Surface Crack Segmentation Computer Vision Project

Overview

Surface cracks in concrete and other materials represent significant defects that can compromise the integrity of civil structures. Effective building inspection involves evaluating the rigidity and tensile strength of structures, with crack detection being a critical component in assessing overall building health. This project aims to enhance inspection processes by leveraging advanced machine learning techniques for accurate crack identification.

Concrete surface cracks are major defect in civil structures. Building Inspection which is done for the evaluation of rigidity and tensile strength of the building. Crack detection plays a major role in the building inspection, finding the cracks and determining the building health.

Dataset

The dataset used in this project, available here, is a comprehensive collection of images capturing various types of surface cracks in multiple environments.

Model Training

Using the YOLOv11 architecture, this model was trained to detect and segment cracks with high accuracy and efficiency. The key stages of this pipeline include data preprocessing, model configuration, training, and evaluation. Each stage is documented in the Jupyter Notebook file accompanying this project, which details parameters, code, and results.

Source code
Linkedin