robust object tracking via sparsity-based collaborative model

Robust Object Tracking via Sparsity-based Collaborative Model

Wei Zhong, Huchuan Lu and Ming-Hsuan Yang

http://ice.dlut.edu.cn/lu/index.htmlhttp://faculty.ucmerced.edu/mhyang/index.html

In CVPR2012

http://ice.dlut.edu.cn/lu/index.html

http://faculty.ucmerced.edu/mhyang/index.html

●Introduction

● Related Work and Motivation

● The Proposed Method

● Experimental Results

●Conclusion

● Introduction ■ Applications and Challenging Factors




●Conclusion

Introduction

■ Applications and Challenging FactorsThe goal of object tracking is to estimate the states of the target in image sequences. It plays a critical role in vision applications such as motion analysis, activity recognition, video surveillance and traffic monitoring.Model-free tracking (i.e., only the initial position of the object is known) is a challenging problem as it is difficult to develop a robust algorithm dealing with large appearance change caused by varying illumination, camera motion, occlusions, pose variation and shape deformation.

●Introduction

● Related Work and Motivation■Object Tracking with Sparse Representation■Motivation of This Work



●Conclusion

Related Work

Liu et al. [1] propose a method which selects a sparse and discriminative set of features to improve tracking efficiency and robustness. One potential problem with this approach is that the number of discriminative features is fixed, which may not be effective for tracking in dynamic and complex scenes.

Liu et al. [2] propose a tracking algorithm based on histograms of local sparse representation. The histogram generation scheme in [2] does not differentiate foreground and background patches, and reduces the discrimination of the method.

[1] B. Liu, L. Yang, J. Huang, P. Meer, L. Gong, and C. Kulikowski. Robust and fast collaborative tracking with two stage sparse optimization. In ECCV, 2010. [2] B. Liu, J. Huang, L. Yang, and C. Kulikowsk. Robust tracking using local sparse appearance model and k-selection. In CVPR, 2011.[3] X. Mei and H. Ling. Robust visual tracking using l1 minimization. In ICCV, 2009.

Mei and Ling [3] apply sparse representation to visual tracking and deal with occlusions via trivial templates. The algorithm is able to deal with occlusion with l1 minimization formulation using trivial templates at the expense of high computational cost.

Motivation

The Motivation of Our Work

We develop a simple yet robust model that makes use of the generative model to account for appearance change and the discriminative classifier to effectively separate the foreground target from the background.

Our approach exploits both the strength of holistic templates to distinguish the target from the background, and the effectiveness of local patches in handling partial occlusion.

In order to capture appearance variations as well as reduce tracking drifts, we propose a method that takes occlusions into consideration for updating appearance model.

●Introduction


● The Proposed Method ■ Sparsity-based Discriminative Classifier (SDC)

■ Sparsity-based Generative Model (SGM) ■ Collaborative Model● Experimental Results

●Conclusion

Sparsity-based Discriminative Classifier (SDC)

Template Generation

This facilities better object localization as samples containing only partial appearance of the target are treated as the negative samples and their confidence values are restricted to be small.


Feature Selection

The gray-scale feature space is rich yet redundant. With Equation (1), we exact sparse and determinative features that can better distinguish foreground and background.

2

12min sA s p s•

(1)


Confidence Measure

exp /c f bH (2)

Sparsity-based Generative Model (SGM)

Histogram Generation

We use overlapped sliding windows on the normalized images to obtain M patches.

The sparse coefficient vector β of each patch is computed by Equation (3).

(3)

In this work, the sparse coefficient vector β of each patch is concatenated to form a histogram by Equation (4).

2

2 1min

ii i i

y D

1 2, , , M •• • • (4)


Occlusion Handling

In order to deal with occlusions, we modify the constructed histogram to exclude the occluded patches when describing the target object.

o

01

0 otherwisei

io

The patch with large reconstruction error is regarded as occlusion and the corresponding sparse coefficient vector is set to be zero.

(5)

(6)


Similarity Function

We use the histogram intersection function to compute the similarity of histograms between the candidate and the template due to its effectiveness by Equation (7).

(7) 1min ,

J M j jc cjL

Collaborative Model

We propose a collaborative model using SDC and SGM within the particle filter framework , and the tracking result is the candidate with the highest probability.

The generative model is effective to account for appearance change;The discriminative classifier is effective to separate the foreground target from the background;Our method exploits the collatborative strength of both schemes using Equation (8).

(8) 1exp / min ,

c c c

J M j jf b cj

p H L

●Introduction



● Experimental Results■Qualitative Evaluation■Quantitative Evaluation

●Conclusion

Experimental Results- Qualitative Evaluation

Demo:

Heavy Occlusion

Motion Blur

Rotation Illumination Change

Cluttered Background

Experimental Results- Qualitative Evaluation

Experimental Results- Quantitative Evaluation

2 2

g tgtxCenter yError x y

Experimental Results- Quantitative Evaluation

G

TG

Tarea ROverlapRate

area R

R

R

●Introduction




●Conclusion

Conclusion

In this paper, we propose an effective and robust tracking method based on the collaboration of generative and discriminative models.

The SDC module can effectively deal with cluttered and complex background.

The SGM module enables our tracker to better handle heavy occlusion.

Experiments demonstrate the robustness of our tracker.

Thank You!

robust object tracking via sparsity-based collaborative model

Documents