このアイテムのアクセス数: 340

このアイテムのファイル:
ファイル 記述 サイズフォーマット 
j.compag.2020.105499.pdf1.18 MBAdobe PDF見る/開く
タイトル: Implementation of deep-learning algorithm for obstacle detection and collision avoidance for robotic harvester
著者: Li, Yang
Iida, Michihisa  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-7443-5926 (unconfirmed)
Suyama, Tomoya
Suguri, Masahiko
Masuda, Ryohei  kyouindb  KAKEN_id
著者名の別形: 李, 楊
飯田, 訓久
壽山, 智也
村主, 勝彦
増田, 良平
キーワード: Robotic combine harvester
Deep learning
Human detection
Image cascade network
Network slimming
発行日: Jul-2020
出版者: Elsevier B.V.
誌名: Computers and Electronics in Agriculture
巻: 174
論文番号: 105499
抄録: Convolutional neural networks (CNNs) are the current state of the art systems in image semantic segmentation (SS). However, because it requires a large computational cost, it is not suitable for running on embedded devices, such as on rice combine harvesters. In order to detect and identify the surrounding environment for a rice combine harvester in real time, a neural network using Network Slimming to reduce the network model size, which takes wide neural networks as the input model, yielding a compact model (hereafter referred to as “pruned model”) with comparable accuracy, was applied based on an image cascade network (ICNet). Network Slimming performs channel-level sparsity of convolutional layers in the ICNet by imposing L1 regularization on channel scaling factors with the corresponding batch normalization layer, which removes less informative feature channels in the convolutional layers to obtain a more compact model. Then each of the pruned models were evaluated by mean intersection over union (IoU) on the test set. When the compaction ratio is 80%, it gives a 97.4% reduction of model volume size, running 1.33 times faster with comparable accuracy as the original model. The results showed that when the compaction ratio is less than 80%, a more efficient (less computational cost) model with a slightly reduced accuracy in comparison to the original model was achieved. Field tests were conducted with the pruned model (80% compaction ratio) to verify the performance of obstacle detection. Results showed that the average success rate of collision avoidance was 96.6% at an average processing speed of 32.2 FPS (31.1 ms per frame) with an image size of 640 × 480 pixels on a Jetson Xavier. It shows that the pruned model can be used for obstacle detection and collision avoidance in robotic harvesters.
著作権等: © 2020. This manuscript version is made available under the CC-BY-NC-ND 4.0 license http://creativecommons.org/licenses/by-nc-nd/4.0/.
The full-text file will be made open to the public on 1 July 2022 in accordance with publisher's 'Terms and Conditions for Self-Archiving'.
この論文は出版社版でありません。引用の際には出版社版をご確認ご利用ください。
This is not the published version. Please cite only the published version.
URI: http://hdl.handle.net/2433/252404
DOI(出版社版): 10.1016/j.compag.2020.105499
出現コレクション:学術雑誌掲載論文等

アイテムの詳細レコードを表示する

Export to RefWorks


出力フォーマット 


このリポジトリに保管されているアイテムはすべて著作権により保護されています。