# Dead Chicken Identification Method Based on a Spatial-Temporal Graph Convolution Network

## TL;DR

This paper presents a new method using cameras and AI to accurately detect dead hens in cage systems, improving farm welfare and efficiency.

## Contribution

A novel dead hen detection method using spatiotemporal graph convolution networks and multimodal data for improved accuracy.

## Key findings

- The improved YOLOv7-Pose model achieved 92.8% average precision in keypoint detection.
- The dead hen identification model reached 99.0% overall classification accuracy.
- The method effectively reduces false alarms from occlusion and ambiguous visual features.

## Abstract

This paper introduces a practical vision system for early, reliable dead hen detection in caged layer houses. Using synchronized visible and thermal infrared cameras with geometric alignment, it extracts hen keypoint trajectories via pose estimation and tracking, then applies a spatiotemporal graph convolutional network for video level decisions. The method is designed to reduce false alarms caused by occlusion and by confusing “resting” with “dead.” Experiments show strong accuracy across challenging barn conditions, supporting faster inspection, timely removal, and improved welfare management in large-scale farms.

In intensive cage rearing systems, accurate dead hen detection remains difficult due to complex environments, severe occlusion, and the high visual similarity between dead hens and live hens in a prone posture. To address these issues, this study proposes a dead hen identification method based on a Spatial-Temporal Graph Convolutional Network (STGCN). Unlike conventional static image-based approaches, the proposed method introduces temporal information to enable dynamic spatial-temporal modeling of hen health states. First, a multimodal fusion algorithm is applied to visible light and thermal infrared images to strengthen multimodal feature representation. Then, an improved YOLOv7-Pose algorithm is used to extract the skeletal keypoints of individual hens, and the ByteTrack algorithm is employed for multi-object tracking. Based on these results, spatial-temporal graph-structured data of hens are constructed by integrating spatial and temporal dimensions. Finally, a spatial-temporal graph convolution model is used to identify dead hens by learning spatial-temporal dependency features from skeleton sequences. Experimental results show that the improved YOLOv7-Pose model achieves an average precision (AP) of 92.8% in keypoint detection. Based on the constructed spatial-temporal graph data, the dead hen identification model reaches an overall classification accuracy of 99.0%, with an accuracy of 98.9% for the dead hen category. These results demonstrate that the proposed method effectively reduces interference caused by feeder occlusion and ambiguous visual features. By using dynamic spatial-temporal information, the method substantially improves robustness and accuracy of dead hen detection in complex cage rearing environments, providing a new technical route for intelligent monitoring of poultry health status.