KARD - Kinect Activity Recognition Dataset

To cite this dataset, please refer to the following paper: Human Activity Recognition Process Using 3-D Posture Data. S. Gaglio, G. Lo Re, M. Morana. In IEEE Transactions on Human-Machine Systems. 2014 doi: 10.1109/THMS.2014.2377111 ********************** ********************** ********************** KARD contains 18 Activities. Each activity is performed 3 times by 10 different subjects. 1 Horizontal arm wave 2 High arm wave 3 Two hand wave 4 Catch Cap 5 High throw 6 Draw X 7 Draw Tick 8 Toss Paper 9 Forward Kick 10 Side Kick 11 Take Umbrella 12 Bend 13 Hand Clap 14 Walk 15 Phone Call 16 Drink 17 Sit down 18 Stand up In total, you have 4 (files) x 18 (activities) x 3 (repetitions) x 10 (subjects), that is 2160 files. Each filename is in the form aA_sS_eN_string where A is a two-digit actionID and S is a two-digit subjectID for the N-th repetition. The string parameter depends on the the type of provided information: - depthmaps.txt: depth map, - .mp4: 640x480 RGB video, - realworld.txt: joints position in real world coordinates, - screen.txt: joints position in screen coordinates and depth value. For example, the file a04_s03_e02_realworld.txt contains the skeleton joints position in real world coordinates for the second repetition of the action #4 performed by the subject #3. The files containing the skeleton coordinates (realworld.txt and screen.txt) list the 15 joints in consecutive blocks, one for each frame. line 1 Head line 2 Neck line 3 Right Shoulder line 4 Right Elbow line 5 Right Hand line 6 Left Shoulder line 7 Left Elbow line 8 Left Hand line 9 Torso line 10 Right Hip line 11 Right Knee line 12 Right Foot line 13 Left Hip line 14 Left Knee line 15 Left Foot Each file contains 15xF lines, where F is the number of frames for that sequence, and each line reports three numbers: real world coordinates (x, y, z) for realworld.txt, or screen coordinates and depth value (u, v, depth) for screen.txt. The dataset is made of 540 sequences for about a total of 1 hour of videos captured at a resolution of 640x480 pixels at 30fps. Uncompressed frame images are also available on request.

引用本数据集，请参阅以下论文：《基于三维姿态数据的人类活动识别流程》（Human Activity Recognition Process Using 3-D Posture Data），作者S. Gaglio、G. Lo Re、M. Morana，发表于《IEEE人机系统汇刊》（IEEE Transactions on Human-Machine Systems），2014年，DOI: 10.1109/THMS.2014.2377111

KARD数据集包含18类人类活动，每类活动由10名不同受试者各完成3次。活动列表如下：
1. 水平挥臂
2. 高挥臂
3. 双手挥摆
4. 接帽
5. 高抛
6. 绘制X形
7. 绘制对勾形
8. 抛纸
9. 前踢
10. 侧踢
11. 取伞
12. 弯腰
13. 拍手
14. 行走
15. 接打电话
16. 饮水
17. 坐下
18. 起立

总计文件数为4（文件类型）×18（活动类别）×3（重复次数）×10（受试者），即共2160个文件。每个文件名格式为`aA_sS_eN_string`，其中A为两位数字的活动ID，S为两位数字的受试者ID，N为该活动重复次数的序号。string参数对应提供的信息类型：
- `depthmaps.txt`：深度图
- `.mp4`：分辨率为640×480的RGB视频
- `realworld.txt`：真实世界坐标系下的关节点位置
- `screen.txt`：屏幕坐标系下的关节点位置及深度值

例如，文件`a04_s03_e02_realworld.txt`包含受试者3完成的第4类活动第2次重复的骨架关节点真实世界坐标。

包含骨架坐标的文件（`realworld.txt`与`screen.txt`）按连续块列出15个关节点，每个帧对应一个块，具体关节顺序如下：
1. 头部
2. 颈部
3. 右肩
4. 右肘
5. 右手
6. 左肩
7. 左肘
8. 左手
9. 躯干
10. 右髋
11. 右膝
12. 右脚
13. 左髋
14. 左膝
15. 左脚

每个文件包含15×F行数据，其中F为该序列的总帧数，每一行对应三个数值：对于`realworld.txt`文件，为真实世界坐标系下的(x, y, z)坐标；对于`screen.txt`文件，为屏幕坐标系下的(u, v)坐标及深度值。

本数据集共包含540个序列，总时长约1小时，视频分辨率为640×480像素，帧率为30fps。未压缩的帧图像可按需获取。

搜集汇总

背景与挑战

背景概述

KARD是一个用于人类活动识别的数据集，基于Kinect传感器采集，包含18种日常活动，由10名受试者各重复3次，总计2160个文件。数据集提供多模态信息，包括RGB视频（640x480分辨率，30fps）、深度图和骨架关节坐标（15个关节），结构清晰，适用于活动识别算法研究。