<p>While multi-object tracking is critical for autonomous driving systems, traditional algorithms exhibit three fundamental limitations in complex scenarios: (1) blurred feature representation under occlusion and re-identification scenarios causing identity switches, (2) insufficient sensitivity to scale-variant targets due to fixed geometric constraints in conventional IoU-based loss functions, and (3) gradient degradation in deep convolutional layers hindering discriminative feature learning. To address these challenges, we propose AE-StrongSORT (Attention-Enhanced StrongSORT), an attention-enhanced tracking framework featuring three systematic innovations: first, the GAM-YOLO (global attention mechanism-YOLO)hybrid architecture integrates multi-scale feature fusion with a global attention mechanism (GC2f structure). This design enhances cross-dimensional feature interaction through localized channel-spatial attention gates, significantly improving occlusion-resistant feature representation (IDF1 <InlineEquation ID="IEq1"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_99524_Article_IEq1.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="14" /> </InlineMediaObject> <EquationSource Format="TEX">\(\uparrow\)</EquationSource> </InlineEquation> 9.99%, IDsw <InlineEquation ID="IEq2"> <InlineMediaObject> <ImageObject Color="BlackWhite" FileRef="41598_2025_99524_Article_IEq2.gif" Format="GIF" Height="17" Rendition="HTML" Resolution="72" Type="Linedraw" Width="14" /> </InlineMediaObject> <EquationSource Format="TEX">\(\downarrow\)</EquationSource> </InlineEquation> 9.85%). Second, the F-EIoU loss function introduces dynamic size-dependent penalty terms and difficulty-adaptive weighting factors, effectively balancing learning priorities between small targets and normal instances. Third, the optimized CBH-Conv module employs Hardswish activation and depthwise separable convolution to mitigate gradient vanishing while maintaining real-time efficiency (achieving a 17% MOTA improvement at 213 FPS).Evaluated on the MOT-16 dataset, AE-StrongSORT demonstrates substantial improvements over the baseline StrongSORT, with 17%, 2.78%, and 9.99% gains in MOTA, HOTA, and IDF1 metrics respectively, alongside significant reductions in false/missed detections. These advances establish a novel technical pathway for robust vehicle tracking in real-world traffic scenarios characterized by coexisting challenges of scale variation, motion blur, and dense occlusion.</p>

Attention-enhanced StrongSORT for robust vehicle tracking in complex environments

期刊论文
出版模式：

开放获取
发表日期：

2025年5月20日

查看全文

Wei Xu,
Xiaodong Du,
Ruochen Li,
Bingjie Li,
Yuhu Jiao,
Lei Xing

摘要

While multi-object tracking is critical for autonomous driving systems, traditional algorithms exhibit three fundamental limitations in complex scenarios: (1) blurred feature representation under occlusion and re-identification scenarios causing identity switches, (2) insufficient sensitivity to scale-variant targets due to fixed geometric constraints in conventional IoU-based loss functions, and (3) gradient degradation in deep convolutional layers hindering discriminative feature learning. To address these challenges, we propose AE-StrongSORT (Attention-Enhanced StrongSORT), an attention-enhanced tracking framework featuring three systematic innovations: first, the GAM-YOLO (global attention mechanism-YOLO)hybrid architecture integrates multi-scale feature fusion with a global attention mechanism (GC2f structure). This design enhances cross-dimensional feature interaction through localized channel-spatial attention gates, significantly improving occlusion-resistant feature representation (IDF1 \(\uparrow\) 9.99%, IDsw \(\downarrow\) 9.85%). Second, the F-EIoU loss function introduces dynamic size-dependent penalty terms and difficulty-adaptive weighting factors, effectively balancing learning priorities between small targets and normal instances. Third, the optimized CBH-Conv module employs Hardswish activation and depthwise separable convolution to mitigate gradient vanishing while maintaining real-time efficiency (achieving a 17% MOTA improvement at 213 FPS).Evaluated on the MOT-16 dataset, AE-StrongSORT demonstrates substantial improvements over the baseline StrongSORT, with 17%, 2.78%, and 9.99% gains in MOTA, HOTA, and IDF1 metrics respectively, alongside significant reductions in false/missed detections. These advances establish a novel technical pathway for robust vehicle tracking in real-world traffic scenarios characterized by coexisting challenges of scale variation, motion blur, and dense occlusion.