lmy98129/VLPD

Official Code of CVPR'23 Paper "VLPD: Context-Aware Pedestrian Detection via Vision-Language Semantic Self-Supervision"

37
/ 100
Emerging

This project helps computer vision researchers and engineers develop better pedestrian detection systems for real-world scenarios. It takes in images or video frames and outputs bounding box detections for pedestrians, even in challenging conditions like small scale or heavy occlusion. Researchers working on autonomous driving, surveillance, or smart city applications would find this useful.

No commits in the last 6 months.

Use this if you need to develop or evaluate advanced pedestrian detection models that leverage contextual information for improved accuracy.

Not ideal if you are looking for a plug-and-play pedestrian detection tool without needing to dive into research-level model training and evaluation.

pedestrian-detection autonomous-driving surveillance computer-vision-research object-detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

22

Forks

5

Language

Python

License

MIT

Last pushed

Apr 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lmy98129/VLPD"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.