Comparing State-of-the-Art Deep Learning Algorithms for the Automated Detection and Tracking of Black Cattle
Sensors · 03.01.2023 · 23 (1) · 532
DOI: 10.3390/s23010532 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 03.01.2023. Verfasst von Su Myat Noe und 3 weiteren Autor:innen. Beteiligte Einrichtung: Interdisciplinary Graduate School of Agriculture and Engineering, University of Miyazaki, Miyazaki 889-2192, Japan. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 70-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: JST SPRING.
Abstract (Originalsprache)
Effective livestock management is critical for cattle farms in today’s competitive era of smart modern farming. To ensure farm management solutions are efficient, affordable, and scalable, the manual identification and detection of cattle are not feasible in today’s farming systems. Fortunately, automatic tracking and identification systems have greatly improved in recent years. Moreover, correctly identifying individual cows is an integral part of predicting behavior during estrus. By doing so, we can monitor a cow’s behavior, and pinpoint the right time for artificial insemination. However, most previous techniques have relied on direct observation, increasing the human workload. To overcome this problem, this paper proposes the use of state-of-the-art deep learning-based Multi-Object Tracking (MOT) algorithms for a complete system that can automatically and continuously detect and track cattle using an RGB camera. This study compares state-of-the-art MOTs, such as Deep-SORT, Strong-SORT, and customized light-weight tracking algorithms. To improve the tracking accuracy of these deep learning methods, this paper presents an enhanced re-identification approach for a black cattle dataset in Strong-SORT. For evaluating MOT by detection, the system used the YOLO v5 and v7, as a comparison with the instance segmentation model Detectron-2, to detect and classify the cattle. The high cattle-tracking accuracy with a Multi-Object Tracking Accuracy (MOTA) was 96.88%. Using these methods, the findings demonstrate a highly accurate and robust cattle tracking system, which can be applied to innovative monitoring systems for agricultural applications. The effectiveness and efficiency of the proposed system were demonstrated by analyzing a sample of video footage. The proposed method was developed to balance the trade-off between costs and management, thereby improving the productivity and profitability of dairy farms; however, this method can be adapted to other domestic species.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Interdisciplinary Graduate School of Agriculture and Engineering, University of Miyazaki, Miyazaki 889-2192, Japan.
- Graduate School of Engineering, University of Miyazaki, Miyazaki 889-2192, Japan.
- Field Science Center, Faculty of Agriculture, University of Miyazaki, Miyazaki 889-2192, Japan.
ORCID-Profile: Thi Thi Zin, Pyke Tin
Förderung
- JST SPRING
Zitieren
APA
Myat Noe, S., Zin, T. T., Tin, P., & Kobayashi, I. (2023). Comparing State-of-the-Art Deep Learning Algorithms for the Automated Detection and Tracking of Black Cattle. Sensors, 23(1), 532. https://doi.org/10.3390/s23010532
Vancouver
Myat Noe S, Zin TT, Tin P, Kobayashi I. Comparing State-of-the-Art Deep Learning Algorithms for the Automated Detection and Tracking of Black Cattle. Sensors. 2023;23(1):532. doi:10.3390/s23010532
BibTeX
@article{MyatNoe2023,
author = {Myat Noe, Su and Zin, Thi Thi and Tin, Pyke and Kobayashi, Ikuo},
title = {Comparing State-of-the-Art Deep Learning Algorithms for the Automated Detection and Tracking of Black Cattle},
journal = {Sensors},
year = {2023},
volume = {23},
number = {1},
pages = {532},
doi = {10.3390/s23010532}
}
EUVIMED