Part-Based Visual Tracking with Online Latent Structural Learning

Rui Yao, Qinfeng Shi, Chunhua Shen, Yanning Zhang, Anton van den Hengel; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013, pp. 2363-2370

Abstract


Despite many advances made in the area, deformable targets and partial occlusions continue to represent key problems in visual tracking. Structured learning has shown good results when applied to tracking whole targets, but applying this approach to a part-based target model is complicated by the need to model the relationships between parts, and to avoid lengthy initialisation processes. We thus propose a method which models the unknown parts using latent variables. In doing so we extend the online algorithm pegasos to the structured prediction case (i.e., predicting the location of the bounding boxes) with latent part variables. To better estimate the parts, and to avoid over-fitting caused by the extra model complexity/capacity introduced by the parts, we propose a two-stage training process, based on the primal rather than the dual form. We then show that the method outperforms the state-of-the-art (linear and non-linear kernel) trackers.

Related Material


[pdf]
[bibtex]
@InProceedings{Yao_2013_CVPR,
author = {Yao, Rui and Shi, Qinfeng and Shen, Chunhua and Zhang, Yanning and van den Hengel, Anton},
title = {Part-Based Visual Tracking with Online Latent Structural Learning},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2013}
}