双目立体视觉匹配的预处理技术

Matching Preprocessing Technology of Binocular Stereo Vision

针对双目立体视觉图对区域匹配应用中存在的问题,提出一种三阶段的匹配预处理方法.该方法将小波阈值去噪算法和直方图均衡化技术相结合,有效地去除了图像随机噪声和高斯噪声,实现了立体图对间亮度差异的平衡,并经过拉普拉斯锐化处理提高了图像对的对比度.实验结果表明,三阶段匹配预处理算法可有效提高立体图对间的匹配准确率.

To solve the problem existing in the application of binocular stereo vision image-pair,a three-stages matching preprocessing method was proposed.This method combines the wavelet de-nosing algorithm and histogram equalization method effectively.The random noise and Gauss noise of image are filtered and luminance difference between stereo image-pairs is balanced at the same time.Finally the contrast of image-pairs was improved by Laplace sharpen processing.The effectiveness of three-stages matching preprocessing algorithm was proved by experiment.The application of the algorithm could improve the matching accuracy of stereo image-pairs effectively.