https://github.com/sea-me-coss/perception

https://github.com/sea-me-coss/perception

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/sea-me-coss/perception
• Owner: SEA-ME-COSS
• Created: 2024-01-02T11:58:58.000Z (about 1 year ago)
• Default Branch: main
• Last Pushed: 2024-06-28T10:35:23.000Z (6 months ago)
• Last Synced: 2024-09-17T23:09:39.713Z (4 months ago)
• Language: Python
• Size: 64.9 MB
• Stars: 0
• Watchers: 0
• Forks: 1
• Open Issues: 3
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# Perception



This repository is for the **Perception** part of the [Autonomous-Driving-System](https://github.com/SEA-ME-COSS/Autonomous-Driving-System) project.

-----------------------------------

### Train Dataset

- Gazebo

	- Traffic Light

		- Red (546 images)

		- Yellow (451 images)

		- Green (599 images)

	- RoundAbout (890 images)

	- Crosswalk (926 images)

- Real World

	- Traffic Light

		- Red (360 images)

		- Yellow (30 images)

		- Green (211 images)

	- RoundAbout (350 images)

	- Crosswalk (296 images)

 	- Lane 

------------------------------------

### Labelling

- Tools 

    - https://github.com/HumanSignal/labelImg

    - https://github.com/labelmeai/labelme (For lane detection)

------------------------------------

### Model

- Yolov8

    - https://docs.ultralytics.com/ko

	- https://github.com/ultralytics/ultralytics

------------------------------------

### Usage

- /data/main.py

	- Make raw dataset from rosbag

- /object_detect/objectDetect.py

	- Detect object in Gazebo simulation   	

- /object_detect/real.py

	- Detect object in real world