DegangWang97/IEEE_TGRS_PDBSNet

[TGRS 2023 ESI Highly Cited Paper (TOP 1%)] PDBSNet: Pixel-Shuffle Downsampling Blind-Spot Reconstruction Network for Hyperspectral Anomaly Detection

32
/ 100
Emerging

This tool helps geospatial analysts and remote sensing specialists identify unusual or unexpected objects within hyperspectral satellite imagery. You input a hyperspectral image, and it outputs an 'anomaly score' map, highlighting pixels that deviate significantly from their surroundings. This is particularly useful for tasks like environmental monitoring or defense applications where spotting irregularities is critical.

No commits in the last 6 months.

Use this if you need to reliably find small, rare, or unexpected features in your hyperspectral satellite or aerial images without prior knowledge of what those anomalies might look like.

Not ideal if you are working with standard RGB or multispectral images, or if you already have labeled data for the specific anomalies you want to detect.

remote-sensing hyperspectral-imaging geospatial-analysis environmental-monitoring target-detection
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 8 / 25

How are scores calculated?

Stars

20

Forks

2

Language

Python

License

GPL-2.0

Last pushed

Jul 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/DegangWang97/IEEE_TGRS_PDBSNet"

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