论文标题
detr人群探测
DETR for Crowd Pedestrian Detection
论文作者
论文摘要
人群场景中的行人发现提出了一个具有挑战性的问题，这是由于启发式定义的映射从锚到行人到行人，以及NMS与高度重叠的行人之间的冲突。最近提出的端到端检测器（ED），DETR和可变形的DETR，使用Transformer架构替换手工设计的组件，例如NMS和锚固，通过计算查询之间的所有成对交互，从而消除了重复的预测。受这些作品的启发，我们探索了他们在人群人群检测中的表现。出乎意料的是，与使用FPN更快的RCNN相比，结果与可可获得的结果相反。此外，由于人群场景中的地面真相数量较大，ED的双方比赛损害了训练效率。在这项工作中，我们确定了推动埃德（Ed）表现不佳的基本动机，并提出了一个新的解码器来解决这些问题。此外，我们设计了一种机制来利用专门用于ED的行人的遮挡较少的可见部分，并实现进一步的改进。还引入了更快的两分匹配算法，以使人群数据集的ED培训更加实用。拟议的检测器PED（行人端到端探测器）在Citypersons和CrowdHuman上的表现都优于先前的EDS，而基线更快。它还通过最先进的行人检测方法实现了可比的性能。代码将很快发布。
Pedestrian detection in crowd scenes poses a challenging problem due to the heuristic defined mapping from anchors to pedestrians and the conflict between NMS and highly overlapped pedestrians. The recently proposed end-to-end detectors(ED), DETR and deformable DETR, replace hand designed components such as NMS and anchors using the transformer architecture, which gets rid of duplicate predictions by computing all pairwise interactions between queries. Inspired by these works, we explore their performance on crowd pedestrian detection. Surprisingly, compared to Faster-RCNN with FPN, the results are opposite to those obtained on COCO. Furthermore, the bipartite match of ED harms the training efficiency due to the large ground truth number in crowd scenes. In this work, we identify the underlying motives driving ED's poor performance and propose a new decoder to address them. Moreover, we design a mechanism to leverage the less occluded visible parts of pedestrian specifically for ED, and achieve further improvements. A faster bipartite match algorithm is also introduced to make ED training on crowd dataset more practical. The proposed detector PED(Pedestrian End-to-end Detector) outperforms both previous EDs and the baseline Faster-RCNN on CityPersons and CrowdHuman. It also achieves comparable performance with state-of-the-art pedestrian detection methods. Code will be released soon.
