Paper Info
Title
Robust Object Tracking via Locality Sensitive Histograms.
Abstract
This paper presents a novel locality sensitive histogram (LSH) algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrence of each intensity value by adding ones to the corresponding bin, an LSH is computed at each pixel location, and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value exponentially reduces with respect to the distance to the pixel location where the histogram is computed. An efficient algorithm is proposed that enables the LSHs to be computed in time linear in the image size and the number of bins. In addition, this efficient algorithm can be extended to exploit color images. A robust tracking framework based on the LSHs is proposed, which consists of two main components: a new feature for tracking that is robust to illumination change and a novel multiregion tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically. Evaluation using the latest benchmark shows that our algorithm is the top performer.
Year
DOI
Venue
2017
10.1109/TCSVT.2016.2527300
IEEE Trans. Circuits Syst. Video Techn.
Keywords
Field
DocType
Histograms,Target tracking,Visualization,Lighting,Robustness,Color
Computer vision,Histogram,Pattern recognition,Bin,Computer science,Robustness (computer science),Eye tracking,Video tracking,Artificial intelligence,Pixel,Image histogram,Image resolution
Journal
Volume
Issue
ISSN
27
5
1051-8215
Citations 
PageRank 
References 
4
0.39
28
Authors
5
Name
Order
Citations
PageRank
Shengfeng He140633.19
Rynson W. H. Lau272.79
Qingxiong Yang32586106.93
Jiang Wang41504.28
Yang Ming-Hsuan515303620.69