亚洲一区欧美在线,日韩欧美视频免费观看,色戒的三场床戏分别是在几段,欧美日韩国产在线人成

基于區(qū)域語義和邊緣信息融合的作物苗期植株分割模型
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

智慧農(nóng)業(yè)研究院開放基金項目(IAR2021A02)、安徽省自然科學(xué)基金項目(2108085MC96、1808085ME158)和安徽省研發(fā)計劃項目(202004a06020016、202004a06020061)


Segmentation of Crop Plant Seedlings Based on Regional Semantic and Edge Information Fusion
Author:
Affiliation:

Fund Project:

  • 摘要
  • |
  • 圖/表
  • |
  • 訪問統(tǒng)計
  • |
  • 參考文獻(xiàn)
  • |
  • 相似文獻(xiàn)
  • |
  • 引證文獻(xiàn)
  • |
  • 資源附件
  • |
  • 文章評論
    摘要:

    為在自然環(huán)境下準(zhǔn)確分割作物苗期植株,實現(xiàn)苗期植株定位及其表型自動化測量,本文提出一種融合目標(biāo)區(qū)域語義和邊緣信息的作物苗期植株分割網(wǎng)絡(luò)模型。以U-Net網(wǎng)絡(luò)構(gòu)建主干網(wǎng)絡(luò),基于側(cè)邊深度監(jiān)督機(jī)制,引導(dǎo)主干網(wǎng)絡(luò)在提取特征時能感知植株邊緣信息;利用空間空洞特征金字塔構(gòu)建特征融合模塊,融合主干網(wǎng)絡(luò)和邊緣感知模塊提取的特征,融合后的特征圖具有足夠的細(xì)節(jié)信息和更強(qiáng)的語義信息;聯(lián)合邊緣感知的損失與特征融合的損失,構(gòu)建聯(lián)合損失函數(shù),用于整體網(wǎng)絡(luò)優(yōu)化。實驗結(jié)果表明,本文模型對不同數(shù)據(jù)集的作物植株的語義分割像素準(zhǔn)確率高達(dá)0.962,平均交并比達(dá)到0.932;與U-Net、SegNet、PSPNet、DeepLabV3模型相比,本文模型在不同數(shù)據(jù)集上平均交并比最高提升0.07,對自然環(huán)境下作物苗期植株具有良好的分割效果和泛化能力,可為植株定位、對靶噴藥、長勢識別等應(yīng)用提供重要依據(jù)。

    Abstract:

    To segment crop plant seedlings accurately in natural environment, a segmentation network model based on regional semantic and edge information was presented. Firstly, the U-Net network was used as the backbone network, and the side depth supervision mechanism was used to guide the backbone network to perceive the plant edge information when extracting features. Then, based on atrous spatial pyramid pooling, the feature fusion module was built to fuse the semantic information in the backbone network and the edge information extracted by the edge perception module. The fused feature map would have enough detail information and strong semantic information. Besides, combined with the loss of edge perception and the loss of feature fusion, the joint loss function was defined for the overall network optimization. The experimental results showed that the proposed model can achieve the pixel accuracy of 0.962 and the mean intersection over union of 0.932. Compared with the U-Net, SegNet, PSPNet and DeepLabV3 models,the mean intersection over union of the used model was about 0.07 higher. Therefore, the proposed model can achieve good segmentation effect and generalization ability for crop plant seedlings in natural environment, which can provide important basis for plant location, target spraying, growth recognition and other applications.

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

廖娟,陳民慧,張鍇,鄒禹,張順,朱德泉.基于區(qū)域語義和邊緣信息融合的作物苗期植株分割模型[J].農(nóng)業(yè)機(jī)械學(xué)報,2021,52(12):171-181. LIAO Juan, CHEN Minhui, ZHANG Kai, ZOU Yu, ZHANG Shun, ZHU Dequan. Segmentation of Crop Plant Seedlings Based on Regional Semantic and Edge Information Fusion[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(12):171-181.

復(fù)制
分享
文章指標(biāo)
  • 點擊次數(shù):
  • 下載次數(shù):
  • HTML閱讀次數(shù):
  • 引用次數(shù):
歷史
  • 收稿日期:2021-07-13
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-09-28
  • 出版日期:
文章二維碼