3D SSD Tracking from Uncalibrated Video

Abstract. In registration-based tracking precise pose between a reference template and the current image is determined by warping image patches into the template coordinates and matching pixel-wise intensities. Efficient such algorithms are based on relating spatial and temporal derivatives using numerical optimization algorithms. We extend this approach from planar patches into a formulation where the 3D geometry of a scene is both estimated from uncalibrated video and used in the tracking of the same video sequence. Experimentally we compare convergence and accuracy of our uncalibrated 3D tracking to previous approaches. Notably, the 3D algorithm can successfully track over significantly larger pose changes than ones using only planar regions. It also detects occlusions and removes/inserts tracking regions as appropriate in response. 

• Type: Conference
• Year: 2004
• Where: SCVMA
• Authors: Dana Cobzas, Martin Jägersand
• Keywords: Computer Graphics, Numerical Optimization Algorithms, SCVMA 2004, Tracking Precise Pose, Uncalibrated 3D Tracking