Automatic Registration of Mobile LiDAR Data and Multi-lens Combined Images using Image Initial Poses

Even given the initial extrinsic of LiDAR and camera, high-precision automatic alignment between the Lidar scans and pictures acquired by mobile measurement systems (MMS) remains challenging due to clock asynchrony between sensors during data acquisition. In addition, the majority of images and mobile LiDAR Data registration methods are proposed for panoramic image sequences. A few research works have been focused on multi-lens combined images. We proposed an automated alignment approach for mobile lidar scans and multi-camera combined pictures using the initial poses of the images. First, we calibrate the extrinsic of the multi-lens combined camera and LiDAR sensor. Then, the odometry is obtained by the LiDAR SLAM algorithm, and the initial pose of each image is obtained. Then the sparse feature point cloud with the same scale as the lidar scan is obtained through the SfM algorithm with image initial poses. Finally, the iterative closest point (ICP) method is used to register the LiDAR scene points set with the image feature points set. The method is qualitatively and quantitatively evaluated on the indoor and outdoor data sets gathered from the self-developed mobile measurement platform. The alignment error of the approach suggested in this work is less than 1 pixel.