Currently, most human action recognition systems are trained with feature sets that have no missing data. Unfortunately, the use of human pose estimation models to provide more des...
Patrick Peursum, Hung Hai Bui, Svetha Venkatesh, G...
Abstract. Image-based full body 3D reconstruction for tele-immersive applications generates large amount of data points, which have to be sent through the network in real-time. In ...
Thinning is a frequently used method for extracting skeletons in discrete spaces. This paper presents an efficient parallel Žthinning algorithm that directly extracts medial line...
This paper presents a method for identifying image loci that can be used as a basis for object segmentation and image registration. The focus is on 1D and 2D shape loci in 3D image...