Detecci\'on y Cuantificaci\'on de Erosi\'on Fluvial con Visi\'on Artificial

TL;DR

This paper presents EROSCAN, an AI-based web tool using YOLOv11 for automatic detection and quantification of fluvial erosion from images, improving efficiency and accuracy over traditional methods.

Contribution

It introduces a novel AI approach combining computer vision and LiDAR data for automatic erosion detection and quantification, integrated into an accessible web application.

Findings

Detection accuracy of 70% for erosion patterns

Reliable estimation of erosion area in pixels and square meters

Development of an interactive web tool for erosion analysis

Abstract

Fluvial erosion is a natural process that can generate significant impacts on soil stability and strategic infrastructures. The detection and monitoring of this phenomenon is traditionally addressed by photogrammetric methods and analysis in geographic information systems. These tasks require specific knowledge and intensive manual processing. This study proposes an artificial intelligence-based approach for automatic identification of eroded zones and estimation of their area. The state-of-the-art computer vision model YOLOv11, adjusted by fine-tuning and trained with photographs and LiDAR images, is used. This combined dataset was segmented and labeled using the Roboflow platform. Experimental results indicate efficient detection of erosion patterns with an accuracy of 70%, precise identification of eroded areas and reliable calculation of their extent in pixels and square meters. As a final product, the EROSCAN system has been developed, an interactive web application that allows users to upload images and obtain automatic segmentations of fluvial erosion, together with the estimated area. This tool optimizes the detection and quantification of the phenomenon, facilitating decision making in risk management and territorial planning.