TUM Kitchen

TUM Kitchen是涵盖厨房日常活动的动作识别数据集。数据集包含由4个具有重叠视点的摄像机捕获的20个视频序列。相机以25 fps从4个视点捕获场景，每个RGB帧的分辨率为384 × 288像素。数据分别标记为左手，右手和人的躯干。

TUM Kitchen is an action recognition dataset covering daily kitchen activities. It contains 20 video sequences captured by four cameras with overlapping viewpoints. The cameras capture the scene at 25 fps, with each RGB frame having a resolution of 384 × 288 pixels. The dataset provides annotations for the left hand, right hand, and human torso respectively.

搜集汇总

背景与挑战

背景概述

TUM Kitchen是一个厨房日常活动动作识别数据集，包含4个摄像机捕获的20个视频序列，数据标注包括手部和躯干动作，由慕尼黑工业大学于2009年发布。