Learning Multi-task Correlation Particle Filters for Visual Tracking

Tianzhu Zhang      Changsheng Xu      Ming-Hsuan Yang

 

Figure 1. The proposed model is able to cover object state well with a few particles. (a) The model can cover object state well by using search regions of particles. (b) The model can shepherd particles toward the target object.

Abstract


We propose a multi-task correlation particle filter (MCPF) for robust visual tracking. We first present the multi-task correlation filter (MCF) that takes the interdependencies among different object parts and features into account to learn their correlation filters jointly. Next, the proposed MCPF is introduced to exploit and complement the strength of a MCF and a particle filter. Compared with existing tracking methods based on correlation filters and particle filters, the proposed MCPF has several advantages. First, it exploits the interdependencies among different features to derive the correlation filters jointly, and makes the learned filters complement and enhance each other to obtain consistent responses. Second, it handles partial occlusion via a part-based representation, and exploits the intrinsic relationship among local parts via spatial constraints to preserve object structure and learn their correlation filters jointly. Third, it effectively handles large scale variation via a particle sampling scheme by drawing particles at different scales for target object state estimation. Fourth, it shepherds the sampled particles toward the modes of the target state distribution via the MCF, and effectively covers object states well using fewer particles than conventional particle filters, thereby resulting in robust tracking performance and low computational cost. Extensive experimental results on four challenging benchmark datasets demonstrate that the proposed MCPF tracking algorithm performs favorably against the state-of-the-art methods.

Related Publications


"Learning Multi-task Correlation Particle Filters for Visual Tracking"


Tianzhu Zhang, Changsheng Xu, Ming-Hsuan Yang.
Journal Version
[Paper] [Code] [Attribute Results] [Supplementary Material]

"Multi-task Correlation Particle Filter for Robust Object Tracking"


Tianzhu Zhang, Changsheng Xu, Ming-Hsuan Yang.
CVPR 2017
[Paper] [Code]

Experimental Results



Figure 2. Precision and success plots over all the 50 sequences using one-pass evaluation on the OTB-2013 Dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.

Figure 3. Precision and success plots over all 100 sequences using one-pass evaluation on the OTB-2015 dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.

Figure 4. Precision and success plots over the 128 sequences using one-pass evaluation on the Temple Color dataset. The legend contains the area-under-the-curve score and the average distance precision score at 20 pixels for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.


Figure 5. Comparison with the state-of-the-art tracking methods on the VOT2015 dataset. The results are presented in terms of robustness and accuracy. The proposed MCPF method performs favorably against the state-of-the-art trackers.


Figure 6. Tracking performance based on attributes of image sequences in the OTB2013 dataset. Success and precision plots on 11 tracking challenges of scale variation, out of view, out-of-plane rotation, low resolution, in-plane rotation, illumination, motion blur, background clutter, occlusion, deformation, and fast motion. The legend contains the AUC and PS scores for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.


Figure 7. Tracking performance based on attributes of image sequences on the OTB2015 dataset. Success and precision plots on 11 tracking challenges of scale variation, out of view, out-of-plane rotation, low resolution, in-plane rotation, illumination, motion blur, background clutter, occlusion, deformation, and fast motion. The legend contains the AUC and PS scores for each tracker. Our MCPF method performs favorably against the state-of-the-art trackers.


Video Tracking Results


We show tracking results of 25 challenging videos.



car4


deer


skating1


soccer


shaking


singer1


singer2


couple


jogging-1


walking2


jumping


skiing


lemming


motorRolling


basketball


tiger1


tiger2


woman


sylvester


motorRolling


jogging 2


football1


fleetface


faceocc2


dudek


 



Thank you for visiting my project!