Skip to main navigation Skip to search Skip to main content

Analyse granulométrique d'échantillons de sol par vision par ordinateur et réseaux de neurones

Translated title of the thesis: Particle size analysis of soil samples using computer vision and neural networks
  • Thomas Plante St-Cyr

Student thesis: Master's thesisMaster in Engineering: Construction Engineering

Abstract

Optical granulometry coupled with deep learning offers a rapid alternative to traditional mechanical sieving for soil characterization. This thesis presents the development of an open dataset, named Photogranulometry, comprising 12,714 high-resolution images of 316 soil samples annotated with their laboratory particle size distribution curves. To process this high visual dimensionality under weak supervision, an architecture based on attention-based multiple instance learning (ABMIL) and a DINOv2 feature extractor is introduced. This method analyzes photographs as grouped tiles to predict the global particle size distribution curve without explicit segmentation. The model achieves a median weighted mean absolute error of 4.06%. The study demonstrates the viability of the approach on moist samples, which eliminates the laboratory drying step and enables in-situ geotechnical analysis.
Date31 Jul 2026
Original languageFrench
Awarding Institution
  • École de technologie supérieure
SupervisorFrançois Duhaime (Supervisor) & Jean-Sébastien Dubé (Co-supervisor)

Cite this

'