hustvl/YOLOP

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2234 stars · 458 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

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

library · maturity maintenance

computer-vision image-processing machine-learning deep-learning autonomous-vehicles computer-vision deep-learning machine-learning python embedded object-detection lane-detection semantic-segmentation multitask-learning yolo bdd100k real-time-inference embedded-devices research-code gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="hustvl/YOLOP")