DocF/multispectral-object-detection

Multispectral Object Detection with Yolov5 and Transformer

47
/ 100
Emerging

This tool helps improve the accuracy of object detection in challenging conditions, especially at night or in varied lighting. It takes pairs of images—one from a regular camera (RGB) and one from a thermal camera (infrared)—and identifies objects within them. Operations engineers, security personnel, or anyone needing reliable automated surveillance and object recognition would use this.

460 stars. No commits in the last 6 months.

Use this if you need to detect objects with high reliability in environments where traditional cameras struggle, such as in low light, fog, or obscured views, by leveraging both visible and thermal imagery.

Not ideal if you only have single-modality (e.g., only RGB or only thermal) image data, as it is specifically designed for fusing information from both types.

night vision surveillance thermal imaging autonomous systems object detection
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

460

Forks

76

Language

Python

License

AGPL-3.0

Last pushed

May 19, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DocF/multispectral-object-detection"

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