CAJ | 학술논문

针对传统匹配算法得到的初始视差图不精确的问题，提出一种基于均值偏移和区域映射的视差图优化算法。该算法首先采用均值偏移算法对视差图进行区域分割，提取由误匹配所导致的黑洞区域；将左原始图像的分割区域映射到视差图中，从而对视差图进行每个区域内的平面拟合，去除误匹配点和像素跳跃点；结合标定数据得到三维场景的深度信息和三维坐标，最终实现三维重建。通过对图割算法及四种经典匹配算法进行实验，结果显示本算法能显著提高视差图的精度，降低低纹理区域和遮挡区域的误匹配率，且改善了重建效果。
침대전통필배산법득도적초시시차도불정학적문제，제출일충기우균치편이화구역영사적시차도우화산법。해산법수선채용균치편이산법대시차도진행구역분할，제취유오필배소도치적흑동구역；장좌원시도상적분할구역영사도시차도중，종이대시차도진행매개구역내적평면의합，거제오필배점화상소도약점；결합표정수거득도삼유장경적심도신식화삼유좌표，최종실현삼유중건。통과대도할산법급사충경전필배산법진행실험，결과현시본산법능현저제고시차도적정도，강저저문리구역화차당구역적오필배솔，차개선료중건효과。
To solve the problem of low accuracy for initial disparity map calculated by traditional matching algorithms,this pa-per proposed a disparity map refinement algorithm based on image region segmentation and region mapping.First the method segmented the initial disparity map into regions by Mean-Shift algorithm,and then extracted the black holes caused by error matching.To remove these mismatching points and disparity jumping points,the algorithm mapped segmentation regions of the original image into the disparity map,and fitted planes with planar fitting algorithm.It calculated depth information and three-dimensional coordinates according to the calibration data.Finally it completed the reconstruction.This paper compared the re-fined disparity maps with the results calculated by the graph cut algorithm and other four traditional algorithms.Experimental results show that this method can greatly reduce the error matching rates,especially in textureless regions and occluded re-gions,and can improve the reconstruction quality.