对于双目视觉立体匹配算法,先验的视差范围估计是影响算法匹配效果和运行时间的重要因素.在双目视觉系统的实际应用中,匹配视图之间的视差范围通常随场景的变化而不断改变,因此需要对视图间的视差范围进行有效的自动估计.针对此问题,开发了一种双模相机,可分时采集场景的灰度图像和深度图像,该深度图像与灰度图像有相同的空间分辨力.在双目视图匹配过程中,通过引入深度图的信息,可约束每一个待匹配像素的视差范围.对于实验室内采集的普通视图对,本文方法相较以视图间视差最大、最小值为约束的方法,匹配速度提高3倍以上,匹配误差减少2%,有效提高了匹配的可靠性和普适性.

A crucial parameter for the successes of stereo matching algorithms is the disparity search range estimation.It is necessary to estimate the disparity search range between stereo pairs automatically in real time systems.A dual-mode camera which can be used to take stereo images or depth maps is developed in our work.Under the constraint of the depth map with the same spatial resolution as the stereo pairs,expected disparity of each pixel is limited within a narrow search range.For images captured in our lab,the process of stereo matching is sped up more than 3 times and the error percentage is reduced by 2% compared with the method that estimates the minimal and maximal disparity between stereo pairs.