Towards long‐term UAV object tracking via effective feature matching. Issue 20 (1st September 2020)

• Record Type: Journal Article
• Authors: Zhao, Baojun; Wang, Hongshuo; Tang, Linbo; Han, Yuqi
• Is Part Of: Electronics letters. Volume 56:Issue 20(2020)
• Page Start: 1056
• Page End: 1059
• Publication Date: 2020-09-01
• Subjects: object tracking -- object detection -- feature extraction -- image matching -- pattern clustering -- remotely operated vehicles -- autonomous aerial vehicles -- image colour analysis -- image sequences -- target tracking; long‐term UAV object -- effective feature matching -- object tracking -- unmanned aerial vehicles -- UAVs -- extensive research attention -- collected local features -- novel density‐based -- tracking condition -- keypoint‐matching based confidence indicator -- density clustering -- local feature matching -- long‐term tracker -- long‐term UAV‐based tracking -- performance degradation -- crucial interference -- occlusion -- inherent advantage -- target owing; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2020.1096
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : Object tracking based on unmanned aerial vehicles (UAVs) has attracted extensive research attention recently since it provides the ability to continuously observing and tracking the target owing to its inherent advantage. However, occlusion is a crucial interference which may cause performance degradation in long‐term UAV‐based tracking. In this Letter, the authors propose a robust and efficient long‐term tracker based upon local feature matching and density clustering. To be more specific, the authors propose a keypoint‐matching based confidence indicator to monitor the tracking condition and activate the re‐detection module when occlusion is predicted. Once occlusion occurs, a novel density‐based clustering method is utilised to re‐locate the target with the collected local features. Extensive experiments have demonstrated that the proposed algorithm performs favourably against the other related trackers.