DIH: Depth Images with Humans

The DIH dataset has been created for human body landmark detection and human pose estimation from depth images. It dataset contains a set of synthetic images and a set of images acquired with a Kinect 2 depth sensor. Both datasets include annotations of 17 body landmarks: head, neck, shoulders, elbows, wrists, hips, knees, ankles and eyes.

搜集汇总

背景与挑战

背景概述

DIH: Depth Images with Humans 是一个专门用于人体关键点检测和姿态估计的深度图像数据集。它包含合成图像和通过Kinect 2传感器采集的真实图像，所有图像均标注了17个身体关键点，如头部、关节和眼睛等，适用于计算机视觉中的人体分析任务。