Real-time Defect Detection in Conveyor Belts using Point Clouds Generated by a ToF Camera

• Xaime Pardal Cardama ^[1] ; Carlos V. Regueiro ^[1] ; Miguel R. Luaces ^[1]
  1. [1] Universidade da Coruña

     Universidade da Coruña

     A Coruña, España

     
• Localización: Proceedings XoveTIC 2025: Impulsando el talento científico / coord. por Manuel Lagos Rodríguez, Hilda Romero-Velo, Álvaro Leitao , Javier Pereira-Loureiro , Manuel Penedo , 2026, ISBN 978-84-9749-925-5, págs. 249-256
• Idioma: inglés
• Enlaces
  • Texto completo
• Resumen

  • A three-dimensional analysis system was developed using Time-of-Flight (ToF) in-frared cameras to detect conveyor belt teeth and estimate their speed. From the captured pointclouds, structural patterns are identified through geometric fitting and spatial segmentation. Asa novel contribution, the system detects belt teeth, locating absences and deformations. Detec-tion is performed by comparing the expected distribution with the observed one. The speed ofthe conveyor belt is estimated by calculating the relative displacement between consecutive pointclouds. The system was successfully tested, providing accurate and reliable analysis in dynamicindustrial environments.