Simple and Effective Load Volume Estimation in Moving Trucks using LiDARs

• Lucas L. Amorim Federal University of Espírito Santo
• Filipe Mutz Federal Institute of Espirito Santo
• Claudine Badue Federal University of Espírito Santo
• Alberto de Souza Federal University of Espírito Santo
• Thiago Oliveira-Santos Federal University of Espírito Santo

DOI: https://doi.org/10.5753/sibgrapi.2019.9800

Resumo

Industries need to track the amount of materialsand goods transported through processing units in order tooptimize production. In large-scale industries, trucks and trainsare commonly used for transportation. The manual evaluationof the volume of material being transported by these vehiclescan be imprecise, inefficient, and even unsafe for employees.Therefore, this work presents an automated system for estimatingthe volume of load in moving trucks using a pair of multi-layerlight detection and ranging (LiDAR) sensors. The sensors aremounted in a structure so that trucks can pass through withoutstopping. The proposed system can be used with any type ofcompact load such as grains, and powders. A mesh of the load isbuilt and used for estimating the volume. A simple, efficient, andeffective heuristic is proposed for tracking the truck’s positions.The system was deployed and evaluated in a mining company inreal conditions of operation. Experimental results indicate thatthe system produces accurate estimates of the volume of orepowder transported by trucks. The reconstruction of the loadsand the estimative of their volumes are performed once the datais acquired and lasts less than 1.5 minutes on average.

Palavras-chave: point cloud registration, GICP, mesh reconstruction, volume measurement

Referências

B. A. B. Correia R. Davies F. D. Carvalho F. C. Rodrigues Computer vision system for the automatic measurement of volumes of wood vol. 1989 1993.

H. Marshall et al. "Automated log counting: proof of concept algorithm" Proceedings of SilviLaser 2011 11th International Conference on LiDAR Applications for Assessing Forest Ecosystems University of Tasmania Australia 16–20 October 20Conference Secretariat pp. 1-13 2011.

M. Acuna A. Sosa "Automated volumetric measurements of truckloads through multi-view photogrammetry and 3d reconstruction software" Croatian Journal of Forest Engineering: Journal for Theory and Application of Forestry Engineering vol. 40 no. 1 pp. 151-2019.

H. Anwar S. M. Abbas A. Muhammad K. Berns "Volumetric estimation of contained soil using 3d sensors" Intl. Commercial Vehicle Technology Symposium pp. 11-13 2014.

E. Duff "Automated volume estimation of haul-truck loads" Proceedings of the Australian Conference on Robotics and Automation pp. 179-2000.

M. Nylinder T. Kubénka M. Hultnäs "Roundwood measurement of truck loads by laser scanning" Field study at Arauco pulp mill Nueva Aldea pp. 1-9 2008.

J. L. Bentley "Multidimensional binary search trees used for associative searching" Commun. ACM vol. 18 no. 9 pp. 509-Sep. 1975.

A. Segal D. Haehnel S. Thrun "Generalized-icp" Robotics: science and systems vol. 2 no. 4 pp. 2009.

T. Möller B. Trumbore "Fast minimum storage ray/triangle intersection" ACM SIGGRAPH 2005 Courses. ACM pp. 7 2005.

M. Kazhdan M. Bolitho H. Hoppe "Poisson surface reconstruction" Proceedings of the fourth Eurographics symposium on Geometry processing vol. 7 2006.

M. Garland P. S. Heckbert "Surface simplification using quadric error metrics" Proceedings of the 24th annual conference on Computer graphics and interactive techniques pp. 209-1997.

B. Mirtich "Fast and accurate computation of polyhedral mass properties" Journal of graphics tools vol. 1 no. 2 pp. 31-50 1996.