# cfzd/Ultra-Fast-Lane-Detection

Ultra Fast Structure-aware Deep Lane Detection (ECCV 2020)

Repository: https://github.com/cfzd/Ultra-Fast-Lane-Detection
Canonical: https://ross.abutalabs.com/products/ultra-fast-lane-detection
Language: Python
License: MIT
License Family: permissive
Topics: lane-detection, autonomous-driving, lane-detector, lane-finding, road-detection, autonomous-vehicles, cnn, pytorch
Last push: 2022-12-14T06:50:09+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2293, "days_push": 1358, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2048, forks 528 (observed 2026-08-28T04:06:09.027566+00:00)

## What it is
A PyTorch implementation of the ECCV 2020 paper 'Ultra Fast Structure-aware Deep Lane Detection', providing training and evaluation code for fast lane detection models. It includes pretrained ResNet-18 models on the CULane and TuSimple benchmarks running at hundreds of FPS.

## Use cases
- detect lane markings in dashcam or driving footage
- train a lane detection model on CULane or TuSimple datasets
- run real-time lane detection on a GPU for autonomous driving research
- benchmark lane detection accuracy and speed
- replicate ECCV 2020 lane detection paper results

## When to choose
- you need a fast, well-cited lane detection baseline in PyTorch
- you want pretrained models for CULane or TuSimple benchmarks
- you are doing autonomous driving perception research

## When to avoid
- you need a production-ready lane detection SDK with deployment support
- you want the improved TPAMI 2022 version (use Ultra-Fast-Lane-Detection-v2)
- you need multi-task driving perception beyond lane detection

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, machine-learning, deep-learning
- domain: autonomous-vehicles, computer-vision, deep-learning
- platform: python
- tags: lane-detection, pytorch, eccv-2020, autonomous-driving, cnn, research-code, gpu

## Member repositories
- cfzd/Ultra-Fast-Lane-Detection (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:09.027566+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:57:41.842741+00:00, confidence not recorded.
  - readme: https://github.com/cfzd/Ultra-Fast-Lane-Detection (fetched 2026-08-28T04:06:09.027566+00:00, sha 530e2e06b348)
- Data as of 2026-08-30T08:39:29.467469+00:00.