基于自适应参数的匹配代价融合算法

摘要

Due to the limitations of single matching cost algorithm and the bad adaptive of fixed parameter combined method,a new combined cost based on adaptive parameters is presented.Firstly,sum of absolute difference and census algorithm were used to calculate the matching cost for each pixel separately.Secondly,the mean and standard deviation of cost for each pixel within the disparity range were calculated,and then the weight is obtained.Finally,the twoalgorithms together with the corresponding weight were combined,and then the new cost function is obtained.Experimental results show that the proposed method is better than single algorithm of matching error rate (reduced about 12％).And the cost function combines advantages of different algorithms in weak texture,repetition texture and changing illumination situations.%针对单一匹配代价算法局限性强、固定参数融合方式适应性差等问题,提出一种基于自适应参数的多种匹配代价函数融合算法.采用绝对差之和与Census算法,分别计算像素点代价;通过统计像素点在视差范围内代价的平均值和标准差,得到对应的权值;对2种算法进行加权融合,得到新的代价函数.实验结果表明,该算法较单一匹配算法误匹配率降低约12％;在弱纹理、重复纹理和光照变化的情况下,综合了不同算法的优点.