#454 · Primary category： Computer Vision
LaneATT
Code for the paper entitled "Keep your Eyes on the Lane: Real-time Attention-guided Lane Detection" (CVPR 2021)
Project last updated：10/09/22
GitHub Stars
696
Forks
175
Contributors
1
License
MIT
Why we included this project
LaneATT is a lane detection model from a CVPR 2021 paper, built around an attention mechanism that picks out the most relevant lane features while keeping the backbone lightweight. Speed was a design goal from the start, which matters for ADAS and autonomous driving perception. The repo ships a complete training and evaluation pipeline: dataset loaders for TuSimple, CULane, and LLAMAS, plus pretrained checkpoints that reproduce the results reported in the paper. The code is compact and readable, so it works well as a baseline when you want to compare a newer lane detection approach against something solid. One caveat: it expects PyTorch 1.6 and a CUDA-compiled NMS module, so budget time for environment setup rather than expecting a plug-and-play install.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)