CNN Classifier for Just-in-Time Woodpeckers Detection and Deterrent

TL;DR

This paper presents a CNN-based classifier implemented on microcontrollers to detect woodpecker drumming in real-time, enabling autonomous deterrent systems to prevent property damage efficiently.

Contribution

It introduces a lightweight CNN model converted to TF Lite Micro for embedded detection of woodpecker drumming, optimizing for low computational cost and real-time performance.

Findings

Successfully detects woodpecker drumming signatures

Runs efficiently on microcontroller units

Enables autonomous woodpecker deterrent systems

Abstract

Woodpeckers can cause significant damage to homes, especially in suburban areas. There are a number of preventing and repelling methods including passive decoys, though these may only provide temporary relief. Subsequently, it may be more efficient to implement a woodpecker deterrent, such as motion, light, sound, or ultrasound that would be triggered by detection of woodpecker signature drumming. To detect the typical 25 Hz drumming frequency, sampling periods under 10 milliseconds with frequent FFTs are required with considerable computational costs. An in-hardware spectrum analyzer may avoid these costs by trading off frequency for time resolutions. The trained model converted to TF Lite Micro, ported to an MCU, and identifies a variety of the prerecorded woodpecker drumming. The plan is to integrate the prototype with a deterrent device making it a completely autonomous solution.