Please use this identifier to cite or link to this item: http://localhost/handle/Hannan/232373
Title: Robust Object Tracking via Locality Sensitive Histograms
Authors: Shengfeng He;Rynson W. H. Lau;Qingxiong Yang;Jiang Wang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
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.
URI: http://localhost/handle/Hannan/232373
volume: 27
issue: 5
More Information: 1006,
1017
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7401033.pdf5.02 MBAdobe PDF
Title: Robust Object Tracking via Locality Sensitive Histograms
Authors: Shengfeng He;Rynson W. H. Lau;Qingxiong Yang;Jiang Wang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
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.
URI: http://localhost/handle/Hannan/232373
volume: 27
issue: 5
More Information: 1006,
1017
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7401033.pdf5.02 MBAdobe PDF
Title: Robust Object Tracking via Locality Sensitive Histograms
Authors: Shengfeng He;Rynson W. H. Lau;Qingxiong Yang;Jiang Wang;Ming-Hsuan Yang
Year: 2017
Publisher: IEEE
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.
URI: http://localhost/handle/Hannan/232373
volume: 27
issue: 5
More Information: 1006,
1017
Appears in Collections:2017

Files in This Item:
File SizeFormat 
7401033.pdf5.02 MBAdobe PDF