用密度图改进拥挤场景下的目标检测，减少误检和漏检。
Density-based Object Detection in Crowded Scenes
- 基于密度图与最优传输，动态分配锚点并加权
- 在CrowdHuman上提升检测精度，尤其在高密度区域
- 适合处理行人密集、重叠严重的监控场景
与普通场景相比，拥挤场景中目标高度重叠，导致训练时锚点模糊，推理时预测易被错误抑制。为此，提出密度引导锚点（DGA）和密度引导NMS（DG-NMS）。通过非平衡最优传输（UOT）问题，将每个真实目标的密度以最小运输成本分配至锚点位置，生成具有实例特性的密度分布，用于优化锚点分配与权重；同时，利用预测密度图自适应调整NMS阈值，减少误抑制。设计了针对重叠邻近物体的重叠感知运输代价，有效应对模糊锚点。在挑战性数据集CrowdHuman和Citypersons上的实验表明，所提方法在拥挤场景下具有更强的鲁棒性与有效性。代码与预训练模型将后续公开。
原文摘要 · Abstract (English)
Compared with the generic scenes, crowded scenes contain highly-overlapped instances, which result in: 1) more ambiguous anchors during training of object detectors, and 2) more predictions are likely to be mistakenly suppressed in post-processing during inference. To address these problems, we propose two new strategies, density-guided anchors (DGA) and density-guided NMS (DG-NMS), which uses object density maps to jointly compute optimal anchor assignments and reweighing, as well as an adaptive NMS. Concretely, based on an unbalanced optimal transport (UOT) problem, the density owned by each ground-truth object is transported to each anchor position at a minimal transport cost. And density on anchors comprises an instance-specific density distribution, from which DGA decodes the optimal anchor assignment and re-weighting strategy. Meanwhile, DG-NMS utilizes the predicted density map to adaptively adjust the NMS threshold to reduce mistaken suppressions. In the UOT, a novel overlap-aware transport cost is specifically designed for ambiguous anchors caused by overlapped neighboring objects. Extensive experiments on the challenging CrowdHuman dataset with Citypersons dataset demonstrate that our proposed density-guided detector is effective and robust to crowdedness. The code and pre-trained models will be made available later.
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。