• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利：CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法，用中文像聊天一样搜索，搜遍4000万医学文献。AI智能推荐，让科研检索更轻松。

立即免费搜索

文件翻译

保留排版，准确专业，支持PDF/Word/PPT等文件格式，支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述，25分钟生成高质量综述，智能提取关键信息，辅助科研写作。

立即免费体验

水稻作物多光谱图像匹配中探测器与特征描述符的比较分析

Comparative Analysis of Detectors and Feature Descriptors for Multispectral Image Matching in Rice Crops.

作者信息

Forero Manuel G, Mambuscay Claudia L, Monroy María F, Miranda Sergio L, Méndez Dehyro, Valencia Milton Orlando, Gomez Selvaraj Michael

机构信息

Semillero Lún, Facultad de Ingeniería, Universidad de Ibagué, Ibagué 730002, Colombia.

International Center for Tropical Agriculture (CIAT), Cali 763537, Colombia.

出版信息

Plants (Basel). 2021 Aug 28;10(9):1791. doi: 10.3390/plants10091791.

DOI:10.3390/plants10091791
PMID:34579324
原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8465351/
Abstract

Precision agriculture has greatly benefited from advances in machine vision and image processing techniques. The use of feature descriptors and detectors allows to find distinctive keypoints in an image and the use of this approach for agronomical applications has become a widespread field of study. By combining near infrared (NIR) images, acquired with a modified Nikon D80 camera, and visible spectrum (VIS) images, acquired with a Nikon D300s, a proper crop identification could be obtained. Still, the use of different sensors brings an image matching challenge due to the difference between cameras and the possible distortions from each imaging technique. The aim of this paper is to compare the performance of several feature descriptors and detectors by comparing near infrared and visual spectral bands in rice crop images. Therefore, a group of 20 different scenes with different cameras and growth stages in a rice crop were evaluated. Thus, red, green, blue (RGB) and L, a, b (CIE Lab*) channels were extracted from VIS images in order to compare the matches obtained between each of them and the corresponding NIR image. The BRISK, SURF, SIFT, ORB, KAZE, and AKAZE methods were implemented, which act as descriptors and detectors. Additionally, a combination was made between the FAST algorithm for the detection of keypoints with the BRIEF, BRISK, and FREAK methods for features description. BF and FLANN matching methods were used. The algorithms were implemented in Python using OpenCV library. The green channel presented the highest number of correct matches in all methods. In turn, the method that presented the highest performance both in time and in the number of correct matches was the combination of the FAST feature detector and the BRISK descriptor.

摘要

精准农业从机器视觉和图像处理技术的进步中受益匪浅。特征描述符和检测器的使用能够在图像中找到独特的关键点，并且这种方法在农艺应用中的使用已成为一个广泛的研究领域。通过将使用改装后的尼康D80相机获取的近红外（NIR）图像与使用尼康D300s相机获取的可见光谱（VIS）图像相结合，可以实现对作物的准确识别。然而，由于相机之间的差异以及每种成像技术可能产生的畸变，使用不同的传感器带来了图像匹配的挑战。本文的目的是通过比较水稻作物图像中的近红外和可见光谱带，来比较几种特征描述符和检测器的性能。因此，对一组20个不同场景进行了评估，这些场景涉及不同的相机和水稻作物的不同生长阶段。因此，从VIS图像中提取红色、绿色、蓝色（RGB）通道以及L、a、b（CIE Lab*）通道，以便比较它们与相应NIR图像之间获得的匹配情况。实现了BRISK、SURF、SIFT、ORB、KAZE和AKAZE方法，这些方法既作为描述符又作为检测器。此外，还将用于关键点检测的FAST算法与用于特征描述的BRIEF、BRISK和FREAK方法进行了组合。使用了BF和FLANN匹配方法。这些算法使用OpenCV库在Python中实现。绿色通道在所有方法中呈现出最高数量的正确匹配。反过来，在时间和正确匹配数量方面表现最佳的方法是FAST特征检测器和BRISK描述符的组合。

