A Radiometric Varying Robust Stereo Matching Algorithm
CAO Xiaoqian1,2, MA Caiwen1
1. Xi'an Institute of Optics and Precision Mechanic, Chinese Academy of Sciences, Xi'an 710119, China;
2. University of Chinese Academy of Sciences, Beijing 100049, China
In order to improve the matching rate of radiometric varying stereo images, a novel stereo matching algorithm based on the improved epipolar distance transformation in log-chromaticity space is proposed. In log-chromaticity space, the intensity proportion of stereo image pairs is computed firstly according to raw disparity map; secondly, epipolar distance transformation is performed on left and right images respectively using proportional intensity deviation parameters; at last, the final disparity map is acquired by the belief propagation method. Theoretically, the matching rate of the proposed algorithm is independent of radiometric varying situations including differences in light source's position, spectrum, intensity and the parameters setting of cameras. Experimental results indicate that the matching rate of the proposed algorithm is improved at most 60% comparing with the original epipolar distance transformation algorithm and at most 78% comparing with the state of art algorithms such as ANCC (adaptive normalized cross correlation) when applied to textureless image pairs.
[1] 叶平,李自亮,王轩,等.基于立体视觉定位的球形机器人系统研制[J].机器人,2012,34(6):697-703.Ye P, Li Z L, Wang X, et al. Design of a ball-shaped robot with stereovision-based localization[J]. Robot, 2012, 34(6): 697-703.[2] 宋鑫坤,陈万米,徐昱琳,等.基于视差平面分割的移动机器人障碍物地图构建方法[J].机器人,2010,32(2):171-178.Song X K, Chen W M, Xu Y L, et al. Disparity image plane segmentation based obstacle map construction for mobile robot[J]. Robot, 2010, 32(2): 171-178.[3] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms[J]. International Journal of Computer Vision, 2002, 47(1/2/3): 7-42.[4] Yang Q Q, Li D X, Wang L H, et al. Full-image guided filtering for fast stereo matching[J]. IEEE Signal Processing Letters, 2013, 20(3): 237-240. [5] 马祥音,查红彬.采用自适应平滑约束的立体匹配方法[J].计算机辅助设计与图形学学报,2010,22(1):108-113.Ma X Y, Zha H B. Stereo matching by using adaptive smoothness term[J]. Journal of Computer-Aided Design & Computer Graphics, 2010, 22(1): 108-113.[6] Xiong W, Chung H S, Jia J Y. Fractional stereo matching using expectation-maximization[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3): 428-443. [7] 钮圣虓,王盛,杨晶晶,等.完全基于边缘信息的快速图像分割算法[J].计算机辅助设计与图形学学报,2012,24(11):1410-1419.Niu S X, Wang S, Yang J J, et al. A fast image segmentation algorithm fully based on edge information[J]. Journal of Computer-Aided Design & Computer Graphics, 2012, 24(11): 1410-1419.[8] Zitnik C L, Kanade T A. Cooperative algorithm for stereo matching and occlusion detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(7): 675-684. [9] 霍智勇,朱秀昌,刘天亮.基于线性生长的区域立体匹配算法研究[J].仪器仪表学报,2011,32(4):819-824.Huo Z Y, Zhu X C, Liu T L. Region based stereo matching algorithm using line growing method[J]. Chinese Journal of Science Instrument, 2011, 32(4): 819-824.[10] 张锐,钟凡,彭群生,等.室外场景光照估计的基图像分解算法[J].计算机辅助设计与图像学学报,2013,25(4):442-449.Zhang R, Zhong F, Peng Q S, et al. Basis image decomposition for outdoor lighting estimation[J]. Journal of Computer-Aided Design & Computer Graphics, 2013, 25(4): 442-449.[11] Finlayson G, Xu R. Illuminant and gamma comprehensive normalisation in log RGB space[J]. Pattern Recognition Letters, 2003, 24(11): 1679-1690. [12] Finlayson G D, Hordley S D, Hubel P M. Color by correlation: A simple, unifying framework for color constancy[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 23(11): 1209-1221.[13] Hirschmuller H, Scharstein D. Evaluation of stereo matching costs on images with radiometric differences[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(9): 1582-1599. [14] Heo Y S, Lee K M, Lee S U. Robust stereo matching using adaptive normalized cross-correlation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2011, 33(4): 807-822. [15] Heo Y S, Lee K M, Lee S U. Joint depth map and color consistency estimation for stereo images with different illuminations and cameras[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(5): 1094-1106. [16] 邹宇华,陈伟海,吴星明,等.一种室外非理想光照条件下的立体匹配算法[J].机器人,2012,34(3):344-353.Zou Y H, Chen W H, Wu X M, et al. A stereo matching algorithm under outdoor unideal illumination condition[J]. Robot, 2012, 34(3): 344-353.[17] Yang Q X, Ahuja N. Stereo matching using epipolar distance transform[J]. IEEE Transactions on Image Processing, 2012, 21(10): 4410-4419.
