Real-time Cricket Sorting By Sex

TL;DR

This paper introduces a low-cost, real-time automated sex-sorting system for house crickets using computer vision and physical actuation, achieving high accuracy and demonstrating practical deployment for sustainable insect farming.

Contribution

The work presents a novel, integrated system combining a Raspberry Pi, YOLOv8 nano, and a sorting arm for real-time cricket sex sorting, advancing automation in insect agriculture.

Findings

Achieved 86.8% overall sorting accuracy in real-world tests.

Model reached a mean Average Precision of 0.977 on test data.

Demonstrated feasibility of lightweight deep learning on resource-constrained devices.

Abstract

The global demand for sustainable protein sources is driving increasing interest in edible insects, with Acheta domesticus (house cricket) identified as one of the most suitable species for industrial production. Current farming practices typically rear crickets in mixed-sex populations without automated sex sorting, despite potential benefits such as selective breeding, optimized reproduction ratios, and nutritional differentiation. This work presents a low-cost, real-time system for automated sex-based sorting of Acheta domesticus, combining computer vision and physical actuation. The device integrates a Raspberry Pi 5 with the official Raspberry AI Camera and a custom YOLOv8 nano object detection model, together with a servo-actuated sorting arm. The model reached a mean Average Precision at IoU 0.5 (mAP@0.5) of 0.977 during testing, and real-world experiments with groups of crickets achieved an overall sorting accuracy of 86.8%. These results demonstrate the feasibility of deploying lightweight deep learning models on resource-constrained devices for insect farming applications, offering a practical solution to improve efficiency and sustainability in cricket production.