crack-detection-and-severity-classsification-using-yolov5-seg-and-restnet-18

This project leverages deep learning for automated detection and severity classification of road and concrete cracks in real-time video and image feeds. Using YOLOv5 for object detection and a custom-trained ResNet-18 model for classifying crack severity into No Crack, Mild, Moderate, and Severe. The Streamlit UI enables easy visualization

https://github.com/atjibraan/crack-detection-and-severity-classsification-using-yolov5-seg-and-restnet-18

Last synced: 6 months ago · JSON representation ·

Repository

This project leverages deep learning for automated detection and severity classification of road and concrete cracks in real-time video and image feeds. Using YOLOv5 for object detection and a custom-trained ResNet-18 model for classifying crack severity into No Crack, Mild, Moderate, and Severe. The Streamlit UI enables easy visualization

Basic Info

Host: GitHub
Owner: atjibraan
Language: Python
Default Branch: main
Homepage:
Size: 29.6 MB

Statistics

Stars: 0
Watchers: 1
Forks: 0
Open Issues: 0
Releases: 0

Created 11 months ago · Last pushed 6 months ago

Metadata Files

Readme Contributing Citation

README.md

🧱 Crack Detection & Severity Classification using YOLOv5 + ResNet18

Access the Gradio app through https://huggingface.co/spaces/AJibraan/Crack

This project presents an end-to-end deep learning solution to automatically detect and classify cracks on concrete or pavement surfaces. We use YOLOv5 for crack detection and ResNet18 for severity classification. The dataset is accessed directly from Roboflow using their API.

📊 Overview

Manual inspection of structural surfaces like roads, bridges, and buildings is inefficient and subjective. This project automates the process: - YOLOv5 is used for real-time crack detection in images. - ResNet18 is used to classify each detected crack as Mild, Moderate, or Severe.

The combination of detection and classification provides a scalable system for intelligent infrastructure assessment.

🧬 Dataset

📦 Source: Roboflow

We used a custom annotated dataset hosted on Roboflow, accessed using its API for streamlined training and testing.

Replace the placeholders below with your actual Roboflow project details.

```python

Install Roboflow SDK

!pip install roboflow

Access Roboflow Dataset

from roboflow import Roboflow rf = Roboflow(apikey="YOURAPI_KEY") project = rf.workspace("your-workspace").project("your-project-name") dataset = project.version("1").download("yolov5")

Owner

Name: Jibraan Attar
Login: atjibraan
Kind: user

Repositories: 1
Profile: https://github.com/atjibraan

Pursuing Post graduation in Data science and AI | Statistician

Citation (CITATION.cff)

cff-version: 1.2.0
preferred-citation:
  type: software
  message: If you use YOLOv5, please cite it as below.
  authors:
  - family-names: Jocher
    given-names: Glenn
    orcid: "https://orcid.org/0000-0001-5950-6979"
  title: "YOLOv5 by Ultralytics"
  version: 7.0
  doi: 10.5281/zenodo.3908559
  date-released: 2020-5-29
  license: AGPL-3.0
  url: "https://github.com/ultralytics/yolov5"

ecosyste.ms

Data

Tools

Indexes

Applications

Experiments

Open Source Science