# hustvl/YOLOP

You Only Look Once for Panopitic Driving Perception.（MIR2022）

Repository: https://github.com/hustvl/YOLOP
Canonical: https://ross.abutalabs.com/products/yolop
Language: Python
License: MIT
License Family: permissive
Topics: multitask-learning, object-detection, lane-detection, drivable-area-segmentation, jetson-tx2, autonomous-driving
Last push: 2023-10-20T16:50:37+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": 1834, "days_push": 1048, "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 2234, forks 458 (observed 2026-08-28T04:06:29.178088+00:00)

## What it is
YOLOP is a multi-task deep learning network that jointly performs traffic object detection, drivable area segmentation, and lane detection in a single forward pass for autonomous driving perception. It achieves real-time inference on embedded devices like Jetson TX2 while maintaining competitive accuracy on the BDD100K dataset.

## Use cases
- detect traffic objects in driving scenes in real time
- segment drivable road area from camera images
- detect lane lines for autonomous driving
- run multi-task driving perception on embedded hardware like Jetson
- benchmark panoptic driving perception models on BDD100K
- study multi-task learning for vision models

## When to choose
- you need real-time joint detection, drivable area, and lane perception from a single network
- you target embedded autonomous-driving hardware with limited compute
- you want a research baseline for multi-task driving perception

## When to avoid
- you need production-grade, actively maintained perception software
- you only need a single task like generic object detection
- you work outside driving/camera-based road scenes

## Facets
- artifact type: library
- maturity: maintenance
- function: computer-vision, image-processing, machine-learning, deep-learning
- domain: autonomous-vehicles, computer-vision, deep-learning, machine-learning
- platform: python, embedded
- tags: object-detection, lane-detection, semantic-segmentation, multitask-learning, yolo, bdd100k, real-time-inference, embedded-devices, research-code, gpu, linux

## Member repositories
- hustvl/YOLOP (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:29.178088+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 2026-08-30T02:44:22.866054+00:00, confidence not recorded.
  - readme: https://github.com/hustvl/YOLOP (fetched 2026-08-28T04:06:29.178088+00:00, sha 14600a7266aa)
- Data as of 2026-08-30T08:39:29.467469+00:00.