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MRE-PointNet+AE的綠蘿葉片外形參數(shù)估測算法
CSTR:
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

南京農(nóng)業(yè)大學-塔里木大學教師開放科研聯(lián)合基金項目(NNLH202006)、中央高?;究蒲袠I(yè)務費專項資金項目(KYLH202006,、KYZ201914)、新疆生產(chǎn)建設(shè)兵團南疆重點產(chǎn)業(yè)支撐計劃項目(2017DB006)和國家自然科學基金項目(31601545)


Estimation Algorithm of Leaf Shape Parameters of Scirpus sibiricum Based on MRE-PointNet and Autoencoder Model
Author:
Affiliation:

Fund Project:

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

    為了準確,、高效,、自動獲取植物葉片外形參數(shù),提出一種基于多分辨率編碼點云深度學習網(wǎng)絡(luò)(MRE-PointNet)和自編碼器模型的綠蘿葉片外形參數(shù)估測算法,。使用Kinect V2相機以垂直姿態(tài)獲取綠蘿葉片點云數(shù)據(jù),,采用直通濾波、分割,、點云精簡算法對數(shù)據(jù)進行預處理,,通過測定的葉片外形參數(shù)反演綠蘿葉片幾何模型,并計算幾何模型的葉長,、葉寬,、葉面積。將不同參數(shù)組合構(gòu)建的幾何模型離散成點云數(shù)據(jù)輸入MRE-PointNet網(wǎng)絡(luò),,得到幾何模型葉片外形參數(shù)估測的預訓練模型,。針對拍攝過程中存在的葉片部分遮擋和噪聲問題,采用自編碼器網(wǎng)絡(luò)對點云數(shù)據(jù)進行二次處理,,以幾何模型離散的點云數(shù)據(jù)作為輸入,,經(jīng)過編碼-解碼運算得到自編碼器的預訓練模型,提升了MRE-PointNet網(wǎng)絡(luò)在遮擋情況下對葉片外形參數(shù)估測的魯棒性,。試驗共采集300片綠蘿葉片點云數(shù)據(jù),,按照2∶1比例進行劃分,以其中200片點云數(shù)據(jù)作為訓練集,,對預訓練模型MRE-PointNet做模型遷移的參數(shù)微調(diào),,以剩下的100片點云數(shù)據(jù)作為測試集,,評估模型對綠蘿葉片外形參數(shù)的估測能力。采用本文算法將外形參數(shù)估測值和真實值進行數(shù)學統(tǒng)計與線性回歸分析,,得出葉長,、葉寬和葉面積估測的R2和RMSE分別為0.9005和0.4170cm、0.9131和0.3164cm,、0.9447和3.8834cm2,。試驗表明,基于MRE-PointNet和自編碼器模型的綠蘿葉片外形參數(shù)估測算法具有較高的精確度和實用性,。

    Abstract:

    In order to obtain the leaf shape parameters of plant leaves efficiently, accurately and automatically, a multi-resolution coded point cloud deep learning network (MRE-PointNet) and autoencoder model based on the Scirpus sibiricum leaf shape parameter estimation algorithm was proposed. The Kinect V2 camera was used to acquire the point cloud data of Scirpus sibiricum leaves in vertical attitude, and the data was pre-processed by straight-pass filtering, segmentation and point cloud simplification algorithm. The geometric model constructed with different parameter combinations was discretized into point cloud data and input into MRE-PointNet network to obtain the pre-training model of the geometric model shape parameter estimation. In order to solve the problem of partial occlusion and noise of the leaves in the filming process, an autoencoder network with secondary processing of the point cloud data was used to obtain the autoencoder pre-training model by taking the discrete point cloud data of the geometric model as input and encoding-decoding operation, which improved the robustness of the MRE-PointNet network in estimating the shape parameters of the occluded data. A total of 300 point clouds of Scirpus sibiricum leaves were collected. With the ratio of 2∶1, totally 200 slices of point cloud data were used as the training set to fine-tune for model transfer to the pre-training model MRE-PointNet, and the remaining 100 slices of point cloud data were used as the test set. By the algorithm, the mathematical statistics and linear regression analysis were performed to compare the estimated and real values of the shape parameters. The experiment results showed that the estimated R2 and RMSE of leaf length were 0.9005 and 0.4170cm, leaf width was 0.9131 and 0.3164cm, and leaf area was 0.9447 and 3.8834cm2, respectively, based on the MRE-PointNet and the self-training model. The encoder model algorithm for estimating the shape parameters of scirpus sibiricum leaves had high precision and practicality.

    參考文獻
    相似文獻
    引證文獻
引用本文

王浩云,肖海鴻,馬仕航,陳玲,王江波,徐煥良.基于MRE-PointNet+AE的綠蘿葉片外形參數(shù)估測算法[J].農(nóng)業(yè)機械學報,2021,52(1):146-153. WANG Haoyun, XIAO Haihong, MA Shihang, CHEN Ling, WANG Jiangbo, XU Huanliang. Estimation Algorithm of Leaf Shape Parameters of Scirpus sibiricum Based on MRE-PointNet and Autoencoder Model[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(1):146-153.

復制
分享
文章指標
  • 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:2020-09-20
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-01-10
  • 出版日期:
文章二維碼