Transfer Learning-Driven Cattle Instance Segmentation Using Deep Learning Models

Rotimi-Williams Bello (), Pius A. Owolawi, Etienne A. van Wyk and Chunling Tu
Additional contact information
Rotimi-Williams Bello: Department of Computer Systems Engineering, Faculty of Information and Communication Technology, Tshwane University of Technology, Pretoria 0152, South Africa
Pius A. Owolawi: Department of Computer Systems Engineering, Faculty of Information and Communication Technology, Tshwane University of Technology, Pretoria 0152, South Africa
Etienne A. van Wyk: Department of Computer Systems Engineering, Faculty of Information and Communication Technology, Tshwane University of Technology, Pretoria 0152, South Africa
Chunling Tu: Department of Computer Systems Engineering, Faculty of Information and Communication Technology, Tshwane University of Technology, Pretoria 0152, South Africa

Agriculture, 2024, vol. 14, issue 12, 1-23

Abstract: Among the emerging applications of artificial intelligence is animal instance segmentation, which has provided a practical means for various researchers to accomplish some aim or execute some order. Though video and image processing are two of the several complex tasks in artificial intelligence, these tasks have become more complex due to the large data and resources needed for training deep learning models. However, these challenges are beginning to be overcome by the transfer learning method of deep learning. In furtherance of the application of the transfer learning method, a system is proposed in this study that applies transfer learning to the detection and recognition of animal activity in a typical farm environment using deep learning models. Among the deep learning models compared, Enhanced Mask R-CNN obtained a significant computing time of 0.2 s and 97% mAP results, which are better than the results obtained by Mask R-CNN, Faster R-CNN, SSD, and YOLOv3, respectively. The findings from the results obtained in this study validate the innovative use of transfer learning to address challenges in cattle segmentation by optimizing the segmentation accuracy and processing time (0.2 s) of the proposed Enhanced Mask R-CNN.

Keywords: activity recognition; animal; farm environment; Mask R-CNN; transfer learning (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2024
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/14/12/2282/pdf (application/pdf)
https://www.mdpi.com/2077-0472/14/12/2282/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:14:y:2024:i:12:p:2282-:d:1542635

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().