CAJ | 학술논문

针对传统Census变换在视差不连续区域和噪声干扰情况下误匹配率较高的情况，提出了一种利用邻域相关信息的改进Census变换立体匹配算法。根据邻域像素的相关信息，将传统的Census变换中像素与邻域像素的差异应用2位信息表示，使变换后的图像在视差不连续区域的信息表示更为丰富，同时减少噪声对匹配质量的影响。通过并行化自适应匹配代价聚合、亚像素插值、左右一致性约束、遮挡区插值，最终得到了稠密视差图。经Middlebury立体图片测试表明，该算法结构简单，复杂度低，具有较高的鲁棒性，有效地提高了匹配精度。
침대전통Census변환재시차불련속구역화조성간우정황하오필배솔교고적정황，제출료일충이용린역상관신식적개진Census변환입체필배산법。근거린역상소적상관신식，장전통적Census변환중상소여린역상소적차이응용2위신식표시，사변환후적도상재시차불련속구역적신식표시경위봉부，동시감소조성대필배질량적영향。통과병행화자괄응필배대개취합、아상소삽치、좌우일치성약속、차당구삽치，최종득도료주밀시차도。경Middlebury입체도편측시표명，해산법결구간단，복잡도저，구유교고적로봉성，유효지제고료필배정도。
This paper proposes a modified Census transform which is based on information of the neighborhood for stereo matching to improve the classic Census transform by reducing mismatching of depth discontinuity as well as the noise dis-turbance. This new Census transform utilizes 2 bit to represent the differences between the pixel and its neighborhood. The result image of the transform provides more details on depth discontinuity and minimizes the impact of noise on the quality of matching. A dense disparity map is then generated through paralleled adaptive cost aggregation, stereo correspondence, sub-pixel interpolation and interpolation of the occluded regions. The evaluation of Middlebury stereo images shows that the proposed algorithm enhances the accuracy of matching with concise structure and low complexity with strong robustness.