1-3 次元フローとフレーム間差分を併用した物体追跡(第1部門 メディア処理)

抄録

Although optical flow is useful for object tracking, estimation of the flow by the gradient method is ill-posed problem. In order to avoid ill-posedness, we have proposed a tracking method via 1D flow, which is calculated on the straight lines (calculation axes). We update these axes based on the positive 1D flow. Since, origin of the axes is located on the restricted position, we can't reduce a tracking error. We propose tracking method by using both 1D flow and frame difference.