Skip to content

srjchsv/icy-bridges-detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Object detection project

Task is to detect objects - icy bridges, on images coming from road cameras.

  • Data from "rtp-aws", I also tried to solve this problem.
  • Made annotattion with "CVAT.ai" with free account
    • Created 2 classes:
      • bridges
      • icy_bridges
  • Split data into train and validate batches
  • Trained Yolo v8 image detection model
  • Validated the trained model

Its a simple solution to try solve the problem and learn the CV technologies and object detection.

Here is what it was able to detect:

Labeled objects

"How it should be"

Whats model detected on validation

"What model detected"

Confusion Matrix

"Confusion Martix"

useful resources:

Train Yolov8 object detection on a custom dataset https://www.youtube.com/watch?v=m9fH9OWn8YM