New publication on Edge AI and Deep Learning to Improve Poultry Farming Practices

Home > Research & innovation > New publication on Edge AI and Deep Learning to Improve Poultry Farming Practices
New Publication

The paper “Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC” was published in MDPI journal Sensors, within the Special Issue Novel Architectures and Applications for Artificial Intelligent and Internet of Things Ecosystems.

The research, conducted by a team of experts including Stevan Cakic, Tomo Popović, Srdjan Krčo, Daliborka Nedić, Dejan Babić, and Ivan Jovović, focuses on the creation of prediction models that can be deployed on edge AI devices equipped with cameras and installed in poultry farms.

Abstract

This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with cameras and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on a farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detecting dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further dataset development and prediction model improvements are needed.

The full paper is available here.

Related Posts