Visual tracking via spatially aligned correlation filters network

Zhang, M. and Wang, Q. and Xing, J. and Gao, J. and Peng, P. and Hu, W. and Maybank, Stephen J. (2018) Visual tracking via spatially aligned correlation filters network. In: Ferrari, V. and Hebert, M. and Sminchisescu, C. and Weiss, Y. (eds.) Computer Vision – ECCV 2018: 15th European Conference, Munich, Germany, September 8–14, 2018, Proceedings, Part III. Lecture Notes in Computer Science 11207. Springer, pp. 484-500. ISBN 9783030012182.

Abstract

Correlation filters based trackers rely on a periodic assumption of the search sample to efficiently distinguish the target from the background. This assumption however yields undesired boundary effects and restricts aspect ratios of search samples. To handle these issues, an end-to-end deep architecture is proposed to incorporate geometric transformations into a correlation filters based network. This architecture introduces a novel spatial alignment module, which provides continuous feedback for transforming the target from the border to the center with a normalized aspect ratio. It enables correlation filters to work on well-aligned samples for better tracking. The whole architecture not only learns a generic relationship between object geometric transformations and object appearances, but also learns robust representations coupled to correlation filters in case of various geometric transformations. This lightweight architecture permits real-time speed. Experiments show our tracker effectively handles boundary effects and aspect ratio variations, achieving state-of-the-art tracking results on recent benchmarks.

Metadata

Statistics

DownloadsShow export options

Export as XMLJSONCSV

Activity Overview

6 month trend

245Downloads

6 month trend

136Hits

Additional statistics are available via IRStats2.

Archive Staff Only (login required)

Edit/View Item