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RDN-YOLO的自然環(huán)境下水稻病害識別模型研究
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項(xiàng)目:

國家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2022YFD2001801-3)和國家自然科學(xué)基金項(xiàng)目(32201665)


Rice Disease Recognition in Natural Environment Based on RDN-YOLO
Author:
Affiliation:

Fund Project:

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

    針對自然環(huán)境下水稻病害識別準(zhǔn)確度易受復(fù)雜背景干擾、病害類間差異小難以準(zhǔn)確識別等問題,以提高水稻病害識別精度并進(jìn)行模型的有效輕量化為前提,提出了一種水稻病害識別網(wǎng)絡(luò)模型(RiceDiseaseNet, RDN-YOLO)。以YOLO v5為基本框架,在主干網(wǎng)絡(luò)的特征提取階段嵌入跨階段部分網(wǎng)絡(luò)融合模塊(C2f),增強(qiáng)模型對病害特征的感知能力,并引入空間深度轉(zhuǎn)換卷積(SPDConv),擴(kuò)展模型的感受野,進(jìn)一步提升模型對小病斑特征提取能力;在頸部網(wǎng)絡(luò)嵌入SPDConv結(jié)構(gòu),并利用輕量級卷積GsConv替換部分標(biāo)準(zhǔn)卷積,提高頸部網(wǎng)絡(luò)對病害部位的定位和類別信息預(yù)測的準(zhǔn)確性及推理速度;以穗瘟病、葉瘟病、胡麻斑病、稻曲病和白枯病5種常見水稻病害為研究對象,在自然環(huán)境下采集水稻病害圖像,制作水稻病害數(shù)據(jù)集,進(jìn)行模型訓(xùn)練與測試。實(shí)驗(yàn)結(jié)果表明,本文模型病害檢測精確率高達(dá)94.2%,平均精度均值達(dá)93.5%,模型參數(shù)量為8.1MB;與YOLO v5、Faster R-CNN、YOLO v7、YOLO v8模型相比,模型參數(shù)量略大于YOLO v5,但平均精度均值最高約高12.2個百分點(diǎn),在一定程度上減輕模型復(fù)雜度的同時獲得良好的水稻病害識別效果。

    Abstract:

    Rice diseases such as brown spot, white leaf blight, bacterial blight and rice blast occur frequently during rice development stages, causing serious losses in rice production. Aiming at the challenges in accurately identifying rice diseases under natural conditions, where background is complex, and differences between disease classes are subtle, a rice disease detection network model (RDN-YOLO) was proposed to improve the accuracy of rice disease detection. Firstly, the YOLO v5 network was used as the basic framework, and the C2f module was embedded in the backbone network to enhance the model’s perception of disease features. Besides, the SPDConv was introduced in the backbone network to expand the model’s perception field and further improve the feature extraction ability of minor disease spots. Secondly, the SPDConv was embedded in the neck network, and the lightweight convolution GsConv was used to replace the standard convolution, which can improve the accuracy of positioning of the disease site and prediction of category information and inference speed, contributing to higher accuracy. The model was trained and tested on a dataset comprising images of five common rice diseases: ear blast, leaf blast, leaf spot, smut, and bacterial blight, where the dataset were collected under natural environment. Experimental results showed that the proposed model achieved a disease detection accuracy of 94.2% with mAP of 93.5% and model parameters of 8.1MB. Compared with other models YOLO v5, Faster R-CNN, YOLO v7 and YOLO v8, the complexity of the proposed model was only slightly lower than that of YOLO v5, but the mAP was approximately 12.2 percentage points than that of YOLO v5, which signified a notable advancement in rice disease detection, achieving high accuracy while reducing model complexity to a certain extent.

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

廖娟,劉凱旋,楊玉青,嚴(yán)從寬,張愛芳,朱德泉.基于RDN-YOLO的自然環(huán)境下水稻病害識別模型研究[J].農(nóng)業(yè)機(jī)械學(xué)報,2024,55(8):233-242. LIAO Juan, LIU Kaixuan, YANG Yuqing, YAN Congkuan, ZHANG Aifang, ZHU Dequan. Rice Disease Recognition in Natural Environment Based on RDN-YOLO[J]. Transactions of the Chinese Society for Agricultural Machinery,2024,55(8):233-242.

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:2024-04-15
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2024-08-10
  • 出版日期: