A study on object contour tracking with large motion using optical flow and active contour model

Abstract

In this study, an object contour tracking method is proposed for an object with large motion and irregular shapes in video sequences. To track object contour accurately, an active contour model was used, and the initial snake point of the next frame is set by calculating an optical flow of feature points with changing curvature in the object contour tracked from the previous frame. Here, any misled optical flow due to irregular changes in shapes or fast motion was filtered by producing an edge map different from the previous frame, and as a solution to the energy shortage of objects with complex contour, snake points were added according to partial curvature for better performance. Findings from experiments with real video sequences showed that the contour of an object with large motion and irregular shapes was extracted precisely. © 2013 Springer Science+Business Media Dordrecht.