Estimation of fill factor for earth-moving machines based on 3D point clouds

Abstract Bucket fill factor is of paramount importance in measuring the productivity of earth-moving machines which is the amount of material loaded in the bucket within one scooping. In this paper, a stereo vision-based method is proposed and a novel perception system is developed. The system tested on a wheel loader is able to provide an accurate estimation of the fill factor. Disparity is computed for a pair of stereo images to reconstruct high fidelity 3-D point clouds. Preliminary processing is then used to extract regions of interest. In addition to applying existing state-of-the-art techniques including point cloud registration, stitching, and surface interpolation, our system also incorporates the structural information of wheel loaders, achieving excellent performance of 94.72 % accuracy even under the unavailability of visual information due to occlusion, and under different environment conditions. This research paves the way for the arrival of fully autonomous earth-moving machines in the future.