An online algorithm for matching noisy space curves with statistical error analysis

摘要: In this thesis, we presents a new algorithm that finds the longest partial match between two space curves. The iteratively extends an initial matching portion of curves within some tolerance over quality. Each iteration adjusts transformation (rotation, scale, and translation) to handle noisy data more robustly enlarge matched portion. To control accuracy, statistical threshold is introduced stop iterative extension. Experiment shows has comparable accuracy well known ICP [3] but its efficiency improved by order magnitude. been demonstrated synthetic range data. it noise distributions performs effectively complex shapes.