospect and practical value, receive the highest attention of researcher all over the world.
Currently, since the external factor such as complex background, illumination and target such as rotate, block at the influence of internal factors, make It obtains tracking process to be typically located under a uncontrolled environment, therefore target following is still a challenging problem.
Summary of the invention
In order to solve above-mentioned background technique propose the technical issues of, the present invention is intended to provide a kind of target of video sequence with Track method, is set out using space time information, is tracked, can be effectively mentioned to target in conjunction with treatment mechanism and time and space significance is blocked High target following robustness and real-time.
In order to achieve the above technical purposes, the technical solution of the present invention is as follows:
A kind of method for tracking target of video sequence, comprising the following steps:
(1) target image is normalized, reduces illumination interference;
(2) according to the target position of initial frame, the spatio-temporal context information of target is extracted, constructs space-time context model, The relationship of space-time context model Yu target position confidence map is established, to carry out target following;
(3) determine whether to update the learning rate of space-time context model using the mechanism of blocking, using update learning rate more New space-time context model;
(4) scale renewal process is established according to the time and space significance in object tracking process between before and after frames.
Further, detailed process is as follows for step (2):
(a) relationship of spatial context model Yu target position confidence map is established:
In formula (1), and P (x | m (z), o) it is spatial context model, indicate that the space of target and surrounding context feature is closed System, x are certain point position coordinates in target, and z indicates that the contextual location coordinate of target, o are tracking target, XcFor context spy Sign defines Xc=m (z)=(I (z), z) | ∈ Ωc(x*), I (z) is the gray value in image at z, Ωc(x*) it is around target Context area, P (m (z) | o) indicates target local context prior probability;
(b) P (x | m (z), o)=h is enabledsc(x-z) (2)
P (m (z) | o)=I (z) ωσ(z-x*) (3)
In formula (2), (3), hsc(x-z) be relative distance and direction about target and local contextual location z function, x*For target's center position, ωσ(z-x*) it is Weighted Gauss function, is defined as:
In formula (4), a represents normaliztion constant, and σ represents scale parameter;
Formula (2)-(4) are substituted into formula (1), are obtained
In formula (5), subscript t indicates t frame;
(c) space-time context model is obtained according to spatial context model:
In formula (6),It is spatial context modelFourier transformation,It is space-time context modelFourier transformation, ρtRepresent learning rate;
(d) space-time context model is established according to formula (5)With the relationship of target position confidence map:
In formula (7), F indicates Fourier transformation;
(e) target's centerBy seeking target position confidence map mt+1(x) extreme value obtains:
Further, detailed process is as follows for step (3):
Define the peak sidelobe ratio of t frame:
In formula (9), μsl-tAnd σsl-tIt is confidence map m respectivelyt(x) mean value and standard deviation around peak value in 12 × 12 neighborhoods;
It enables
Δ m=mt-mt-1 (11)
WhenAnd ppsr-t≥pth, Δ m < Mtol, indicate that target is in gradually to walk out and block, model should be carried out more at this time Newly;WhenAnd ppsr-t≥pth, Δ m > Mtol, indicate that target following is in good condition, cope with model at this time and be updated;WhenOr ppsr-t< pthWhen, indicate that target is in serious shielding or full occlusion state, at this time without model modification;Wherein, pth For the given threshold of peak sidelobe ratio, MtolFor the given threshold of the variable quantity of target confidence map;
Update the learning rate ρ of space-time context modelt:
Space-time context model is updated according to the learning rate of update:
Further, pthValue be 2.5 × 10-3
Further, detailed process is as follows for step (4):
In formula (14), η represents fading factor, and n indicates to calculate target scale, s in every n frametIndicate t frame target scale, σt Indicate t frame scale parameter.
Further, η=0.51, n=5.
By adopting the above technical scheme bring the utility model has the advantages that
(1) present invention using Bayesian frame to the time-space relationship of the target to be tracked and its local context region into Row modeling, obtains the statistic correlation of target He its peripheral region low-level features, robustness with higher;
(2) present invention copes with complex scene, has judgement to circumstance of occlusion using treatment mechanism is blocked, can Judged according to object variations process, therefore application blocks treatment mechanism to a certain extent and reduces the accumulation of error, and There can be certain inhibiting effect to the drift of target, improve the robustness for target following under complex situations;
