WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
WiderPerson: A Diverse Dataset for Dense Pedestrian Detection in the Wild
复制标题
WiderPerson：用于野外密集行人检测的多样化数据集
DOI：
10.1109/tmm.2019.2929005
复制
发表时间：
2020-02-01
影响因子：
7.3
通讯作者：
Guo, Guodong
中科院分区：
文献类型：
--
作者：
Zhang, Shifeng;Xie, Yiliang;Guo, Guodong
随着现有基准数据集的可用性，行人检测已经取得了重大进展。然而，在真实的世界需求和当前行人检测基准之间的多样性和密度方面存在差距：首先，大多数现有数据集取自车辆行驶通过常规交通场景，通常导致多样性不足;其次，具有高度遮挡行人的人群场景仍然代表性不足，导致密度低。为了缩小这一差距，促进未来的行人检测研究，我们引入了一个大型而多样化的数据集WiderPerson，用于在野外进行密集行人检测。该数据集涉及广泛场景中的五种类型的注释，不再局限于交通场景。总共有13 382幅图像，具有399 786个注释，即每幅图像29.87个注释，这意味着该数据集包含具有各种遮挡的密集行人。因此，由于场景和遮挡的变化很大，所提出的数据集中的行人极具挑战性，这适合于评估野外的行人检测器。我们引入了改进的Faster R-CNN和vanilla RetinaNet作为新行人检测基准的基线。在以前的数据集上进行了几个实验，包括Caltech-USA和CityPersons，以分析所提出的数据集的泛化能力，我们在这些以前的数据集上实现了最先进的性能，没有花里胡哨。最后，我们分析了常见的故障情况，发现行人检测器的分类能力需要提高，以减少误报率和误检率。建议的数据集可在http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson上获得。
Pedestrian detection has achieved significant progress with the availability of existing benchmark datasets. However, there is a gap in the diversity and density between real world requirements and current pedestrian detection benchmarks: first, most existing datasets are taken from a vehicle driving through the regular traffic scenario, usually leading to insufficient diversity; second, crowd scenarios with highly occluded pedestrians are still underrepresented, resulting in low density. To narrow this gap and facilitate future pedestrian detection research, we introduce a large and diverse dataset named WiderPerson for dense pedestrian detection in the wild. This dataset involves five types of annotations in a wide range of scenarios, no longer limited to the traffic scenario. There are a total of 13 382 images with 399 786 annotations, that is, 29.87 annotations per image, which means this dataset contains dense pedestrians with various kinds of occlusions. Hence, pedestrians in the proposed dataset are extremely challenging due to large variations in the scenario and occlusion, which is suitable to evaluate pedestrian detectors in the wild. We introduce an improved Faster R-CNN and the vanilla RetinaNet to serve as baselines for the new pedestrian detection benchmark. Several experiments are conducted on previous datasets including Caltech-USA and CityPersons to analyze the generalization capabilities of the proposed dataset, and we achieve state-of-the-art performances on these previous datasets without bells and whistles. Finally, we analyze common failure cases and find the classification ability of pedestrian detector needs to be improved to reduce false alarm and misdetection rates. The proposed dataset is available at http://www.cbsr.ia.ac.cn/users/sfzhang/WiderPerson.