A deep learning based system for real time lane detection on road images and video streams. The project uses TensorFlow and OpenCV to identify lane markings and overlay them on input frames. The design is inspired by the method described in:
Robust Lane Detection Based on Convolutional Neural Network and Random Sample Consensus Zhang et al., 2014.
This repository contains training scripts, inference code, and tools for preprocessing and visualization.
- Real-time lane detection in video streams
- Image preprocessing for better lane visibility
- CNN model for accurate lane marking detection
- Visualization of detected lanes on original images
- Python 3.6+
- PyTorch 3.6+
- OpenCV
- NumPy
- Matplotlib
- scikit-learn
-
Clone the repository:
git clone https://github.com/team-torpedo/lane-detection-cnn.git cd lane-detection-cnn -
Install the required packages:
pip install -r requirements.txt
-
Download the pre-trained model weights or train your own model using the provided training scripts.
This project is licensed under the MIT License - see the LICENSE file for details.
Built by Team Torpedo