双目立体匹配算法研究
Research on Binocular Stereo Matching Algorithm
Abstract
双目立体视觉在定位、导航、无人驾驶、三维重建等领域得到了广泛应用。双目立体匹配技术作为双目立体视觉的关键环节,一直都是研究热点,它利用双目相机在不同视点对同一场景进行取景后进行两幅输入图像的对应点匹配,从而获取对应点视差,进而可以计算该点在实际场景中的三维信息。 为了提高双目立体匹配的精度与效率,单序列Census变换与多尺度代价聚合技术被提出。但单序列Census变换存在对中心点依赖过大,在弱纹理区域容易出现误匹配等缺点;而多尺度代价聚合的跨尺度运算使得立体匹配运算效率低。针对上述缺点,本文做了如下研究工作: (1)提出了双序列Census变换算法。算法利用5*5小窗口灰度中值替代中... Binocular vision has been widely used in many fields, such as navigation, unmanned and 3D reconstruction. As a key part of binocular stereoscopic vision, binocular stereo matching technology has always been a research hotspot, in this area, binocular camera is used to shoot in different viewpoints on the same scene, then the two input images will be matched by finding the corresponding points, con...