Three-dimensional Scan Registration using Curvelet Features in Planetary Environments

Topographic mapping in planetary environments relies on accurate three-dimensional 3D scan registration methods. However, most global registration algorithms relying on features such as fast point feature histograms and Harris-3D show poor alignment accuracy in these settings due to the poor structure of the Mars-like terrain, and the variable-resolution, occluded, sparse range data that are difficult to register without some a priori knowledge of the environment. In this paper, we propose an alternative approach to 3D scan registration using the curvelet transform that performs multiresolution geometric analysis to obtain a set of coefficients indexed by scale coarsest to finest, angle, and spatial position. Features are detected in the curvelet domain to take advantage of the directional selectivity of the transform. A descriptor is computed for each feature by calculating the 3D spatial histogram of the image gradients, and nearest-neighbor-based matching is used to calculate the feature correspondences. Correspondence rejection using random sample consensus identifies inliers, and a locally optimal singular value decomposition-based estimation of the rigid-body transformation aligns the laser scans given the reprojected correspondences in the metric space. Experimental results on a publicly available dataset of a planetary analogue indoor facility, as well as simulated and real-world scans from Neptec Design Group's IVIGMS 3D laser rangefinder at the outdoor CSA Mars yard, demonstrate improved performance over existing methods in the challenging sparse Mars-like terrain.