15 People - 22 Landmarks Annotation Data of 3D Human Body. The dataset diversity includes multiple scenes, different ages, different costumes, different human body sitting postures. In terms of annotation, we annotate the 2D and 3D coordinates of the 22 landmarks of the human body, landmark attributes, the rectangular frame of the human body. The dataset can be used for tasks such as human body instance segmentation and human behavior recognition.
For more details, please refer to the link: https://www.nexdata.ai/datasets/computervision/1235?source=Github
15 people, 21,210 images
gender distribution: 6 males, 9 females; age distribution: 11-27 years old
home environment, office environment
multiple scenes, different ages, different costumes, different human body sitting postures
2D camera: logitech Brio 4K Pro, the resolution is 4K; 3D camera: realsense L515, the resolution is 1,920*1,080
the image data format is .jpg, the annotation file format is .json, the camera parameter file format is .json, the point cloud file format is .pcd
collecting the 2D and 3D images of various sitting positions of the human body (3D depth image and 4k 2D RGB image have been registered)
annotating the 2D and 3D coordinates of the 22 landmarks of the human body, landmark attributes, the rectangular frame of the human body
The mask edge location errors in x and y directions are less than 3 pixels, which is considered as a qualified annotation; Based on the landmarks, the accuracy rate shall be more than 95%, annotating accuracy = number of correct annotations / total number of annotations; The accuracy rate of label shall be more than 97%.
Commercial License