cfzd/Ultra-Fast-Lane-Detection
A PyTorch CNN model that detects lane markings in road images for autonomous driving.
Not currently ranked — collecting fresh signals.
star history
This repository implements the paper ‘Ultra Fast Structure-aware Deep Lane Detection’ (ECCV 2020) using PyTorch. It provides a deep learning architecture for real-time lane detection in road images, supporting training on CULane and Tusimple datasets with ResNet backbones. The project includes single and multi-GPU training scripts, configurable data roots, and evaluation code modified from SCNN and Tusimple Benchmark.
Frequently asked
- What is cfzd/Ultra-Fast-Lane-Detection?
- A PyTorch CNN model that detects lane markings in road images for autonomous driving.
- Is Ultra-Fast-Lane-Detection open source?
- Yes — cfzd/Ultra-Fast-Lane-Detection is open source, released under the MIT license.
- What language is Ultra-Fast-Lane-Detection written in?
- cfzd/Ultra-Fast-Lane-Detection is primarily written in Python.
- How popular is Ultra-Fast-Lane-Detection?
- cfzd/Ultra-Fast-Lane-Detection has 2k stars on GitHub.
- Where can I find Ultra-Fast-Lane-Detection?
- cfzd/Ultra-Fast-Lane-Detection is on GitHub at https://github.com/cfzd/Ultra-Fast-Lane-Detection.