DocumentCode :
3757283
Title :
Study on Deep Learning and Its Application in Visual Tracking
Author :
Dan Hu;Xingshe Zhou;Xiaohao Yu;Zhiqiang Hou
Author_Institution :
Sch. of Comput. Sci., Northwestern Polytech. Univ., Xi´an, China
fYear :
2015
Firstpage :
240
Lastpage :
246
Abstract :
Inspired by recent advances in deep learning, this paper reviews the deep learning methodologies and its applications in object tracking. To overcome the complexity and low-efficiency of existing full-connected deep learning based tracker, we use a novel convolutional deep belief network (CDBN) with convolution, weights sharing and pooling to have much fewer parameters, in addition to gain translation invariance which would benefit the tracker performance. Empirical evaluation demonstrates our CDBN based tracker outperforms several state-of-the-art methods on an open tracker benchmark.
Keywords :
"Machine learning","Visualization","Convolution","Feature extraction","Kernel","Training","Neural networks"
Publisher :
ieee
Conference_Titel :
Broadband and Wireless Computing, Communication and Applications (BWCCA), 2015 10th International Conference on
Type :
conf
DOI :
10.1109/BWCCA.2015.63
Filename :
7424831
Link To Document :
بازگشت