กก
Fast Tracking via Spatio-Temporal
Context Learning
Kaihua Zhang1, Lei Zhang1, Ming-Hsuan Yang2, David Zhang1
1Dept. of Computing, The Hong Kong Polytechnic University, Hong Kong
2Electrical Engineering and Computer Science, University of California at Merced, United States
(a) Learn spatial context at the t-th frame
(b) Detect object location at the (t+1)-th frame
ABSTRACT
In this paper, we present a simple yet fast and robust algorithm which exploits the spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its local context based on a Bayesian framework, which models the statistical correlation between the low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is posed by computing a confidence map, and obtaining the best target location by maximizing an object location likelihood function. The Fast Fourier Transform is adopted for fast learning and detection in this work. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.
กก
PAPER
Fast Tracking via Spatio-Temporal Context Learning. Kaihua Zhang, Lei Zhang, Ming-Hsuan Yang, David Zhang. Submitted.
[PDF]
SOURCE CODES
DATA
DEMO
If you have any questions, please contact
Kaihua Zhang, zhkhua at gmail dot com
Kaihua Zhang Last Updated: 2013-11-24