ASiam: adaptive Siamese regression tracking with adversarial template generation and motion‐based failure recovery. Issue 14 (1st December 2019)

• Record Type: Journal Article
• Authors: Jiang, Xiaolong; Xiao, Zehao; Zhang, Baochang; Cao, Xianbin
• Is Part Of: IET image processing. Volume 13:Issue 14(2019)
• Page Start: 2694
• Page End: 2705
• Publication Date: 2019-12-01
• Subjects: image motion analysis -- object tracking -- object detection -- learning (artificial intelligence) -- target tracking -- regression analysis; ASiam -- novel adversarial template generation module -- motion‐based failure recovery module -- temporal coherence -- adaptive target template -- sharp template quality -- Siamese tracking backbone -- motion response map -- adaptive Siamese regression tracking -- object tracking -- temporal evolution -- motion detection -- motion‐based failure recovery; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6699
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Object tracking is challenged by the varying appearances of targets and the real‐time requirement. Siamese regression trackers, being one of the most popular tracking paradigms, excel in efficiency but suffer at adaptability to cope with appearance variations. To improve their adaptability, the authors propose a new adaptive Siamese (ASiam) tracker, which integrates a novel adversarial template generation module and a motion‐based failure recovery module. The template generation module exploits the temporal coherence and evolution of target appearance variations encoded in preceding tracklets and then generates an adaptive target template online which approximates the varying target in the coming frame. This generation module is optimised via adversarial learning to achieve accurate appearance prediction and sharp template quality. The generated template, together with a search region, are fed into a Siamese tracking backbone to compute an appearance response map via dense similarity computation in a sliding‐window way. At frames where the Siamese tracking fails, the failure recovery module is invoked to perform deep frame differencing motion detection to provide a motion response map. By fusing different response maps, the drifted tracker can be re‐calibrated. Extensive experiments on the OTB2013, OTB2015, and VOT2016 datasets prove the accuracy and efficiency of the proposed tracker.