Publications / 2011 Proceedings of the 28th ISARC, Seoul, Korea

An Object Detection Algorithm for 3D Terrain Data Collected via Laser Scanning

Ji Woon Park, Hyun Seok Yoo, Young suk Kim
Pages 1449-1452 (2011 Proceedings of the 28th ISARC, Seoul, Korea, ISBN 978-89-954572-4-5, ISSN 2413-5844)
Abstract:

The intelligent excavating system (IES) aims for the full-scale automation of the excavation process that includes a series of tasks such as movement, excavation, and loading. The core elements of the IES include excavating robots, 3D modeling of surrounding terrains, and the technology for detecting objects accurately (i.e., for detecting the location of nearby loading trucks and humans as well as of obstacles positioned on the movement paths). These are absolutely necessary in ensuring the performance quality and safety of the equipment. This study was conducted to detect the terrains and objects near the location of the intelligent excavating robot via a 3D laser scanning system and to ensure the quality and safety of automated excavation. Moreover, an algorithm for estimating the location, height, width, and shape of objects in the 3D-realized terrain that surrounds the location of the excavator was proposed. The performance of the algorithm was verified via tests inside an actual earthwork field.

Keywords: Object, Detection, Earth Work, 3D, Excavation