In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly conne...In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly connected and structured, which makes motion connectivity an advanced feature for segmentation. Accordingly, after sharp noise elimination, the cumulated difference image, which exhibits the coherent motion of the moving object, is adaptively thresholded. Then the maximal connected region is labeled, post-processed and output as the final segmenting mask. Hence the initial video object is effectively extracted. Comparative experimental results show that the proposed algorithm extracts the initial video object automatically, promptly and properly, thereby achieving satisfactory subjective and objective performance.展开更多
Performance of traditional adaptive line enhancer （ALE） in suppressing Gaussian noise is low and can get worse at low input signal-to-noise ratio（SNR）. For greatly overcoming these disadvantages, feature of fourth...Performance of traditional adaptive line enhancer （ALE） in suppressing Gaussian noise is low and can get worse at low input signal-to-noise ratio（SNR）. For greatly overcoming these disadvantages, feature of fourth-order cumulant （FOC） different slices for quasi-stationary random process is analyzed, fourth order cumulant（FOC） different slice-based adaptive dynamic line enhancer is presented, and output SNR of the proposed enhancer is derived and bigger than that of the ALE via theoretical analysis. Simulation tests with the underwater moving target-radiated data have shown that the proposed enhancer outperforms the ALE in suppressing Gaussian noise and enhancing dynamic line spectrum feature.展开更多
基金The National Natural Science Foundation of China(No60672094)
文摘In order to obtain the initial video objects from the video sequences, an improved initial video object extraction algorithm based on motion connectivity is proposed. Moving objects in video sequences are highly connected and structured, which makes motion connectivity an advanced feature for segmentation. Accordingly, after sharp noise elimination, the cumulated difference image, which exhibits the coherent motion of the moving object, is adaptively thresholded. Then the maximal connected region is labeled, post-processed and output as the final segmenting mask. Hence the initial video object is effectively extracted. Comparative experimental results show that the proposed algorithm extracts the initial video object automatically, promptly and properly, thereby achieving satisfactory subjective and objective performance.
文摘Performance of traditional adaptive line enhancer （ALE） in suppressing Gaussian noise is low and can get worse at low input signal-to-noise ratio（SNR）. For greatly overcoming these disadvantages, feature of fourth-order cumulant （FOC） different slices for quasi-stationary random process is analyzed, fourth order cumulant（FOC） different slice-based adaptive dynamic line enhancer is presented, and output SNR of the proposed enhancer is derived and bigger than that of the ALE via theoretical analysis. Simulation tests with the underwater moving target-radiated data have shown that the proposed enhancer outperforms the ALE in suppressing Gaussian noise and enhancing dynamic line spectrum feature.
