期刊
IEEE ACCESS
卷 8, 期 -, 页码 71272-71278出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/ACCESS.2020.2987642
关键词
Agriculture; Semantics; Agricultural machinery; Graphics; Feature extraction; Wheels; Microsoft Windows; Convolutional encoder-decoder network; crop line detection; semantic graphics; vision based control
资金
- Korea Research Fellowship Program through the National Research Foundation (NRF) of Korea - Ministry of Science and ICT [NRF-2015H1D3A1062316]
- Basic Science Research Program through the NRF - Ministry of Education [NRF-2019R1A6A1A09031717, NRF-2019R1A2C1011297, NRF-2020R1C1C1015010]
- Research Program for Agriculture Science and Technology Development Rural Development Administration, South Korea [PJ01207103]
This paper presents a novel vision based approach for detecting rows of crop in paddy field. The precise detection of crop row enables a farm-tractor to autonomously navigate the field for successful inter-row weeding. While prior works on crop row detection rely primarily on various image based features, a deep neural network based approach for learning semantic graphics to directly extract the crop rows from an input image is used in this work. A deep convolutional encoder decoder network is trained to detect the crop lines using semantic graphics. The detected crop lines are then used to derive control signal for steering the tractor autonomously in the field. The results demonstrate that the proposed method is able to detect the rows of paddy accurately and enable the tractor to navigate autonomously along the crop rows even with a simple proportional only controller.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据