Dawei Yang

Dawei Yang

Auto-generated profile, based on publicly available information

Dawei Yang

University of Science and Technology of China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2023
Verified
Conference Paper
Closed access
QYQianjin Yu
Qianjin Yu
YMYinchao Ma
Yinchao Ma
JHJianfeng He
Jianfeng He
DYDawei Yang
Dawei Yang
TZTianzhu Zhang
Tianzhu Zhang
Recently, the need for advanced anti-UAV techniques is increasing due to the rising threat of unauthorized drone intrusion. Object tracking, specifically in thermal infrared (TIR) videos, offers a potential solution to this issue. However, the tracked target often suffers dramatic scale variation, frequent target disappearance, and camera movement which severely influence tracking performance. Therefore, we propose a Unified Transformer-based Tracker, dubbed UTTracker, which contains the following four modules. Firstly, a multi-region local tracking module is designed with temporal cues for tackling target appearance variation and multi-region search for tracking targets in multi proposals. Complementarily, a global detection module is introduced to meet the challenge of target frequent disappearance. Meanwhile, a background correction module is incorporated to align the backgrounds between adjacent frames for alleviating camera movement. Particularly, a dynamic small object detection module for tracking the small target that lacks appearance information. Thanks to the designed modules, our UTTracker can achieve robust UAV tracking in TIR scenarios. Numerous experiments on the 1st and 2nd anti-UAV benchmarks demonstrate the effectiveness of UTTracker. Notably, UTTracker is the foundation of the 2nd-place winning entry in the 3rd Anti-UAV Challenge.

16 May 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
YMYinchao Ma
Yinchao Ma
JHJianfeng He
Jianfeng He
DYDawei Yang
Dawei Yang
TZTianzhu Zhang
Tianzhu Zhang
FWFeng Wu
Feng Wu
Visual tracking aims to estimate object state in a video sequence, which is challenging when facing drastic appearance changes. Most existing trackers conduct tracking with divided parts to handle appearance variations. However, these trackers commonly divide target objects into regular patches by a hand-designed splitting way, which is too coarse to align object parts well. Besides, a fixed part detector is difficult to partition targets with arbitrary categories and deformations. To address the above issues, we propose a novel adaptive part mining tracker (APMT) for robust tracking via a transformer architecture, including an object representation encoder, an adaptive part mining decoder, and an object state estimation decoder. The proposed APMT enjoys several merits. First, in the object representation encoder, object representation is learned by distinguishing target object from background regions. Second, in the adaptive part mining decoder, we introduce multiple part prototypes to adaptively capture target parts through cross-attention mechanisms for arbitrary categories and deformations. Third, in the object state estimation decoder, we propose two novel strategies to effectively handle appearance variations and distractors. Extensive experimental results demonstrate that our APMT achieves promising results with high FPS. Notably, our tracker is ranked the first place in the VOT-STb2022 challenge.