DocumentCode :
178776
Title :
Visual Tracking Using Multi-stage Random Simple Features
Author :
Yang He ; Zhen Dong ; Min Yang ; Lei Chen ; Mingtao Pei ; Yunde Jia
Author_Institution :
Beijing Lab. of Intell. Inf. Technol., Beijing Inst. of Technol., Beijing, China
fYear :
2014
fDate :
24-28 Aug. 2014
Firstpage :
4104
Lastpage :
4109
Abstract :
In recent years, deep models offer a promising solution to extract powerful features. Motivated by the effectiveness of the Convolutional Networks (ConvNets) model in image classification and object detection, we present a visual tracking algorithm using the ConvNets model to extract multistage features. The key point of this paper is to show that the multi-stage features extracted by the ConvNets are very proper for visual tracking. In addition, we design a general procedure to generate simple rectangle filters with different complexity, and employ the rectangle filters to construct the ConvNets. The computational cost is reduced by using integral images. The filters are kept constant, thus the update of our tracker would not cost much time. The tracking is formulated as a binary classification problem, and we use an online naive Bayes classifier to build our tracker. The experimental results demonstrate that our tracker achieves comparable results against several state-of-the-art methods.
Keywords :
Bayes methods; feature extraction; filtering theory; image classification; object detection; object tracking; Bayes classifier; ConvNets model; convolutional networks; image classification; integral images; multistage random simple features; object detection; rectangle filters; visual tracking; Computational modeling; Computer vision; Feature extraction; Robustness; Target tracking; Visualization; convolutional neural networks; multi-stage random features; visual tracking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Pattern Recognition (ICPR), 2014 22nd International Conference on
Conference_Location :
Stockholm
ISSN :
1051-4651
Type :
conf
DOI :
10.1109/ICPR.2014.703
Filename :
6977416
Link To Document :
بازگشت