Object instance search in videos

Jingjing Meng, Junsong Yuan, Gang Wang, Jianbo Xu
2013 2013 9th International Conference on Information, Communications & Signal Processing  
In this paper, we propose a novel approach for object instance search in videos. Employing discriminative mutual information score and inferring the location of target object centers from matched local feature descriptors using Hough voting, we achieve robust matching and per-frame localization despite orientation and scale variations. We then leverage Max-Path search [1] to efficiently find the globally optimal spatiotemporal trajectory of the object center in each video sequence. Experimental
more » ... results on a collection of mobile-captured videos in real-world environments demonstrate the effectiveness and accuracy of our method.
doi:10.1109/icics.2013.6782862 dblp:conf/IEEEicics/MengYWX13 fatcat:tqwjvhoqj5ghrdvvedpxw3o5qe