Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

EnsemblePigDet: Ensemble Deep Learning for Accurate Pig Detection

Authors
Ahn, HanseSon, SeungwookKim, HeegonLee, SungjuChung, YongwhaPark, Daihee
Issue Date
Jun-2021
Publisher
MDPI
Keywords
agriculture IT; computer vision; pig detection; deep learning; data augmentation; model ensemble
Citation
APPLIED SCIENCES-BASEL, v.11, no.12
Indexed
SCIE
SCOPUS
Journal Title
APPLIED SCIENCES-BASEL
Volume
11
Number
12
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/127915
DOI
10.3390/app11125577
ISSN
2076-3417
2076-3417
Abstract
Automated pig monitoring is important for smart pig farms; thus, several deep-learning-based pig monitoring techniques have been proposed recently. In applying automated pig monitoring techniques to real pig farms, however, practical issues such as detecting pigs from overexposed regions, caused by strong sunlight through a window, should be considered. Another practical issue in applying deep-learning-based techniques to a specific pig monitoring application is the annotation cost for pig data. In this study, we propose a method for managing these two practical issues. Using annotated data obtained from training images without overexposed regions, we first generated augmented data to reduce the effect of overexposure. Then, we trained YOLOv4 with both the annotated and augmented data and combined the test results from two YOLOv4 models in a bounding box level to further improve the detection accuracy. We propose accuracy metrics for pig detection in a closed pig pen to evaluate the accuracy of the detection without box-level annotation. Our experimental results with 216,000 "unseen" test data from overexposed regions in the same pig pen show that the proposed ensemble method can significantly improve the detection accuracy of the baseline YOLOv4, from 79.93% to 94.33%, with additional execution time.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Science and Technology > Department of Computer Convergence Software > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Park, Dai Hee photo

Park, Dai Hee
College of Science and Technology (Department of Computer Convergence Software)
Read more

Altmetrics

Total Views & Downloads

BROWSE