ass日本风韵熟妇pics男人扒开女人屁屁桶到爽|扒开胸露出奶头亲吻视频|邻居少妇的诱惑|人人妻在线播放|日日摸夜夜摸狠狠摸婷婷|制服 丝袜 人妻|激情熟妇中文字幕|看黄色欧美特一级|日本av人妻系列|高潮对白av,丰满岳妇乱熟妇之荡,日本丰满熟妇乱又伦,日韩欧美一区二区三区在线

基于卷積神經(jīng)網(wǎng)絡(luò)的生菜多光譜圖像分割與配準(zhǔn)
CSTR:
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類(lèi)號(hào):

基金項(xiàng)目:

北京市農(nóng)林科學(xué)院協(xié)同創(chuàng)新中心建設(shè)專(zhuān)項(xiàng)(KJCX201917),、國(guó)家自然科學(xué)基金面上項(xiàng)目(31871519)和北京市農(nóng)林科學(xué)院科研創(chuàng)新平臺(tái)建設(shè)項(xiàng)目(PT2021-31)


Segmentation and Registration of Lettuce Multispectral Image Based on Convolutional Neural Network
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問(wèn)統(tǒng)計(jì)
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評(píng)論
    摘要:

    針對(duì)多光譜圖像中由于多鏡頭多光譜相機(jī)各通道之間存在的偏差以及傳統(tǒng)分割方法的不適用,,圖像分析處理過(guò)程往往會(huì)出現(xiàn)無(wú)法自動(dòng)化分割或分割精度較低的問(wèn)題,提出采用基于相位相關(guān)算法和基于UNet的語(yǔ)義分割模型對(duì)田間生菜多光譜圖像進(jìn)行各個(gè)通道的精確配準(zhǔn)并實(shí)現(xiàn)前景分割,。使用Canny算法對(duì)多光譜各通道圖像進(jìn)行邊緣提取,,進(jìn)而使用相位相關(guān)算法對(duì)多光譜各通道圖像進(jìn)行配準(zhǔn),單幅圖像平均處理時(shí)間0.92s,,配準(zhǔn)精度達(dá)到99%,,滿足后續(xù)圖像分割所需精度;以VGG16作為主干特征提取網(wǎng)絡(luò),,直接采用兩倍上采樣,,使最終輸出圖像和輸入圖像高寬相等,構(gòu)建優(yōu)化的UNet模型,。實(shí)驗(yàn)結(jié)果表明:本文所提出的圖像配準(zhǔn)和圖像分割網(wǎng)絡(luò),,分割像素準(zhǔn)確率達(dá)到99.19%,平均IoU可以達(dá)到94.98%,,能夠很好地對(duì)生菜多光譜圖像進(jìn)行前景分割,,可以為后續(xù)研究作物精準(zhǔn)表型的光譜分析提供參考。

    Abstract:

    In view of the deviations between the channels of multi-lens multi-spectral cameras and the inapplicability of traditional segmentation methods in multi-spectral images, the image analysis and processing process often has the problem of inability to automate segmentation or low segmentation accuracy, so a phase-based algorithm was proposed. And the semantic segmentation model based on UNet performs accurate registration of each channel of the field lettuce multispectral image and realizes foreground segmentation. The Canny algorithm was used to extract the edges of the multi-spectral channel images, and then the phase correlation algorithm was used to register the multi-spectral channel images. The average processing time of a single image was 0.92s, efficiency was increased by 40%, and the registration accuracy reached 99%, which met the requirements of subsequent images and the required accuracy of segmentation. VGG16 was used as the backbone feature extraction network, and the double up sampling was directly used to make the final output image and the input image equal in height and width, and the optimized UNet model was constructed. The experimental results showed that the image registration and image segmentation network proposed achieved 99.19% pixel accuracy and an average IoU of 94.98%. It can perform foreground segmentation on lettuce multispectral images very well, which can be used for follow-up spectral analysis to study the precise phenotype of crops.

    參考文獻(xiàn)
    相似文獻(xiàn)
    引證文獻(xiàn)
引用本文

黃林生,邵松,盧憲菊,郭新宇,樊江川.基于卷積神經(jīng)網(wǎng)絡(luò)的生菜多光譜圖像分割與配準(zhǔn)[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2021,52(9):186-194. HUANG Linsheng, SHAO Song, LU Xianju, GUO Xinyu, FAN Jiangchuan. Segmentation and Registration of Lettuce Multispectral Image Based on Convolutional Neural Network[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(9):186-194.

復(fù)制
分享
文章指標(biāo)
  • 點(diǎn)擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2021-04-18
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-09-10
  • 出版日期:
文章二維碼