Robust Markerless Registration of Point Clouds for Terrestrial Laser Scanning-Based Measurement of Bulk Grains Stockpiled in Storehouses

Abstract. Highlights Fully automated registration free from artificial markers for multi-scan point clouds aimed for TLS-based measurement of bulk grains in large storehouses. The geometric structure of the large grain storehouse is explored to derive geometrical features as the structurally semantic information for scene understanding. The geometrical features are modeled as a small ordered set and correspondences are established by performing trials for all possible matching pairs of two sets extracted from two different scans. Significant improvements have been achieved in registration accuracy, computational efficiency and robustness against scenes with symmetric structures as well as the immunity to noises and varying point density. Abstract. Point clouds collected by terrestrial laser scanning (TLS) in the application of bulk grain measurement and quantification contain a vast amount of data, relatively low-textured surfaces and highly symmetric structures. All of these challenges make it a difficult task to automatically register multiple scans from different viewpoints needed to fully cover a large-scale scene. To address the challenges, this paper presents a robust automatic marker-free registration method dedicated for multi-scan TLS point cloud data captured in large grain storehouses. The framework of the dedicated method follows the common procedure to split the entire registration into coarse alignment and fine registration, and uses the iterative closest point (ICP) algorithm for the latter. The main contribution of the proposed dedicated method is an efficient way to find a global coarse alignment that is robust across individual scans in a TLS-based bulk grain measurement project. To tackle the correspondence problem, which is at the core of a registration task, the geometric information inherent in grain storehouses is explored in the stage of global coarse alignment. The derived semantic feature points are modeled as a small ordered set and reliable correspondences are established by performing trials for all possible matching pairs of two sets extracted from two different scans. Experimental results show the dedicated method outperforms the existing generic markless registration approaches in terms of accuracy, robustness and computational efficiency. With robustness, efficiency and accuracy, the proposed markless point cloud registration method dedicated for bulk grain measurement can cover a gap between the TLS technology and various granary field applications. Especially, its applicability to the dominant storage structure in Chinese huge grain reserve system implies remarkable efficiency improvements and will facilitate the application of TLS-based measurement in the national grain inventory of China.