This paper presents a method of synchronizing video sequences with non-rigid human motion in a surveillance video stitching scenario. Different from manual or half-manual video synchronization methods, our work exploits the spatiotemporal structure information embedded in the time-series data itself to realize synchronization automatically and consistently. After projecting into the same plane based on the homography constraint, we formulate the problem of aligning two time series data with unequal lengths as an improved dynamic time warping (DTW)-based optimization problem. Furthermore, we propose a simple but effective shape registration and similarity measure method based on ℛ transform to decrease shape ambiguities. The method has been evaluated qualitatively on several real sequences and demonstrated its effective performance.