No abstract

A high-precision calibration method was proposed. This method is divided four steps: extracting calibration data, building model, calculating inside and outside parameters, and correcting camera distortion. Experimental results show that calibration is very accurate and the total error is not more than 0.06 pixels.

A stereo matching algorithm was proposed based on pyramid algorithm and dynamic programming. High and low resolution images was computed by pyramid algorithm, and then candidate control points were stroke on low-resolution image, and final control points were stroke on the high-resolution images. Finally, final control points were used in directing stereo matching based on dynamic programming. Since the striking of candidate control points on low-resolution image, the time is greatly reduced. Experiments show that the proposed method has a high matching precision.

The stereo matching algorithm based on aligning genomic sequence is proposed in the paper. This method is divided in three steps: do genomic sequence on the same name epipolar of stereo matching, get branch matrix by establishing genomic sequences using the same name epipolar after being genomic sequences, control points technology and dynamic backdate method to get disparity. The experimental results show that stereo matching method based on genomic sequences has fast speed and good matching quality.

To combat the problems of disparity image inpainting, an improved exemplar-based image inpainting method is proposed. The original stereo image we select which corresponds to disparity image is decomposed by TV-based decomposition and the structural information is obtained. The patch priority in the position corresponding to the disparity image is calculated by using the structural information, which reflects true characteristics of the original stereo image and disparity image. Experimental results show that inpainting performance is better with the guidance of this patch priority for disparity image.