An Image-Aided Sparse Point Cloud Registration Strategy for Managing Stockpiles in Dome Storage Facilities

Stockpile volume estimation plays a critical role in several industrial/commercial bulk material management applications. LiDAR systems are commonly used for this task. Thanks to Global Navigation Satellite System (GNSS) signal availability outdoor environments, Uncrewed Aerial Vehicles (UAV) equipped with frequently adopted the derivation of dense point clouds, which can be stockpile estimation. For indoor facilities, static scanners usually acquisition clouds from multiple locations. Acquired then registered common reference frame. Registration such established through deployment registration targets, is not practical scalable implementation. scans facilities bounded by planar walls/roofs, features automatically extracted/matched and process. However, monitoring stockpiles stored dome remains challenging This study introduces an image-aided fine strategy acquired sparse where roof stringers extracted, matched, modeled as quadratic surfaces curves. These Least Squares Adjustment (LSA) procedure derive well-aligned clouds. Planar features, if available, also Registered accurate stockpiles. The proposed approach evaluated using datasets recently developed camera-assisted mapping platform—Stockpile Monitoring Reporting Technology (SMART). Experimental results three indicate capability producing inside feature fitting error 0.03–0.08 m range.