论文标题
在野外搜索人搜索的良好局部匹配
Robust Partial Matching for Person Search in the Wild
论文作者
论文摘要
诸如遮挡，背景等的各种因素将导致未归属的界限，例如，仅覆盖人体的一部分。这个问题很常见，但被前面的搜索工作忽略了。为了减轻此问题，本文提出了一个针对人检测和重新识别（REID）的部分对齐网络（APNET）。 APNET完善了检测到的边界框以覆盖估计的整体身体区域，可以从中提取和对齐歧视零件。对齐零件的特征自然将REID作为部分特征匹配过程，其中选择有效的零件特征进行相似性计算，而丢弃了遮挡或嘈杂区域上的零件特征。这种设计通过边际计算开销来增强人搜索对现实世界挑战的鲁棒性。本文还为野外搜索（LSP）的人搜索提供了一个大规模的数据集，该数据集是迄今为止最大，最具挑战性的人搜索数据集。实验表明，APNET对LSP的性能有了显着改善。同时，它可以在现有人搜索基准等现有人（例如Cuhk-sysu and Prw）上取得竞争性能。
Various factors like occlusions, backgrounds, etc., would lead to misaligned detected bounding boxes , e.g., ones covering only portions of human body. This issue is common but overlooked by previous person search works. To alleviate this issue, this paper proposes an Align-to-Part Network (APNet) for person detection and re-Identification (reID). APNet refines detected bounding boxes to cover the estimated holistic body regions, from which discriminative part features can be extracted and aligned. Aligned part features naturally formulate reID as a partial feature matching procedure, where valid part features are selected for similarity computation, while part features on occluded or noisy regions are discarded. This design enhances the robustness of person search to real-world challenges with marginal computation overhead. This paper also contributes a Large-Scale dataset for Person Search in the wild (LSPS), which is by far the largest and the most challenging dataset for person search. Experiments show that APNet brings considerable performance improvement on LSPS. Meanwhile, it achieves competitive performance on existing person search benchmarks like CUHK-SYSU and PRW.
