Accurate scale estimation for visual tracking with significant deformation. Issue 5 (1st July 2020)

• Record Type: Journal Article
• Authors: Chu, Lutao; Li, Huiyun; Yang, Zhiheng
• Is Part Of: IET computer vision. Volume 14:Issue 5(2020)
• Page Start: 278
• Page End: 287
• Publication Date: 2020-07-01
• Subjects: object tracking -- tracking -- learning (artificial intelligence) -- feature extraction -- image representation -- regression analysis -- object detection; accurate scale estimation -- visual tracking -- significant deformation -- scale variation -- tracking methods -- exhaustive search -- target scales -- finite scales -- discrete scales -- scale estimation method -- scale tracking -- entire continuous scale space -- single-channel BBR -- multichannel situations -- multichannel features -- multichannel BBR -- scale divergence degree -- outstanding scale estimation performance; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2019.0860
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Scale variation of a target frequently appears in tasks of visual tracking. Accurate scale estimation is challenging due to deformation, occlusion, rotation, change in the view angle and diversity of tracking object categories. Most tracking methods employ an exhaustive search of scales to estimate the target scales. However, only finite and discrete scales are usually searched due to the expensive computation requirement. Here, the authors propose a novel scale estimation method based on bounding box regression (BBR). They first formulate the scale tracking as a regression problem, and search for the entire continuous scale space without being limited by a manually specified number of scales. Then they extend the original single‐channel BBR to multi‐channel situations, to allow for better employment of multi‐channel features. To further take advantage of the time prior information of training samples, they derive a time‐related sample weighted multi‐channel BBR. Besides, they propose a quantitative measurement, scale divergence degree, to reflect the diversity of sampling strategy. Experimental results on OTB‐2015D dataset demonstrate that the proposed approach achieves outstanding scale estimation performance for visual tracking with significant deformation.