kbhujbal/SudarshanChakra-acoustic_uav_threat_detection_CNN
🔇 A production-grade deep learning system for real-time drone/UAV detection through acoustic signature analysis. Converts raw audio to Mel-Spectrograms and classifies using a custom CNN. Features auto-dataset ingestion, defense-optimized metrics (high recall), early stopping, model checkpointing, and a ready-to-use inference API.
This system helps military or security personnel monitor their surroundings by listening for unauthorized drone activity. It takes raw environmental audio and processes it to identify specific drone propeller sounds, classifying them as either a 'Threat' (drone detected) or 'Safe' (background noise). This allows defense units to receive immediate alerts about potential aerial threats.
Use this if you need an automated, ground-based acoustic surveillance system to detect the presence of drones in real-time within a monitored area, prioritizing the detection of every possible threat.
Not ideal if you need to identify specific drone models, require visual confirmation, or are operating in environments with extremely high levels of masking background noise that might obscure drone sounds.
Stars
8
Forks
—
Language
Python
License
—
Category
Last pushed
Nov 24, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kbhujbal/SudarshanChakra-acoustic_uav_threat_detection_CNN"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
aqibsaeed/Urban-Sound-Classification
Urban sound classification using Deep Learning
spotify/realbook
Easier audio-based machine learning with TensorFlow.
ArmDeveloperEcosystem/ml-audio-classifier-example-for-pico
ML Audio Classifier Example for Pico 🔊🔥🔔
mimbres/neural-audio-fp
Official implementation of Neural Audio Fingerprint (ICASSP 2021)
f4exb/morseangel
Deep Neural Network for Morse decoding