TY - GEN
T1 - Reliable Patch Trackers
T2 - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
AU - Li, Yang
AU - Zhu, Jianke
AU - Hoi, Steven C.H.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/10/14
Y1 - 2015/10/14
N2 - Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization. In this paper, we propose a new tracking method, Reliable Patch Trackers (RPT), which attempts to identify and exploit the reliable patches that can be tracked effectively through the whole tracking process. Specifically, we present a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework. As the reliable patches distributed over the image, we exploit the motion trajectories to distinguish them from the background. Therefore, the visual object can be defined as the clustering of homo-trajectory patches, where a Hough voting-like scheme is employed to estimate the target state. Encouraging experimental results on a large set of sequences showed that the proposed approach is very effective and in comparison to the state-of-the-art trackers. The full source code of our implementation will be publicly available.
AB - Most modern trackers typically employ a bounding box given in the first frame to track visual objects, where their tracking results are often sensitive to the initialization. In this paper, we propose a new tracking method, Reliable Patch Trackers (RPT), which attempts to identify and exploit the reliable patches that can be tracked effectively through the whole tracking process. Specifically, we present a tracking reliability metric to measure how reliably a patch can be tracked, where a probability model is proposed to estimate the distribution of reliable patches under a sequential Monte Carlo framework. As the reliable patches distributed over the image, we exploit the motion trajectories to distinguish them from the background. Therefore, the visual object can be defined as the clustering of homo-trajectory patches, where a Hough voting-like scheme is employed to estimate the target state. Encouraging experimental results on a large set of sequences showed that the proposed approach is very effective and in comparison to the state-of-the-art trackers. The full source code of our implementation will be publicly available.
UR - https://www.scopus.com/pages/publications/84959247253
U2 - 10.1109/CVPR.2015.7298632
DO - 10.1109/CVPR.2015.7298632
M3 - 会议稿件
AN - SCOPUS:84959247253
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 353
EP - 361
BT - IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2015
PB - IEEE Computer Society
Y2 - 7 June 2015 through 12 June 2015
ER -