A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Robust object tracking guided by top-down spectral analysis visual attention
2015
Neurocomputing
Object tracking is an important computer vision task, and existing tracking algorithms have achieved great progress. However, several challenging issues still remain to be solved, such as abrupt motion, longtime complete occlusion and target reappearing after moving completely out of the frame. To address these issues, we propose a top-down spectral analysis visual attention guided tracking method. Given an image sequence, top-down saliency maps for each input image are calculated by
doi:10.1016/j.neucom.2014.11.006
fatcat:eri6al7kp5a33lfpjlmogd5epu