摘要
为了提高彩色图像的立体匹配精度,结合格式塔心理学和像素的色彩信息,在RGB彩色空间下提出了一种改进的基于误差绝对值累积(SAD)的立体匹配算法。算法使用色彩相似度和像素距离信息获取邻域窗内的像素权值,并使用线性查找表技术加速权值的计算速度;根据像素点RGB色彩分量的分布特点,生成对应的分量权值,进一步增强了匹配代价函数的稳定性。实验结果表明,改进后的匹配算法较灰度SAD及标准彩色SAD算法在精度上有明显的提高。
In order to improve the accuracy of color image stereo matching, an improved sum of absolute differences （SAD） algorithm is proposed in RGB color space employing Gestalt psychology and color in- formation of pixels. Similarity of color and proximity of distance between pixels in the neighborhood win- dow are adopted to produce the weight, and linear look-up table method is also used to accelerate the computing speed. The distribution characteristics of RGB components are also considered to produce the component weights for every pixel, which can further improve the stability of the matching cost function. The results of the experiment show that the proposed algorithm improves the precision compared with gray SAD and standard color SAD significantly.
出处
《光电子．激光》
EI
CAS
CSCD
北大核心
2015年第10期2031-2036,共6页
Journal of Optoelectronics·Laser
