用视觉变压器与随机游走解决群体重识别中的成员与布局变化问题
Vision Transformer based Random Walk for Group Re-Identification
- 基于单目深度估计构建图结构，融合距离信息建模行人关系
- 引入随机游走模块，通过亲和度计算剔除非本组行人
- 有效应对成员更替与队列布局变化，适合跨摄像头群体匹配场景
群体重识别（Group Re-ID）旨在不同摄像头下匹配包含相同人员的群体，主要面临成员变化与布局变化的挑战。现有方法多采用k近邻算法更新节点特征以应对成员变化，但难以处理布局变化问题。为此，我们提出一种基于视觉变压器的随机游走框架。具体地，设计一种基于单目深度估计的视觉变压器，通过行人特征的平均深度值构建图，充分考虑摄像头距离对群体成员关系的影响；同时提出随机游走模块，通过计算目标与候选图像间的亲和度得分，重构图结构并移除不属于当前群体的行人。实验结果表明，该框架在多个数据集上优于多数现有方法。
原文摘要 · Abstract (English)
Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。