Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC
Sensors · 10.03.2023 · 23 (6) · 3002
DOI: 10.3390/s23063002 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 10.03.2023. Verfasst von Stevan Cakic und 5 weiteren Autor:innen. Beteiligte Einrichtung: Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro. Hauptthemen laut MEDLINE: Poultry, Deep Learning. Die Arbeit wurde bisher 53-mal zitiert (Crossref) und nennt 38 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: European Commission, European High-Performance Computing Joint Undertaking (JU), European Union’s Horizon 2020 research and innovation programme and Germany, Italy, Slovenia, France, Spain.
Abstract (Originalsprache)
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 camera 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 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, detection of 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 development of the dataset and improvements in prediction models is needed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty for Information Systems and Technologies, University of Donja Gorica, Oktoih 1, 81000 Podgorica, Montenegro.
- DigitalSmart, Bul. Dz. Vasingtona bb, 81000 Podgorica, Montenegro.
- DunavNET, Bul. Oslobodjenja 133/2, 21000 Novi Sad, Serbia.
ORCID-Profile: Stevan Cakic, Tomo Popovic, Srdjan Krco
Förderung
- European Commission
- European High-Performance Computing Joint Undertaking (JU)
- European Union’s Horizon 2020 research and innovation programme and Germany, Italy, Slovenia, France, Spain
Zitieren
APA
Cakic, S., Popovic, T., Krco, S., Nedic, D., Babic, D., & Jovovic, I. (2023). Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC. Sensors, 23(6), 3002. https://doi.org/10.3390/s23063002
Vancouver
Cakic S, Popovic T, Krco S, Nedic D, Babic D, Jovovic I. Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC. Sensors. 2023;23(6):3002. doi:10.3390/s23063002
BibTeX
@article{Cakic2023,
author = {Cakic, Stevan and Popovic, Tomo and Krco, Srdjan and Nedic, Daliborka and Babic, Dejan and Jovovic, Ivan},
title = {Developing Edge AI Computer Vision for Smart Poultry Farms Using Deep Learning and HPC},
journal = {Sensors},
year = {2023},
volume = {23},
number = {6},
pages = {3002},
doi = {10.3390/s23063002}
}
EUVIMED