Robust Object Tracking via Locality Sensitive Histograms

• Main Authors: HE, Shengfeng, LAU, Rynson W.H, YANG, Qingxiong, WANG, Jiang, YANG, Ming-Hsuan
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2017
• Subjects: Illumination changes; Illumination invariant; Image histograms; Intensity values; Locality sensitives; State-of-the-art methods; Tracking algorithm; Visual tracking; Databases and Information Systems; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/8364; https://ink.library.smu.edu.sg/context/sis_research/article/9367/viewcontent/Robust_Object_Tracking_via_Locality_Sensitive_Histograms.pdf
• Institution: Singapore Management University

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-poi...