Moving object tracking via one-dimensional optical flow using queue

Although optical flow is useful for tracking of a moving object, estimation by the gradient method is ill-posed problem. In order to avoid ill-posedness, we have proposed a tracking method via one dimensional optical flow (1D flow), which is calculated on the straight line (calculation axis). The calculation axes are spanned several direction based on the estimated motion. This method votes with the number of positive 1D flow and updates the calculation axes depending on the voting result. We update these axes every five frames to achieve stable estimation of motion. Hence, it is impossible to track a object which moves fast because this object moves to the outside of the region of interest. If the calculation axes are updated every frame to track a object which moves fast, then this method tends to estimate the wrong direction due to vibration of the camera or partial occlusion. We propose a tracking method via 1D flow using queue. We prepare queues of which the length is five for each direction. The number of positive flow is enqueued. Direction which has maximum value is regarded as the moving direction. We can achieve stable tracking even if a object moves fast, because the calculation axes are updated every frame and estimation of the moving direction is based on the information of the past five frames. In experiment for real image sequences, the proposed method can track a object which moves fast.