.png){kind=icon}
.png){kind=icon}
Return
TSTrack: A Lightweight Transformer-Based Spatiotemporal Feature Refinement Tracking Algorithm
.png){kind=icon}
PRE
AI
DOI：10.1109/TGRS.2025.3614769.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Single-object tracking is a fundamental enabling technology in the field of remote sensing observation. It plays a crucial role in tasks such as uncrewed aerial vehicle (UAV) route surveillance and maritime vessel trajectory prediction. However, because of challenges such as the weak discriminative power of target features, interference from complex environments, and frequent viewpoint changes, existing trackers often suffer from insufficient temporal modeling capabilities and low computational efficiency, which limit their practical deployment. To address these challenges, we propose TSTrack, a novel lightweight single-object tracking framework that integrates Transformer and Mamba-based spatiotemporal modeling. First, we propose the target-aware feature purification preprocessor (TAFPP), designed to dynamically enhance target representation through a synergistic combination of the dynamic position acuity module (DPAM) and spectral channel recalibrator (SCR). Second, we introduce the recurrent Mamba interaction pyramid (RM-IP) to replace traditional recurrent neural network-based structures, leveraging a state-space model (SSM) for efficient and expressive temporal modeling with significantly reduced parameter overhead. Finally, we propose the elastic reconstructive multiscale fusion (ERMSF) module, which adopts a four-branch parallel architecture to achieve effective multiscale feature fusion and dynamic shape adaptation, thereby enhancing robustness against target deformations and scale variations. Extensive experiments conducted on benchmark datasets, including LaSOT, TrackingNet, and GOT-10k, demonstrate the effectiveness of TSTrack. The results show that TSTrack achieves a superior tracking accuracy while maintaining a lightweight design, significantly outperforming existing state-of-the-art methods. The source code is publicly available at https://github.com/BJUTsipl/TSTrack
Keywords:
Mamba
single stream
single target tracking
transformer
Journal
IF:
8.6
Papers:
2.1W
Citations:
10.7W