Testing Computer Vision techniques for bedload sediment transport evaluation in sewers

Marco Grasso (1) , Oliver Giudice (1) , Alberto Campisano (1) , Gashin Shahsavari (2) , Sebastiano Battiato (1) , Carlo Modica (1)

1 Unict - Università degli studi di Catania = University of Catania
2 PRODIG - Pôle de recherche pour l'organisation et la diffusion de l'information géographique

The potential of Computer Vision techniques to support estimation of bedload transport in sewers is investigated. A specific methodology combining the use of algorithms for sediment detection and tracking with advanced image filtering procedures was setup in order to identify the sediment particles contributing to the bedload transport. The methodology was preliminary applied to a large combined sewer channel of Paris City for which videos capturing sediment transport processes during flushing experiments are available.

Mots clés: Image Processing; Sewer flushing; Field Experiments; Sewer sediment transport; Computer Vision

Domaines: Génie civil; Vision par ordinateur et reconnaissance de formes [cs.CV]

Marco Grasso, Oliver Giudice, Alberto Campisano, Gashin Shahsavari, Sebastiano Battiato, et al.. Testing Computer Vision techniques for bedload sediment transport evaluation in sewers. 14th IWA/IAHR International Conference on Urban Drainage (ICUD 2017), Sep 2017, Prague, Czech Republic. pp.1539-1541. ⟨halshs-01629233v2⟩