(3) present invention carries out real-time update to learning rate in object tracking process, can effectively reduce the accumulation of error, Object module updates and target scale renewal process all refers to learning rate, and it is selectable that the update of learning rate can be such that model carries out Update it is more accurate, scale it is correct update also have significant impact to the extraction of target signature, the extraction of error characteristic will affect The tracking of target is caused to drift about or be lost;
(4) present invention is to utilize the connection of target before and after frames to the application of space-time significance measure, is updated to target scale With great influence, the real-time of object tracking process mesoscale update is improved, the influence of interference information is reduced.
Detailed description of the invention
Fig. 1 is flow chart of the invention.
Specific embodiment
Below with reference to attached drawing, technical solution of the present invention is described in detail.
As shown in Figure 1, a kind of method for tracking target of video sequence, comprising the following steps:
Step 1: target image being normalized, illumination interference is reduced, improves operational efficiency.
Step 2: according to the target position of initial frame, extracting the spatio-temporal context information of target, construct space-time context mould Type establishes the relationship of space-time context model Yu target position confidence map, to carry out target following.Detailed process is as follows:
A, the relationship of spatial context model Yu target position confidence map is established:
In formula (1), and P (x | m (z), o) it is spatial context model, indicate that the space of target and surrounding context feature is closed System, x are certain point position coordinates in target, and z indicates that the contextual location coordinate of target, o are tracking target, XcFor context spy Sign defines Xc=m (z)=(I (z), z) | ∈ Ωc(x*), I (z) is the gray value in image at z, Ωc(x*) it is around target Context area, P (m (z) | o) indicates target local context prior probability.
B, P (x | m (z), o)=h is enabledsc(x-z) (2)
P (m (z) | o)=I (z) ωσ(z-x*) (3)
In formula (2), (3), hsc(x-z) be relative distance and direction about target and local contextual location z function, x*For target's center position, ωσ(z-x*) it is Weighted Gauss function, is defined as:
In formula (4), a represents normaliztion constant, and σ represents scale parameter.
Formula (2)-(4) are substituted into formula (1), are obtained
In formula (5), subscript t indicates t frame.
C, space-time context model is obtained according to spatial context model:
In formula (6),It is spatial context modelFourier transformation,It is space-time context modelFourier transformation, ρtRepresent learning rate.
D, space-time context model is established according to formula (5)With the relationship of target position confidence map:
In formula (7), F indicates Fourier transformation.
E, target's centerBy seeking target position confidence map mt+1(x) extreme value obtains:
Step 3: determining whether to update the learning rate of space-time context model using the mechanism of blocking, utilize the learning rate of update Update space-time context model.Detailed process is as follows:
Define the peak sidelobe ratio of t frame:
In formula (9), μsl-tAnd σsl-tIt is confidence map m respectivelyt(x) mean value and standard deviation around peak value in 12 × 12 neighborhoods;
It enables
Δ m=mt-mt-1 (11)
As shown in table 1, whenAnd ppsr-t≥pth, Δ m < Mtol, indicate that target is in gradually to walk out and block, cope at this time Model is updated;WhenAnd ppsr-t≥pth, Δ m > Mtol, indicate that target following is in good condition, model should be carried out at this time It updates;WhenOr ppsr-t< pthWhen, indicate that target is in serious shielding or full occlusion state, at this time without model modification; Wherein, pthFor the given threshold of peak sidelobe ratio, MtolFor the given threshold of the variable quantity of target confidence map.
Update the learning rate ρ of space-time context modelt:
Space-time context model is updated according to the learning rate of update:
Table 1
Step 4: scale renewal process, purpose are established according to the time and space significance in object tracking process between before and after frames It is to improve the real-time that object tracking process mesoscale updates, reduces the influence of interference information.Detailed process is as follows:
In formula (14), η represents fading factor, ηiIt is reduced with the increase of i, indicates influence of the historical frames to present frame at any time Between change, in the present embodiment, η=0.51;N indicates calculating target scale in every n frame, in the present embodiment, n=5, because In 5 frames, target scale variation will not be larger, can reduce calculation amount and improve the real-time of the patent;, stIndicate t frame target Scale, σtIndicate t frame scale parameter.
The above examples only illustrate the technical idea of the present invention, and this does not limit the scope of protection of the present invention, all According to the technical idea provided by the invention, any changes made on the basis of the technical scheme each falls within the scope of the present invention Within.

