Analysis of pig posture detection in group‐housed pigs using deep learning‐based mask scoring instance segmentation
Animal Science Journal · 2024-01 · 95 (1)
DOI: 10.1111/asj.13975 ↗Kurz gefasst
Fachartikel in der Zeitschrift Animal Science Journal, online erschienen am 15.07.2024. Verfasst von Salam Jayachitra Devi und 4 weiteren Autor:innen. Beteiligte Einrichtung: ICAR-National Research Centre on Pig, Rani, Guwahati, Assam, India. Hauptthemen laut MEDLINE: Deep Learning, Posture, Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 35 Literaturangaben. Gefördert von: National Research Centre on Pig, National Research Centre.
Abstract (Originalsprache)
Pig posture is closely linked with livestock health and welfare. There has been significant interest among researchers in using deep learning techniques for pig posture detection. However, this task is challenging due to variations in image angles and times, as well as the presence of multiple pigs in a single image. In this study, we explore an object detection and segmentation algorithm based on instance segmentation scoring to detect different pig postures (sternal lying, lateral lying, walking, and sitting) and segment pig areas in group images, thereby enabling the identification of individual pig postures within a group. The algorithm combines a residual network with 50 layers and a feature pyramid network to extract feature maps from input images. These feature maps are then used to generate regions of interest (RoI) using a region candidate network. For each RoI, the algorithm performs regression to determine the location, classification, and segmentation of each pig posture. To address challenges such as missing targets and error detections among overlapping pigs in group housing, non‐maximum suppression (NMS) is used with a threshold of 0.7. Through extensive hyperparameter analysis, a learning rate of 0.01, a batch size of 512, and 4 images per batch offer superior performance, with accuracy surpassing 96%. Similarly, the mean average precision (mAP) exceeds 83% for object detection and instance segmentation under these settings. Additionally, we compare the method with the faster R‐CNN object detection model. Further, execution times on different processing units considering various hyperparameters and iterations have been analyzed.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- ICAR-National Research Centre on Pig, Rani, Guwahati, Assam, India.
ORCID-Profile: Salam Jayachitra Devi, Jaya Bharati
Förderung
- National Research Centre on Pig
- National Research Centre
Zitieren
APA
Devi, S. J., Doley, J., Bharati, J., Mohan, N. H., & Gupta, V. K. (2024). Analysis of pig posture detection in group‐housed pigs using deep learning‐based mask scoring instance segmentation. Animal Science Journal, 95(1). https://doi.org/10.1111/asj.13975
Vancouver
Devi SJ, Doley J, Bharati J, Mohan NH, Gupta VK. Analysis of pig posture detection in group‐housed pigs using deep learning‐based mask scoring instance segmentation. Animal Science Journal. 2024;95(1). doi:10.1111/asj.13975
BibTeX
@article{Devi2024,
author = {Devi, Salam Jayachitra and Doley, Juwar and Bharati, Jaya and Mohan, N H and Gupta, Vivek Kumar},
title = {Analysis of pig posture detection in group‐housed pigs using deep learning‐based mask scoring instance segmentation},
journal = {Animal Science Journal},
year = {2024},
volume = {95},
number = {1},
doi = {10.1111/asj.13975}
}
EUVIMED