Title :
Key Point Detection by Max Pooling for Tracking
Author :
Xiaoyuan Yu ; Jianchao Yang ; Tianjiang Wang ; Huang, Thomas
Author_Institution :
Dept. of Comput. Sci., Huazhong Univ. of Sci. & Technol., Wuhan, China
Abstract :
Inspired by the recent image feature learning work, we propose a novel key point detection approach for object tracking. Our approach can select mid-level interest key points by max pooling over the local descriptor responses from a set of filters. Linear filters are first learned from targets in first frames. Then max pooling is performed over data driven spatial supporting field to detect discriminant key points, and thus the detected key points bear higher level semantic meanings, which we apply in tracking by structured key point matching. We show that our tracking system is robust to occlusions and cluttered background. Testing on several challenging tracking sequences, we demonstrate that our proposed tracking system can achieve competitive or better performances than the state-of-the-art trackers.
Keywords :
image matching; image sequences; learning (artificial intelligence); object detection; object tracking; image feature learning; key point detection approach; linear filters; max pooling; object tracking; semantic meanings; structured key point matching; tracking sequences; Cybernetics; Encoding; Feature extraction; Lighting; Robustness; Target tracking; Visualization; Data driven max pooling; key point detection; mid-level feature learning; object tracking;
Journal_Title :
Cybernetics, IEEE Transactions on
DOI :
10.1109/TCYB.2014.2327246