Skip to content

Guttappa1238/Concrete-defect-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Concrete-defect-detection

Concrete defect analysis

  1. Analyse the type of defect (Crack, Spalling, rebar)
  2. Segment individual defects along with confidence rate.

Why I Used YOLOv8?

Here are a few main reasons why i consider using YOLOv8 for this work:

1. YOLOv8 has a high rate of accuracy measured by COCO and Roboflow 100.

2. YOLOv8 comes with a lot of developer-convenience features, from an easy-to-use CLI to a well-structured Python package.

3. There is a large community around YOLO and a growing community around the YOLOv8 model, meaning there are many people in computer vision circles

YOLOv8 Architecture:

• Backbone: New CSP-Darknet53 

• Neck: SPPF, New CSP-PAN 

• Head: YOLOv3 Head 

image

Anchor Free Detection

YOLOv8 is an anchor-free model. This means it predicts directly the center of an object instead of the offset from a known anchor box.

image

Dataset information:

The dataset consist of 396 images in total and split into train and valid sets, which also have the labels. I used Roboflow to label the images.

Training And Results:

In this work i have used nano pretrained model. And it gave good results in real time inference.

for trainig run python3 train_yolov8.py

for testing run python3 test_yolov8.py

image

image

Confusion matrix:

image

Results:

image

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages