Poultry Pose Estimation by Detecting Keypoints With Deep Convolutional Network

The project aimed to develop an automated system to detect the poultry's body keypoints using deep convolutional networks. This research was undertaken due to the significant advances in artificial intelligence, specifically in the branch of the deep convolutional network.

Detecting the body's keypoints of poultry is a critical step in developing an automated system that could accurately determine the health status of poultry either through its posture or mobility (how fast the poultry walks). However, this project focuses on posture estimation instead of mobility due to the nature of the available data.

The data used in this project was sourced from various websites, labeled using the DeepLabCut GUI, and then trained using DeepLabCut in Python on Google Colab. The primary objective of this project was to compare the accuracy of the proposed models to other models with different hyperparameters and backbones. By achieving this, it is hoped that the results of this research could lead to the development of more efficient and accurate poultry health monitoring systems.