https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/25bd1d07d396/plants-10-01791-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/80df19fdec42/plants-10-01791-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/33f5547c77c8/plants-10-01791-g0A2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/591365724add/plants-10-01791-g0A3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/09f968680c24/plants-10-01791-g0A4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/6a9f59335784/plants-10-01791-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/62ab0d7cc59c/plants-10-01791-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/ab5001ebe375/plants-10-01791-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/f56ba9cb3321/plants-10-01791-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/cdca6a98bca6/plants-10-01791-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/f9b2dfa8c006/plants-10-01791-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/0cc76b3b8d3a/plants-10-01791-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/893a36171507/plants-10-01791-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/920e839dba50/plants-10-01791-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/26030232cfc4/plants-10-01791-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/a55825893a3e/plants-10-01791-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/d5da43da7610/plants-10-01791-g012a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/c4f960b88293/plants-10-01791-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/fc57804e4163/plants-10-01791-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/0d18ea957d06/plants-10-01791-g015a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/25bd1d07d396/plants-10-01791-g016.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/80df19fdec42/plants-10-01791-g0A1.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/33f5547c77c8/plants-10-01791-g0A2.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/591365724add/plants-10-01791-g0A3.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/09f968680c24/plants-10-01791-g0A4.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/6a9f59335784/plants-10-01791-g001.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/62ab0d7cc59c/plants-10-01791-g002.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/ab5001ebe375/plants-10-01791-g003.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/f56ba9cb3321/plants-10-01791-g004.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/cdca6a98bca6/plants-10-01791-g005.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/f9b2dfa8c006/plants-10-01791-g006.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/0cc76b3b8d3a/plants-10-01791-g007.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/893a36171507/plants-10-01791-g008.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/920e839dba50/plants-10-01791-g009.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/26030232cfc4/plants-10-01791-g010.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/a55825893a3e/plants-10-01791-g011.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/d5da43da7610/plants-10-01791-g012a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/c4f960b88293/plants-10-01791-g013.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/fc57804e4163/plants-10-01791-g014.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/0d18ea957d06/plants-10-01791-g015a.jpg
https://cdn.ncbi.nlm.nih.gov/pmc/blobs/e0d5/8465351/25bd1d07d396/plants-10-01791-g016.jpg

相似文献

1
Comparative Analysis of Detectors and Feature Descriptors for Multispectral Image Matching in Rice Crops.水稻作物多光谱图像匹配中探测器与特征描述符的比较分析
Plants (Basel). 2021 Aug 28;10(9):1791. doi: 10.3390/plants10091791.
2
Comparative Analysis of Color Space and Channel, Detector, and Descriptor for Feature-Based Image Registration.基于特征的图像配准中颜色空间、通道、检测器和描述符的比较分析
J Imaging. 2024 Apr 28;10(5):105. doi: 10.3390/jimaging10050105.
3
Evaluation of Several Feature Detectors/Extractors on Underwater Images towards vSLAM.面向 vSLAM 的水下图像若干特征检测器/提取器的评估
Sensors (Basel). 2020 Aug 4;20(15):4343. doi: 10.3390/s20154343.
4
Performance Evaluation of State-of-the-Art Local Feature Detectors and Descriptors in the Context of Longitudinal Registration of Retinal Images.基于视网膜图像纵向配准的最新局部特征检测器和描述符的性能评估。
J Med Syst. 2018 Feb 17;42(4):57. doi: 10.1007/s10916-018-0911-z.
5
A FAST-BRISK Feature Detector with Depth Information.带深度信息的快速急动特征检测器。
Sensors (Basel). 2018 Nov 13;18(11):3908. doi: 10.3390/s18113908.
6
Feature Point Matching Based on Distinct Wavelength Phase Congruency and Log-Gabor Filters in Infrared and Visible Images.基于特征点的匹配基于红外和可见图像中独特的波长相位一致性和对数 - Gabor 滤波器。
Sensors (Basel). 2019 Sep 29;19(19):4244. doi: 10.3390/s19194244.
7
Deep feature descriptor based hierarchical dense matching for X-ray angiographic images.基于深度特征描述符的 X 射线血管造影图像分层密集匹配。
Comput Methods Programs Biomed. 2019 Jul;175:233-242. doi: 10.1016/j.cmpb.2019.04.006. Epub 2019 Apr 22.
8
Spectral-Spatial Scale Invariant Feature Transform for Hyperspectral Images.高光谱图像的谱-空尺度不变特征变换。
IEEE Trans Image Process. 2018 Feb;27(2):837-850. doi: 10.1109/TIP.2017.2749145. Epub 2017 Sep 4.
9
Comparison of feature point detectors for multimodal image registration in plant phenotyping.多模态图像配准中特征点检测器的比较研究——在植物表型分析中的应用
PLoS One. 2019 Sep 30;14(9):e0221203. doi: 10.1371/journal.pone.0221203. eCollection 2019.
10
USB: ultrashort binary descriptor for fast visual matching and retrieval.USB：超短二进制描述符，用于快速视觉匹配和检索。
IEEE Trans Image Process. 2014 Aug;23(8):3671-83. doi: 10.1109/TIP.2014.2330794. Epub 2014 Jun 12.

引用本文的文献

1
Precision Horticulture: Application of Optical Sensor Technology for Nitrogen Monitoring Status in Cocoplum, a Native Landscaping Plant.精准园艺：光学传感器技术在本土园林植物可可李氮素监测状况中的应用。
Plants (Basel). 2023 Feb 8;12(4):760. doi: 10.3390/plants12040760.
2
From Classical Radiation to Modern Radiation: Past, Present, and Future of Radiation Mutation Breeding.从经典辐射到现代辐射：辐射诱变育种的过去、现在和未来。
Front Public Health. 2021 Dec 21;9:768071. doi: 10.3389/fpubh.2021.768071. eCollection 2021.

本文引用的文献

1
A True-Color Sensor and Suitable Evaluation Algorithm for Plant Recognition.一种用于植物识别的真彩传感器及其合适的评价算法。
Sensors (Basel). 2017 Aug 8;17(8):1823. doi: 10.3390/s17081823.