论文标题
抵抗人群的阻塞和艰难的否定因素，以供野外探测
Resisting Crowd Occlusion and Hard Negatives for Pedestrian Detection in the Wild
论文作者
论文摘要
由于其广泛的应用，在过去的十年中，行人的检测经过了大量研究。尽管进展不断，但人群阻塞和艰难的负面因素仍在挑战当前最新的行人探测器。在本文中，我们提供了两种基于一般基于区域的检测框架来应对这些挑战的方法。具体来说，为了解决闭塞，我们将新型的库仑损失设计为边界框回归的调节器，其中提案被其目标实例吸引，并被相邻的非目标实例所击退。对于艰苦的负面因素，我们提出了一个有效的语义驱动策略来选择锚点位置，该策略可以在培训阶段进行分类细化的培训阶段的信息负面示例。值得注意的是，这些方法也可以应用于一般对象检测域，并且可以以端到端的方式训练。我们在Caltech-Usa和Citypersons基准测试中始终取得了持续的高性能。
Pedestrian detection has been heavily studied in the last decade due to its wide application. Despite incremental progress, crowd occlusion and hard negatives are still challenging current state-of-the-art pedestrian detectors. In this paper, we offer two approaches based on the general region-based detection framework to tackle these challenges. Specifically, to address the occlusion, we design a novel coulomb loss as a regulator on bounding box regression, in which proposals are attracted by their target instance and repelled by the adjacent non-target instances. For hard negatives, we propose an efficient semantic-driven strategy for selecting anchor locations, which can sample informative negative examples at training phase for classification refinement. It is worth noting that these methods can also be applied to general object detection domain, and trainable in an end-to-end manner. We achieves consistently high performance on the Caltech-USA and CityPersons benchmarks.
