OS8-7 Intelligent agricultural landscape identification system

Title:	OS8-7 Intelligent agricultural landscape identification system
Publication:	ICAROB2025
Volume:	30
Pages:	232-235
ISSN:	2188-7829
DOI:	10.5954/ICAROB.2025.OS8-7
Author(s):	Ching Ju Chen, Yu-Cheng Chen, Jing-Yao Lin, Rung-Tsung Chen, Candera Wijaya
Publication Date:	February 13, 2025
Keywords:	Semantic Segmentation, Artificial Intelligence, Image Recognition, Biodiversity, Deep Learning
Abstract:	In recent years, Taiwan's economic development and land restructuring have decreased agricultural land area. The decrease in agricultural land area will affect the food supply for human beings and reduce the habitat of wild animals, destroying biodiversity. With the development of drone technology, the survey of farmland ecology no longer requires a large workforce to visit the site for inspection and analysis. This paper proposes a recognition system based on the Semantic segmentation method to classify agricultural landscapes, watersheds, and habitats automatically. We use two models for training: U-Net with the VGG16 model and U-Net with the Resnet50 model. The experiments in this paper show that the U-Net with VGG16 model and the U-Net with Resnet50 model applied to semantic segmentation of farmland landscape images have their classification categories. Still, some categories may be misclassified due to the similarity of the features, such as grassland, fallow field, and upland fields. This paper suggests that in the future, the number of data sets and the diversity of samples.
PDF File:	https://alife-robotics.co.jp/members2025/icarob/data/html/data/OS/OS8/OS8-7.pdf
Copyright:	© The authors. This article is distributed under the terms of the Creative Commons Attribution License 4.0, which permits non-commercial use, distribution and reproduction in any medium, provided the original work is properly cited. See for details: https://creativecommons.org/licenses/by-nc/4.0/

HOME