Laser scanner measuring improved by image pixels using a Markov random field algorithm

Laser scanners can be employed for spatial measuring tasks, but measuring accuracy is restricted because of the time of flight working principle. Laser-scanner-based observations with measuring errors might lead to rough spatial reconstruction. In this paper, an image registration method applying a Markov random field (MRF) algorithm is proposed. First, point cloud images are projected to a particular plane in a specific way. Then, the characteristic points of the projected image and the color image are extracted by an improved Harris algorithm. Next, the rotation and translation matrices can be calculated from the two image planes through the registration method. Finally, the MRF model is established describing the relation between the pixels and corresponding point cloud, which improves the resolution of the point cloud image. Furthermore, the color information of the point cloud is also matched. This method improves the efficiency and accuracy of registration. The final experimental result shows that using the MRF model increases measuring accuracy by 15%.