Discriminative Feature Transformation for Occluded Pedestrian Detection
Discriminative Feature Transformation for Occluded Pedestrian Detection
复制标题
DOI：
10.1109/iccv.2019.00965
复制
发表时间：
2019-10
期刊：
影响因子：
--
通讯作者：
Chunluan Zhou;Ming Yang;Junsong Yuan
中科院分区：
文献类型：
--
作者：
Chunluan Zhou;Ming Yang;Junsong Yuan
尽管深度卷积神经网络在非遮挡行人检测方面取得了令人鼓舞的性能，但检测部分遮挡的行人仍然是一个巨大的挑战。与非遮挡行人示例相比，由于遮挡部分的缺失，通常更难以将遮挡行人示例与特征空间中的背景区分开。在本文中，我们提出了一种判别性特征转换，它强制行人和非行人示例的特征可分离性，以处理行人检测的遮挡。具体来说，在特征空间中，它使行人示例接近易于分类的非遮挡行人示例的质心，并将非行人示例推向易于分类的非行人示例的质心。这种特征变换部分补偿了特征空间中被遮挡部分的缺失贡献，从而提高了被遮挡行人检测的性能。我们通过添加一个转换网络分支在 Fast R-CNN 框架中实现我们的方法。我们在两个广泛使用的行人检测数据集：Caltech 和 CityPersons 上验证了所提出的方法。实验结果表明，我们的方法在非遮挡和遮挡行人检测方面均取得了良好的性能。
Despite promising performance achieved by deep con- volutional neural networks for non-occluded pedestrian de- tection, it remains a great challenge to detect partially oc- cluded pedestrians. Compared with non-occluded pedes- trian examples, it is generally more difficult to distinguish occluded pedestrian examples from background in featue space due to the missing of occluded parts. In this paper, we propose a discriminative feature transformation which en- forces feature separability of pedestrian and non-pedestrian examples to handle occlusions for pedestrian detection. Specifically, in feature space it makes pedestrian exam- ples approach the centroid of easily classified non-occluded pedestrian examples and pushes non-pedestrian examples close to the centroid of easily classified non-pedestrian ex- amples. Such a feature transformation partially compen- sates the missing contribution of occluded parts in feature space, therefore improving the performance for occluded pedestrian detection. We implement our approach in the Fast R-CNN framework by adding one transformation net- work branch. We validate the proposed approach on two widely used pedestrian detection datasets: Caltech and CityPersons. Experimental results show that our approach achieves promising performance for both non-occluded and occluded pedestrian detection.