Object Tracking by Unified Semantic Knowledge and Instance Features

Suofei ZHANG  Bin KANG  Lin ZHOU  

IEICE TRANSACTIONS on Information and Systems   Vol.E102-D   No.3   pp.680-683
Publication Date: 2019/03/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.2018EDL8181
Type of Manuscript: LETTER
Category: Image Recognition, Computer Vision
object tracking,  convolutional neural networks,  bounding box regression,  

Full Text: PDF(978.7KB)
>>Buy this Article

Instance features based deep learning methods prompt the performances of high speed object tracking systems by directly comparing target with its template during training and tracking. However, from the perspective of human vision system, prior knowledge of target also plays key role during the process of tracking. To integrate both semantic knowledge and instance features, we propose a convolutional network based object tracking framework to simultaneously output bounding boxes based on different prior knowledge as well as confidences of corresponding Assumptions. Experimental results show that our proposed approach retains both higher accuracy and efficiency than other leading methods on tracking tasks covering most daily objects.