Drone and GPS Sensors-Based Grassland Management Using Deep-Learning Image Segmentation

Satoki Tsuichihara, Shingo Akita, Reiichirou Ike, Masahiro Shigeta, Hiroshi Takemura, Takahiro Natori, Naoyuki Aikawa, Kazumasa Shindo, Yasuyuki Ide, Shigeki Tejima

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

Farmers have interests to install the automation of checking grass and condition of raising cows using ICT techniques. In particular, it takes a long time to measure the number of broad-leaved weeds, which badly affect the raising cows, for increasing farm crops efficiently and for observing the health condition of the raising cows. We develop a farm management system that suggests plans for removing the broadleaved weeds using grass images captured by a drone and helps in deciding the amount and the place to put fertilizers. A region segmentation based on the deep-learning method can detect the broad-leaved weeds with an accuracy of around 80 %. Using the results of the segmentation, we can calculate the area covered by broad-leaved weeds in one region of the farm in order to provide suggestions for removing the weeds. By comparing the GPS data of all the sensors, we can find grazing cows' groups and the areas that have larger amounts of cow dung. There is no need to add any fertilizers in these areas, which results in a reduction in cost.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages608-611
Number of pages4
ISBN (Electronic)9781538692455
DOIs
Publication statusPublished - 26 Mar 2019
Event3rd IEEE International Conference on Robotic Computing, IRC 2019 - Naples, Italy
Duration: 25 Feb 201927 Feb 2019

Publication series

NameProceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019

Conference

Conference3rd IEEE International Conference on Robotic Computing, IRC 2019
CountryItaly
CityNaples
Period25/02/1927/02/19

    Fingerprint

Keywords

  • automated agriculture
  • drone
  • image segmentation using deep learning

Cite this

Tsuichihara, S., Akita, S., Ike, R., Shigeta, M., Takemura, H., Natori, T., Aikawa, N., Shindo, K., Ide, Y., & Tejima, S. (2019). Drone and GPS Sensors-Based Grassland Management Using Deep-Learning Image Segmentation. In Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019 (pp. 608-611). [8675581] (Proceedings - 3rd IEEE International Conference on Robotic Computing, IRC 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IRC.2019.00123