Bi-box Regression for Pedestrian Detection and Occlusion Estimation
Bi-box Regression for Pedestrian Detection and Occlusion Estimation
复制标题
DOI：
10.1007/978-3-030-01246-5_9
复制
发表时间：
2018-09
期刊：
影响因子：
--
通讯作者：
Chunluan Zhou;Junsong Yuan
中科院分区：
文献类型：
--
作者：
Chunluan Zhou;Junsong Yuan
遮挡对实际应用中的行人检测提出了巨大的挑战。在本文中，我们提出了一种同时进行行人检测和遮挡估计的新方法，通过回归两个边界框来分别定位行人的全身和可见部分。为此，我们学习了一种由两个分支组成的深度卷积神经网络（CNN），一个用于全身估计，另一个用于可见部分估计。这两个分支在训练过程中受到不同的处理，以便学习它们产生互补的输出，这些输出可以进一步融合以提高检测性能。全身估计分支被训练为回归正行人提案的全身区域，而可见部分估计分支被训练为回归正和负行人提案的可见部分区域。负面行人提案的可见部分区域被迫收缩到其中心。此外，我们引入了选择正训练示例的新标准，这在很大程度上有助于严重遮挡的行人检测。我们在 Caltech 和 CityPersons 数据集上验证了所提出的双盒回归方法的有效性。实验结果表明，我们的方法在检测非遮挡和遮挡行人（尤其是严重遮挡的行人）方面取得了良好的性能。
Occlusions present a great challenge for pedestrian detection in practical applications. In this paper, we propose a novel approach to simultaneous pedestrian detection and occlusion estimation by regressing two bounding boxes to localize the full body as well as the visible part of a pedestrian respectively. For this purpose, we learn a deep convolutional neural network (CNN) consisting of two branches, one for full body estimation and the other for visible part estimation. The two branches are treated differently during training such that they are learned to produce complementary outputs which can be further fused to improve detection performance. The full body estimation branch is trained to regress full body regions for positive pedestrian proposals, while the visible part estimation branch is trained to regress visible part regions for both positive and negative pedestrian proposals. The visible part region of a negative pedestrian proposal is forced to shrink to its center. In addition, we introduce a new criterion for selecting positive training examples, which contributes largely to heavily occluded pedestrian detection. We validate the effectiveness of the proposed bi-box regression approach on the Caltech and CityPersons datasets. Experimental results show that our approach achieves promising performance for detecting both non-occluded and occluded pedestrians, especially heavily occluded ones.