Edge AI-Enabled Chicken Health Detection Based on Enhanced FCOS-Lite and Knowledge Distillation

TL;DR

This paper introduces a lightweight, real-time edge-AI detector for chicken health monitoring that combines enhanced FCOS-Lite with knowledge distillation, achieving high accuracy and speed on resource-constrained CMOS sensors.

Contribution

It proposes a novel compact detector with improved accuracy via a gradient weighting loss, CIOU loss, and knowledge distillation, optimized for deployment on edge-AI CMOS sensors.

Findings

Achieved 95.1% mAP and 94.2% F1-score in chicken health detection.

Operates at over 20 FPS on edge devices with low power consumption.

Demonstrated effective deployment of lightweight AI for poultry health monitoring.

Abstract

The utilization of AIoT technology has become a crucial trend in modern poultry management, offering the potential to optimize farming operations and reduce human workloads. This paper presents a real-time and compact edge-AI enabled detector designed to identify chickens and their healthy statuses using frames captured by a lightweight and intelligent camera equipped with an edge-AI enabled CMOS sensor. To ensure efficient deployment of the proposed compact detector within the memory-constrained edge-AI enabled CMOS sensor, we employ a FCOS-Lite detector leveraging MobileNet as the backbone. To mitigate the issue of reduced accuracy in compact edge-AI detectors without incurring additional inference costs, we propose a gradient weighting loss function as classification loss and introduce CIOU loss function as localization loss. Additionally, we propose a knowledge distillation scheme to transfer valuable information from a large teacher detector to the proposed FCOS-Lite detector, thereby enhancing its performance while preserving a compact model size. Experimental results demonstrate the proposed edge-AI enabled detector achieves commendable performance metrics, including a mean average precision (mAP) of 95.1$\%$ and an F1-score of 94.2$\%$, etc. Notably, the proposed detector can be efficiently deployed and operates at a speed exceeding 20 FPS on the edge-AI enabled CMOS sensor, achieved through int8 quantization. That meets practical demands for automated poultry health monitoring using lightweight intelligent cameras with low power consumption and minimal bandwidth costs.