Authors:
Guilherme G. Netto
1
;
2
;
Bruno N. Coelho
1
;
2
;
Saul E. Delabrida
3
;
Amilton Sinatora
2
;
Héctor Azpúrua
2
;
Gustavo Pessin
2
;
Ricardo A. R. Oliveira
3
and
Andrea G. C. Bianchi
3
Affiliations:
1
Department of Engineering of Control and Automation, School of Mines, Federal University of Ouro Preto (UFOP), 122 Diogo de Vasconcelos, Ouro Preto, MG, 35400-000, Brazil
;
2
Vale Institute of Technology (ITV), 31 Juscelino Kubitschek, Ouro Preto, MG, 35400-000, Brazil
;
3
Computing Department, Federal University of Ouro Preto (UFOP), 122 Diogo de Vasconcelos, Ouro Preto, MG, 35400-000, Brazil
Keyword(s):
Image and Signal Processing, Curvature Outlier, Defects Detection, Machine Vision Inspection, Maintenance.
Abstract:
Continuous belt monitoring is of utmost importance since wears on its surface can develop into tears and even rupture. It can causes the interruption of the conveyor, and consequently, loss of capital, or even worse, serious or fatal accidents. This paper proposes a laser-based machine vision method for detecting defects in conveyor belts to solve the monitoring problem. The approach transforms an image of a laser line into a one-dimensional signal, then analyzes it to detect defects, considering that variations in this signal are caused by defects/imperfections on the belt surface. Differently from previous works, the proposed method can identify a defect through a 2D reconstruction of it. The results reveal that the proposed method was capable to detect superficial imperfections in simulated conveyor belt experiments, achieving high values in metrics such as precision and recall.