Learning and Tracking the 3D Body Shape of Freely Moving Infants from RGB-D sequences

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 42; no. 10; pp. 2540 - 2551
• Main Authors: Hesse, Nikolas, Pujades, Sergi, Black, Michael J., Arens, Michael, Hofmann, Ulrich G., Schroeder, A. Sebastian
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.10.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE); Institute of Electrical and Electronics Engineers
• Subjects: Animals; Avatars; Biological system modeling; Body models; Computer Science; Computer Vision and Pattern Recognition; Data models; data-driven; Face; Human body; Infants; Learning; motion analysis; RGB-D; Shape; Statistical models; Three dimensional bodies; Three dimensional models; Three-dimensional displays; RGB-D; Body models; infants; data-driven; motion analysis

Statistical models of the human body surface are generally learned from thousands of high-quality 3D scans in predefined poses to cover the wide variety of human body shapes and articulations. Acquisition of such data requires expensive equipment, calibration procedures, and is limited to cooperativ...