Claims (4)

1. a kind of method for tracking target of video sequence, which comprises the following steps:
(1) target image is normalized, reduces illumination interference;
(2) according to the target position of initial frame, the spatio-temporal context information of target is extracted, constructs space-time context model, is established The relationship of space-time context model and target position confidence map, to carry out target following;Detailed process is as follows for the step:
(a) relationship of spatial context model Yu target position confidence map is established:
In formula (1), and P (x | m (z), o) it is spatial context model, indicate the spatial relationship of target and surrounding context feature, x It is certain point position coordinates in target, z indicates that the contextual location coordinate of target, o are tracking target, XcIt is fixed for contextual feature Adopted Xc=m (z)=(I (z), z) | ∈ Ωc(x*), I (z) is the gray value in image at z, Ωc(x*) it is upper around target Context area, and P (m (z) | o) indicate target local context prior probability;
(b) P (x | m (z), o)=h is enabledsc(x-z) (2)
P (m (z) | o)=I (z) ωσ(z-x*) (3)
In formula (2), (3), hscIt (x-z) is about target and the relative distance of local contextual location z and the function in direction, x*For Target's center position, ωσ(z-x*) it is Weighted Gauss function, is defined as:
In formula (4), a represents normaliztion constant, and σ represents scale parameter;
Formula (2)-(4) are substituted into formula (1), are obtained
In formula (5), subscript t indicates t frame;
(c) space-time context model is obtained according to spatial context model:
In formula (6),It is spatial context modelFourier transformation,It is space-time context modelFourier transformation, ρtRepresent learning rate;
(d) space-time context model is established according to formula (5)With the relationship of target position confidence map:
In formula (7), F indicates Fourier transformation;
(e) target's centerBy seeking target position confidence map mt+1(x) extreme value obtains:
(3) learning rate for determining whether to update space-time context model using the mechanism of blocking, when being updated using the learning rate of update Empty context model;Detailed process is as follows for the step:
Define the peak sidelobe ratio of t frame:
In formula (9), μsl-tAnd σsl-tIt is confidence map m respectivelyt(x) mean value and standard deviation around peak value in 12 × 12 neighborhoods;
It enables
Δ m=mt-mt-1(11)
WhenAnd ppsr-t≥pth, Δ m < Mtol, indicate that target is in gradually to walk out and block, cope with model at this time and be updated; WhenAnd ppsr-t≥pth, Δ m > Mtol, indicate that target following is in good condition, cope with model at this time and be updated;WhenOr ppsr-t< pthWhen, indicate that target is in serious shielding or full occlusion state, at this time without model modification;Wherein, pthFor peak value The given threshold of secondary lobe ratio, MtolFor the given threshold of the variable quantity of target confidence map;
Update the learning rate ρ of space-time context modelt:
Space-time context model is updated according to the learning rate of update:
(4) scale renewal process is established according to the time and space significance in object tracking process between before and after frames.
2. a kind of method for tracking target of video sequence according to claim 1, it is characterised in that: pthValue be 2.5 × 10-3
3. a kind of method for tracking target of video sequence according to claim 1, which is characterized in that the specific mistake of step (4) Journey is as follows:
In formula (14), η represents fading factor, and n indicates to calculate target scale, s in every n frametIndicate t frame target scale, σtIt indicates T frame scale parameter.
4. a kind of method for tracking target of video sequence according to claim 3, it is characterised in that: η=0.51, n=5.
CN201610813832.4A 2016-09-09 2016-09-09 A kind of method for tracking target of video sequence Active CN106485732B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610813832.4A CN106485732B (en) 2016-09-09 2016-09-09 A kind of method for tracking target of video sequence

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610813832.4A CN106485732B (en) 2016-09-09 2016-09-09 A kind of method for tracking target of video sequence

Publications (2)

Publication Number Publication Date
CN106485732A CN106485732A (en) 2017-03-08
CN106485732B true CN106485732B (en) 2019-04-16

Family

ID=58273728

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610813832.4A Active CN106485732B (en) 2016-09-09 2016-09-09 A kind of method for tracking target of video sequence

Country Status (1)

Country Link
CN (1) CN106485732B (en)

