# Multi-Scale Feature Fusion and Attention-Enhanced R2U-Net for Dynamic Weight Monitoring of Chicken Carcasses

## TL;DR

This paper introduces a deep learning model for automatically and accurately predicting chicken carcass weights using computer vision, aiming to improve poultry farming efficiency.

## Contribution

A novel AR2U-AtNet model with attention mechanisms for dynamic broiler weight monitoring is proposed.

## Key findings

- The model achieved 90.45% mIoU, 95.18% Dice/F1 scores in segmentation.
- Weight prediction reached an R2 score of 0.9324 using regression.
- The model effectively handles carcass variations in size and posture.

## Abstract

Utilizing computer vision technology to develop non-contact methods for broiler weight detection enables real-time monitoring of broiler weight changes. At present, there are very few reports, either internationally or domestically, on broiler carcass weight detection. In this study, a dynamic broiler weight detection model based on deep learning image segmentation is proposed. This model is designed to accurately and efficiently predict broiler weight, addressing the time-consuming and labor-intensive nature of manual operations in commercial broiler production. Ultimately, it aims to improve the efficiency of poultry breeding, demonstrating significant potential and broad applicability.

In recent years, real-time monitoring of broiler chicken weight has become crucial for assessing growth and health status. Currently, obtaining weight data often relies on manual collection. However, this process is cumbersome, labor-intensive, and inefficient. This paper proposes a broiler carcass weight detection model based on deep learning image segmentation and regression to address these issues. The model first segments broiler carcasses and then uses the pixel area of the segmented region as a key feature for a regression model to predict weight. A custom dataset comprising 2709 images from 301 Taihu yellow chickens was established for this study. A novel segmentation network, AR2U-AtNet, derived from R2U-Net, is proposed. To mitigate the interference of background color and texture on target carcasses in slaughterhouse production lines, the Convolutional Block Attention Module (CBAM) is introduced to enable the network to focus on areas containing carcasses. Furthermore, broilers exhibit significant variations in size, morphology, and posture, which impose high demands on the model’s scale adaptability. Selective Kernel Attention (SKAttention) is therefore integrated to flexibly handle broiler images with diverse body conditions. The model achieved an average Intersection over Union (mIoU) score of 90.45%, and Dice and F1 scores of 95.18%. The regression-based weight prediction achieved an R2 value of 0.9324. The results demonstrate that the proposed method can quickly and accurately determine individual broiler carcass weights, thereby alleviating the burden of traditional weighing methods and ultimately improving the production efficiency of yellow-feather broilers.