Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Agriculture / Faculty of Agriculture >
Peer-reviewed Journal Articles, etc >
Development of phenotyping system using low altitude UAV imagery and deep learning
This item is licensed under:Creative Commons Attribution 4.0 International
Title: | Development of phenotyping system using low altitude UAV imagery and deep learning |
Authors: | Lyu, Suxing Browse this author | Noguchi, Noboru Browse this author →KAKEN DB | Ospina, Ricardo Browse this author | Kishima, Yuji Browse this author →KAKEN DB |
Keywords: | panicle detection | vision-based phenotyping | deep learning | unmanned aerial vehicle (UAV) |
Issue Date: | Jan-2021 |
Publisher: | Chinese Academy of Agricultural Engineering |
Journal Title: | international journal of agricultural and biological engineerin |
Volume: | 14 |
Issue: | 1 |
Start Page: | 207 |
End Page: | 215 |
Publisher DOI: | 10.25165/j.ijabe.20211401.6025 |
Abstract: | In this study, a lightweight phenotyping system that combined the advantages of both deep learning-based panicle detection and the photogrammetry based on light consumer-level UAVs was proposed. A two-year experiment was conducted to perform data collection and accuracy validation. A deep learning model, named Mask Region-based Convolutional Neural Network (Mask R-CNN), was trained to detect panicles in complex scenes of paddy fields. A total of 13 857 images were fed into Mask R-CNN, with 80% used for training and 20% used for validation. Scores, precision, recall, Average Precision (AP), and F1-score of the Mask R-CNN, were 82.46%, 80.60%, 79.46%, and 79.66%, respectively. A complete workflow was proposed to preprocess flight trajectories and remove repeated detection and noises. Eventually, the evident changed in rice growth during the heading stage was visualized with geographic distributions, and the total number of panicles was predicted before harvest. The average error of the predicted amounts of panicles was 33.98%. Experimental results showed the feasibility of using the developed system as the high-throughput phenotyping approach. |
Rights: | https://creativecommons.org/licenses/by/4.0/ |
Type: | article |
URI: | http://hdl.handle.net/2115/81175 |
Appears in Collections: | 農学院・農学研究院 (Graduate School of Agriculture / Faculty of Agriculture) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
|