GRID Dataset

QMUL underGround Re-IDentification (GRID) 数据集包含 250 个行人图像对。每对包含从不同相机视图看到的同一个人的两张图像。所有图像均来自安装在繁忙地铁站的 8 个不相交的摄像机视图。旁边的图显示了站的每个摄像机视图的快照和数据集中的示例图像。由于姿势、颜色、光照变化的变化，数据集具有挑战性；以及空间分辨率低导致的图像质量差。

The QMUL underGround Re-IDentification (GRID) dataset contains 250 pedestrian image pairs. Each pair consists of two images of the same person captured from different camera views. All images are acquired from 8 disjoint camera views installed in a busy underground station. The accompanying figure displays snapshots of each camera view at the station and sample images from the dataset. This dataset poses significant challenges due to variations in pose, clothing color, and illumination, as well as poor image quality caused by low spatial resolution.

搜集汇总

背景与挑战

背景概述

GRID Dataset是一个行人重识别数据集，包含250对来自地铁站8个不同摄像机视角的行人图像，具有低分辨率和多种变化因素（如姿势、光照）的挑战性特点。