Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification

The objective of this research was to eliminate the influence of environmental stray light on the measured spectral reflectance in a spectral sensor system used on a weeding teleoperated robot for rape fields. The system mainly consists of a light source, signal acquisition, and data processing. In...

Full description

Bibliographic Details
Main Authors: Tao Tao, Shu Wu, Lin Li, Jinyang Li, Sheng Bao, Xinhua Wei
Format: Article
Language:English
Published: SAGE Publishing 2018-05-01
Series:Advances in Mechanical Engineering
Online Access:https://doi.org/10.1177/1687814018776741
_version_ 1818997938539462656
author Tao Tao
Shu Wu
Lin Li
Jinyang Li
Sheng Bao
Xinhua Wei
author_facet Tao Tao
Shu Wu
Lin Li
Jinyang Li
Sheng Bao
Xinhua Wei
author_sort Tao Tao
collection DOAJ
description The objective of this research was to eliminate the influence of environmental stray light on the measured spectral reflectance in a spectral sensor system used on a weeding teleoperated robot for rape fields. The system mainly consists of a light source, signal acquisition, and data processing. In this study, optical modulation technology and discrete Fourier transform method were used to carry out experiments based on four characteristic wavelengths. The results show that the experimental system can obtain a stable reflectivity value no matter whether the stray light changes slowly or dramatically in the field environment. Furthermore, the calibration equation of spectral reflectance was obtained by curve fitting based on a FieldSpec3 portable spectrometer. The determination coefficients are all close to 1, and the root-mean-square errors are small. Through verification experiments, the results show that the average measurement error is less than 5%. Hence, this proposed method would be very helpful in improving the accuracy and efficiency of the spectral reflectance measurement, which in turn provides a theoretical basis for weed identification during in-field weeding by teleoperated robots.
first_indexed 2024-12-20T21:53:35Z
format Article
id doaj.art-c19287d39b8d4a5e9cd8f1b75f04d592
institution Directory Open Access Journal
issn 1687-8140
language English
last_indexed 2024-12-20T21:53:35Z
publishDate 2018-05-01
publisher SAGE Publishing
record_format Article
series Advances in Mechanical Engineering
spelling doaj.art-c19287d39b8d4a5e9cd8f1b75f04d5922022-12-21T19:25:30ZengSAGE PublishingAdvances in Mechanical Engineering1687-81402018-05-011010.1177/1687814018776741Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identificationTao Tao0Shu Wu1Lin Li2Jinyang Li3Sheng Bao4Xinhua Wei5School of Electrical and Information Engineering, Yangzhou Polytechnic Institute, Yangzhou, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education/School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education/School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education/School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education/School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang, ChinaKey Laboratory of Modern Agricultural Equipment and Technology, Ministry of Education/School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang, ChinaThe objective of this research was to eliminate the influence of environmental stray light on the measured spectral reflectance in a spectral sensor system used on a weeding teleoperated robot for rape fields. The system mainly consists of a light source, signal acquisition, and data processing. In this study, optical modulation technology and discrete Fourier transform method were used to carry out experiments based on four characteristic wavelengths. The results show that the experimental system can obtain a stable reflectivity value no matter whether the stray light changes slowly or dramatically in the field environment. Furthermore, the calibration equation of spectral reflectance was obtained by curve fitting based on a FieldSpec3 portable spectrometer. The determination coefficients are all close to 1, and the root-mean-square errors are small. Through verification experiments, the results show that the average measurement error is less than 5%. Hence, this proposed method would be very helpful in improving the accuracy and efficiency of the spectral reflectance measurement, which in turn provides a theoretical basis for weed identification during in-field weeding by teleoperated robots.https://doi.org/10.1177/1687814018776741
spellingShingle Tao Tao
Shu Wu
Lin Li
Jinyang Li
Sheng Bao
Xinhua Wei
Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
Advances in Mechanical Engineering
title Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
title_full Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
title_fullStr Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
title_full_unstemmed Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
title_short Design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
title_sort design and experiments of weeding teleoperated robot spectral sensor for winter rape and weed identification
url https://doi.org/10.1177/1687814018776741
work_keys_str_mv AT taotao designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification
AT shuwu designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification
AT linli designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification
AT jinyangli designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification
AT shengbao designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification
AT xinhuawei designandexperimentsofweedingteleoperatedrobotspectralsensorforwinterrapeandweedidentification