Abstract

warp_img_132warp_pro_132Seg_img_132

 

While numerous algorithms have been proposed for object tracking with demonstrated success, it remains a challenging problem for a tracker to handle large change in scale, motion, shape deformation with occlusion. One of the main reasons is the lack of effective image representation to account for appearance variation.

 

Most trackers use high-level appearance structure or low-level cues for representing and matching target objects. In this paper, we propose a tracking method from the perspective of mid-level vision with structural information captured in superpixels.

 

We present a discriminative appearance model based on superpixels, thereby facilitating a tracker to distinguish the target and the background with mid-level cues. The tracking task is then formulated by computing a target-background confidence map, and obtaining the best candidate by maximum a posterior estimate.

 

Experimental results demonstrate that our tracker is able to handle heavy occlusion and recover from drifts. In conjunction with online update, the proposed algorithm is shown to perform favorably against existing methods for object tracking.

Related Papers

Superpixel Tracking
Shu Wang, Huchuan Lu, Fan Yang and Ming-Hsuan Yang.
In the 13th International Conference on Computer Vision (ICCV 2011)
Barcelona, Spain,  [PDF][CODE][DATA].

Tracking Result of Figure/Ground Segmentation Across Frames

(Sequence liquor, from Santner et al.)

 

 

Results and Datasets

lemming

 

[Download data (zip)] [Precision plot]

This Sequence is from Santner et al.

liquor

 

[Download data (zip)] [Precision plot]

This Sequence is from Santner et al.

singer1

 

[Download data (zip)] [Precision plot]

This Sequence is from Kwon et al.

basketball

 

[Download data (zip)] [Precision plot]

This Sequence is from Kwon et al.

woman

 

[Download data (zip)] [Precision plot]

This Sequence is from Adam et al.

transformer

 

[Download data (zip)] [Precision plot]

This Sequence is from Kwon et al.

bolt

 

[Download data (zip)] [Precision plot]

New Sequence from Our Own

bird1

 

[Download data (zip)] [Precision plot]

New Sequence from Our Own

bird2

 

[Download data (zip)] [Precision plot]

New Sequence from Our Own

girl

 

[Download data (zip)] [Precision plot]

New Sequence from Our Own