A novel robust and high reliability spatial correlation optical flow algorithm based on median motion estimation and bidirectional symmetry flow technique

Changing in light condition and representative of noise in sequences cause ineffectively in most of motion estimation techniques. This paper proposes a novel robust spatial correlation optical flow algorithm based on the robust motion estimation and effective confidence technique using bidirectional symmetry of forward and backward flow. Experiment results are comprehensively tested on several standard sequences such as AKIYO, COASTGUARD, CONTAINER, and FOREMAN that have different foreground and background movement characteristic. The experiment is tested under the Additive White Gaussian Noise (AWGN) at several noise power levels (such as AWGN at 25 dB (low noise), AWGN at 20 dB, and AWGN at 15 dB (high noise) respectively) in order to demonstrate effectiveness of the proposed algorithm. Peak Signal to Noise Ratio (PSNR) is used as the performance indicator in our experiment.