An object tracking method using deep learning and adaptive particle filter for night fusion image

Affiliation of Author(s):民航学院

Journal:Proc. Int. Conf. Prog. Inf. Comput., PIC

Abstract:In this paper, we propose an online visual tracking algorithm for fused sequences via deep learning and adaptive Particle filter (PF). Our algorithm pretrains a simplified Convolution Neural Network (CNN) to obtain a generic target representation. The outputs from the hidden layers of the network help to form the tracking model for an online PF. During tracking, the moving information guides the distribution of particle samples. The tests illustrate competitive performance compared to the state-of-art tracking algorithms especially when the target or camera moves quickly. © 2017 IEEE.

Translation or Not:no

Date of Publication:2017-01-01

Co-author:hl,Zhang, Yanlin,Meng Ding

Correspondence Author:qxy

Date of Publication:2017-01-01