batear-io/batear

● batear — Ultra-low-cost, off-grid acoustic drone detector. Edge computing. Protect your airspace with a microphone.

What it solves

Batear provides an affordable, edge-based acoustic drone detection system. It replaces expensive radar or camera-based systems with low-cost hardware that can alert users to the presence of nearby drones by detecting their specific rotor harmonics.

How it works

The system uses an ESP32-S3 microcontroller and a MEMS microphone (ICS-43434) to perform Fast Fourier Transform (FFT) harmonic detection entirely on the device. Depending on the configuration, it can be deployed as a wireless detector using encrypted LoRa packets to communicate with a gateway, or as a wired detector using Ethernet/PoE to send alerts directly to a central system like Home Assistant via MQTT.

Who it’s for

It is designed for homeowners, farmers, and communities seeking a low-cost, privacy-preserving (edge-only) way to monitor for drone activity without relying on cloud subscriptions or internet connections.

Highlights

  • Edge-only processing: No cloud or internet connection required for detection.
  • Flexible deployment: Supports both wireless LoRa (via a gateway) and wired Ethernet/PoE options.
  • Smart home integration: Plug-and-play auto-discovery for Home Assistant via MQTT.
  • Ultra-low-cost: Built on ESP32-S3 hardware for accessibility.
  • Secure communication: Uses AES-128-GCM encryption for wireless alerts.

Related

  • Project
    spite/FaceMeshFaceGeometry

    A three.js BufferGeometry helper that converts MediaPipe face landmarks into a 3D mesh with head pose, expression scores, and iris tracking.

  • Project
    dluvizon/deephar

    A multi-task deep learning framework for real-time 2D and 3D human pose estimation and action recognition.

  • Project
    naruya/gaussian-vrm

    A three.js implementation of Instant Skinned Gaussian Avatars that allows realistic, animatable 3D characters to be rendered in web, mobile, and VR applications.

  • Project
    guochengqian/openpoints

    A library for benchmarking and reproducing point-based methods for point cloud understanding, providing a standardized engine for models like PointNet and PointNeXt.