loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Authors: Haruka Ide 1 ; Hiroyuki Ogata 2 ; Takuya Otani 3 ; Atsuo Takanishi 1 and Jun Ohya 1

Affiliations: 1 Department of Modern Mechanical Engineering, Waseda University, 3-4-1, Ookubo, Shinjuku, Tokyo, Japan ; 2 Faculty of Science and Technology, Seikei University, 3-3-1, Kichijoji-kitamachi, Musashino-shi, Tokyo, Japan ; 3 Waseda Research Institute for Science and Engineering, Waseda University, 3-4-1, Ookubo, Shinjuku, Tokyo, Japan

Keyword(s): Synecoculture, Agriculture, Deep Learning, Robot Vision.

Abstract: Synecoculture cultivates useful plants while expanding biodiversity in farmland, but the complexity of its management requires the establishment of new automated systems for management. In particular, pruning overgrown dominant species that lead to reduced diversity is an important task. This paper proposes a method for detecting overgrown plant species occluding other species from the camera fixed in a Synecoculture farm. The camera acquires time series images once a week soon after seeding. Then, a deep learning based semantic segmentation is applied to each of the weekly images. The plant species map, which consist of multiple layers corresponding to the segmented species, is created by storing the number of the existence of that plant species over weeks at each pixel in that layer. Finally, we combine the semantic segmentation results with the earlier plant species map so that occluding overgrown species and occluded species are detected. As a result of conducting experiments usi ng six sets of time series images acquired over six weeks, (1) UNet-Resnet101 is most accurate for semantic segmentation, (2) Using both segmentation and plant species map achieves significantly higher segmentation accuracies than without plant species map, (3) Overgrown, occluding species and occluded species are successfully detected. (More)

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.141.198.13

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Ide, H.; Ogata, H.; Otani, T.; Takanishi, A. and Ohya, J. (2024). Detecting Overgrown Plant Species Occluding Other Species in Complex Vegetation in Agricultural Fields Based on Temporal Changes in RGB Images and Deep Learning. In Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - ICPRAM; ISBN 978-989-758-684-2; ISSN 2184-4313, SciTePress, pages 266-273. DOI: 10.5220/0012352500003654

@conference{icpram24,
author={Haruka Ide. and Hiroyuki Ogata. and Takuya Otani. and Atsuo Takanishi. and Jun Ohya.},
title={Detecting Overgrown Plant Species Occluding Other Species in Complex Vegetation in Agricultural Fields Based on Temporal Changes in RGB Images and Deep Learning},
booktitle={Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - ICPRAM},
year={2024},
pages={266-273},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012352500003654},
isbn={978-989-758-684-2},
issn={2184-4313},
}

TY - CONF

JO - Proceedings of the 13th International Conference on Pattern Recognition Applications and Methods - ICPRAM
TI - Detecting Overgrown Plant Species Occluding Other Species in Complex Vegetation in Agricultural Fields Based on Temporal Changes in RGB Images and Deep Learning
SN - 978-989-758-684-2
IS - 2184-4313
AU - Ide, H.
AU - Ogata, H.
AU - Otani, T.
AU - Takanishi, A.
AU - Ohya, J.
PY - 2024
SP - 266
EP - 273
DO - 10.5220/0012352500003654
PB - SciTePress