Real-time Cricket Sorting By Sex

2025-12-03

AI Summary

To address the lack of efficient, low-cost sex-sorting techniques in edible cricket farming, this study proposes and implements a real-time, edge-deployable automated sex-sorting system. Methodologically, we deploy a lightweight YOLOv8n model on a Raspberry Pi 5 platform, integrated with an official AI camera and a servo-driven mechanical sorting mechanism to establish an end-to-end recognition–decision–execution pipeline. Key contributions include: (1) optimized YOLOv8n training tailored for insect-scale targets; (2) real-time inference (<30 FPS) tightly coordinated with physical actuation under severe resource constraints; and (3) a fully open-source, low-hardware-barrier architecture. Experimental results show a model mAP@0.5 of 0.977 and a population-level sorting accuracy of 86.8%. The system demonstrates feasibility, robustness, and scalability in real-world farming environments, establishing a novel paradigm for precision insect farming.

Technology Category

• Machine Learning: Learning on the Edge & Model Compression
• Computer Vision: Object Detection & Categorization
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

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.

Problem

• Automated sex sorting of house crickets for farming
• Real-time system using computer vision and actuation
• Improving efficiency and sustainability in cricket production

Innovation

• Uses Raspberry Pi and AI camera for real-time detection
• Implements YOLOv8 nano model for accurate cricket sex identification
• Employs servo-actuated arm for automated physical sorting