Families Citing this family (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN107240120B (en) * 2017-04-18 2019-12-17 上海体育学院 Method and device for tracking moving target in video
CN107093189A (en) * 2017-04-18 2017-08-25 山东大学 Method for tracking target and system based on adaptive color feature and space-time context
CN107146238B (en) * 2017-04-24 2019-10-11 西安电子科技大学 Moving Target Tracking Method Based on Feature Block Optimization
CN107045726B (en) * 2017-04-27 2019-12-24 南京航空航天大学 A Target Tracking Method Based on Spatiotemporal Context Model
CN107146240B (en) * 2017-05-05 2019-08-13 西北工业大学 The video target tracking method of taking photo by plane detected based on correlation filtering and conspicuousness
CN107346548A (en) * 2017-07-06 2017-11-14 电子科技大学 A kind of tracking for electric transmission line isolator
CN107424175B (en) * 2017-07-20 2020-09-08 西安电子科技大学 A Target Tracking Method Combining Spatio-temporal Context Information
CN107452015B (en) * 2017-07-28 2020-09-25 南京工业职业技术学院 A Target Tracking System with Redetection Mechanism
CN108022254B (en) * 2017-11-09 2022-02-15 华南理工大学 Feature point assistance-based space-time context target tracking method
CN110084233B (en) * 2018-01-25 2021-02-09 华中科技大学 Method and system for quickly capturing target in production line video sequence
CN108320298B (en) * 2018-04-28 2022-01-28 亮风台(北京)信息科技有限公司 Visual target tracking method and equipment
CN109285179B (en) * 2018-07-26 2021-05-14 昆明理工大学 A moving target tracking method based on multi-feature fusion
CN109325966B (en) * 2018-09-05 2022-06-03 华侨大学 A method for visual tracking through spatiotemporal context
CN110111370B (en) * 2019-05-15 2023-05-30 重庆大学 A visual object tracking method based on TLD and deep multi-scale spatio-temporal features
CN112733770A (en) * 2021-01-18 2021-04-30 全程(上海)智能科技有限公司 Regional intrusion monitoring method and device

Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105117720A (en) * 2015-09-29 2015-12-02 江南大学 Target Scale Adaptive Tracking Method Based on Spatiotemporal Model
CN105654518A (en) * 2016-03-23 2016-06-08 上海博康智能信息技术有限公司 Trace template self-adaption method based on variance estimation

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101999231A (en) * 2008-04-11 2011-03-30 汤姆逊许可证公司 System and method for enhancing the visibility of an object in a digital picture

Patent Citations (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105117720A (en) * 2015-09-29 2015-12-02 江南大学 Target Scale Adaptive Tracking Method Based on Spatiotemporal Model
CN105654518A (en) * 2016-03-23 2016-06-08 上海博康智能信息技术有限公司 Trace template self-adaption method based on variance estimation

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
Fast visual tracking via dense spatio-temporal context learning;Zhang K H等;《13th European Conference on Computer Vision》;20141231;全文
基于置信图特性的改进时空上下文目标跟踪;张雷等;《计算机工程》;20160831;第42卷(第8期);第277-281页
融合时空上下文的超像素跟踪算法研究;杜安安;《中国优秀硕士学位论文全文数据库》;20150815;第I138-1393页

Also Published As

Publication number Publication date
CN106485732A (en) 2017-03-08

Similar Documents

Publication Publication Date Title
CN106485732B (en) A kind of method for tracking target of video sequence
CN105405154B (en) Target object tracking based on color-structure feature
CN114049382A (en) Target fusion tracking method, system and medium in intelligent network connection environment
JP2015181042A (en) detection and tracking of moving objects
CN107301657B (en) A kind of video target tracking method considering target movable information
Wang et al. Improving RGB-D SLAM accuracy in dynamic environments based on semantic and geometric constraints
CN105374049B (en) Multi-corner point tracking method and device based on sparse optical flow method
WO2017066904A1 (en) A navigation apparatus and associated methods
Cho et al. Real-time people counting system for customer movement analysis
CN104023228A (en) Self-adaptive indoor vision positioning method based on global motion estimation
CN102034355A (en) Feature point matching-based vehicle detecting and tracking method
CN111639570B (en) Online multi-target tracking method based on motion model and single-target clue
CN105261034A (en) Method and device for calculating traffic flow on highway
CN103077520A (en) Background deduction method for movable vidicon
CN103942542A (en) Human eye tracking method and device
CN102497505A (en) Multi-ball machine linkage target tracking method and system based on improved Meanshift algorithm
CN112634316B (en) Target tracking method, device, equipment and storage medium
CN115619826A (en) A Dynamic SLAM Method Based on Reprojection Error and Depth Estimation
CN119339007B (en) Scene space model self-adaptive modeling method for multi-source data fusion
Prokaj et al. Using 3d scene structure to improve tracking
Haggui et al. Centroid human tracking via oriented detection in overhead fisheye sequences
CN116524026A (en) Dynamic vision SLAM method based on frequency domain and semantics
CN115223135B (en) Parking space tracking method, device, vehicle and storage medium
CN116523957A (en) Multi-target tracking method, system, electronic equipment and storage medium
CN112101170A (en) Target positioning method, device, computer equipment and storage medium

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant