We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
This paper presents an approach to recover body motions from multiple views using a 3D skeletal model. It takes, as input, foreground silhouette sequences from multiple viewpoints...
We present a method for tracking the 3D position of a nger, using a single camera placed several meters away from the user. After skin detection, we use motion to identify the ges...
A multiple-camera system for 3D pose reconstruction is presented. First, body parts of the user are detected. Each camera has a single-instruction multiple-data (SIMD) processor u...
—Most of the development of pose recognition focused on a single person. However, many applications of computer vision essentially require the estimation of multiple people. Henc...