This project implements a lane detection system using computer vision techniques and deep learning.
Lane detection is a crucial component of advanced driver assistance systems (ADAS) and autonomous vehicles. This project aims to develop a robust lane detection algorithm capable of accurately identifying lane boundaries in images and videos captured by a vehicle's onboard camera.
- Detects lane boundaries in images and videos.
- Supports real-time lane detection.
- Provides visualization of detected lanes overlaid on input images/videos.
- Supports both straight and curved lane detection.
- Uses deep learning models for enhanced accuracy.
- Logs training and evaluation metrics for model performance analysis.
-
Clone the repository:
git clone https://github.com/Ashok-Prajapati2/Road-lane-line-detection.git
-
Install dependencies:
cd Road-lane-line-detection pip install -r requirements.txt
-
Run the application:
python app/main.py
model/model.ipynb
- Place input images or videos in the
data/test_images/
ordata/test_videos/
directory. - Run the application using the provided instructions.
- View the output results in the
results/
directory.
or
- Place input images in the
notebooks/test_images
directory. - Run the script using the jupyter notbook or colob .
- View the output results in the
notebooks/outputs
directory.
or
- Place input videos in the
models/testing
directory. - Run the script using the jupyter notbook or colob .
- View the output results in the
models/videos
ormodels/output
directory.
bash change the image and videos name in `app/main.py` and notebooks.
Configuration files are located in the config/
directory:
environment.yml
: Specifies the conda environment setup.parameters.json
: Contains configurable parameters for the lane detection algorithm.
Contributions are welcome!
This project is licensed under the MIT License. See the LICENSE file for details.
- This project was inspired by Lane Detection using OpenCV by Ashok Kumar.
For questions or feedback, please contact Ashok Kumar.
Here are some examples of lane detection on input images:
Here are some examples of lane detection on input videos: