SMMT提升红外目标跟踪精度，解决遮挡与模糊问题
SMMT: Siamese Motion Mamba with Self-attention for Thermal Infrared Target Tracking
- 用双向状态空间+自注意力捕捉运动特征，恢复边缘细节
- 共享参数减少计算量，保持强表征能力，准确率显著提升
- 适合处理模糊、遮挡严重的红外视频跟踪任务
热红外（TIR）目标跟踪常受目标遮挡、运动模糊和背景杂乱等挑战影响，严重降低追踪性能。本文提出一种新型孪生运动马尔可夫追踪器（SMMT），融合双向状态空间模型与自注意力机制。具体而言，将运动马尔可夫模块引入孪生结构，利用双向建模和自注意力提取运动特征并恢复被忽略的边缘细节。设计了一种孪生权重共享策略，使部分卷积层共享参数，减少计算冗余的同时保持强特征表示能力。此外，提出一种运动边缘感知回归损失，提升对运动模糊目标的追踪精度。在四个热红外跟踪基准数据集（LSOTB-TIR、PTB-TIR、VOT-TIR2015、VOT-TIR2017）上进行了大量实验，结果表明SMMT在热红外目标跟踪中表现卓越。
原文摘要 · Abstract (English)
Thermal infrared (TIR) object tracking often suffers from challenges such as target occlusion, motion blur, and background clutter, which significantly degrade the performance of trackers. To address these issues, this paper pro-poses a novel Siamese Motion Mamba Tracker (SMMT), which integrates a bidirectional state-space model and a self-attention mechanism. Specifically, we introduce the Motion Mamba module into the Siamese architecture to ex-tract motion features and recover overlooked edge details using bidirectional modeling and self-attention. We propose a Siamese parameter-sharing strate-gy that allows certain convolutional layers to share weights. This approach reduces computational redundancy while preserving strong feature represen-tation. In addition, we design a motion edge-aware regression loss to improve tracking accuracy, especially for motion-blurred targets. Extensive experi-ments are conducted on four TIR tracking benchmarks, including LSOTB-TIR, PTB-TIR, VOT-TIR2015, and VOT-TIR 2017. The results show that SMMT achieves superior performance in TIR target tracking.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。