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IM-SSD+ACO算法的整株大豆表型信息提取
CSTR:
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(2016YFD0100201,、2018YFD0201004)


Detection of Pods and Stems in Soybean Based on IM-SSD+ACO Algorithm
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:

    為了減少檢測整株大豆豆莢及莖稈時(shí)相互遮擋對精度造成的影響,，提出了一種基于卷積神經(jīng)網(wǎng)絡(luò)的大豆豆莢及莖稈表型信息檢測方法，根據(jù)大豆植株的生長特征和卷積網(wǎng)絡(luò)的特點(diǎn),，對單次多框檢測器(Single shot multibox detector, SSD）進(jìn)行了改進(jìn),。與傳統(tǒng)SSD相比，改進(jìn)SSD（IM-SSD）具有更好的抗干擾能力和自學(xué)習(xí)能力,。首先,，通過大豆植株圖像采集平臺獲取收獲期的大豆植株圖像，建立大豆植株RGB空間圖像數(shù)據(jù)集,，將數(shù)據(jù)集分為訓(xùn)練集,、測試集和驗(yàn)證集，對訓(xùn)練集進(jìn)行顏色變換,、圖像平移,、旋轉(zhuǎn)和縮放等方式實(shí)現(xiàn)數(shù)據(jù)的擴(kuò)增，提高網(wǎng)絡(luò)的泛化能力,。其次,，提出一種針對大豆植株圖像中豆莢和莖稈的標(biāo)注方法，僅對未被遮擋的部分進(jìn)行標(biāo)注,，目的是降低遮擋產(chǎn)生的誤判,。IM-SSD是在傳統(tǒng)SSD結(jié)構(gòu)的基礎(chǔ)上增加2個(gè)殘差層，使用低層特征圖融合到高層特征圖來增強(qiáng)對小目標(biāo)的檢測能力,，提高網(wǎng)絡(luò)的識別率,，輸入圖像尺寸為600像素×300像素，降低壓縮變形帶來的影響,。對比試驗(yàn)結(jié)果表明,，IM-SSD的平均精度比SSD300高7.79個(gè)百分點(diǎn)，比SSD512高3.83個(gè)百分點(diǎn),。由于卷積神經(jīng)網(wǎng)絡(luò)獲得的大豆植株莖稈定位是分段的,，不能體現(xiàn)莖稈的真實(shí)特征，提出了一種基于蟻群優(yōu)化（Ant colony optimization, ACO）算法的大豆植株莖稈提取方法,，利用ACO結(jié)合IM-SSD的結(jié)果提取完整的大豆植株莖稈,。最后，通過豆莢定位和大豆植株莖稈提取獲得了大豆植株的部分表型信息,，包括全株莢數(shù),、株高,、有效分枝數(shù)、主莖與株型,。

    Abstract:

    Soybean is an important crop in agriculture and plays an important role in the agricultural field of the world. With the increase of population and disasters caused by abnormal climate, how to cultivate more adaptive high-yield crop varieties has become a major problem faced by breeding experts. A soybean detection method was proposed based on deep learning to reduce the influence of illumination, growth difference and occlusion. In view of characteristics of soybean and accuracy of deep learning, single shot multibox detector (SSD) was improved. Compared with the SSD, the improved SSD (IM-SSD) had better anti-interference ability and self-learning ability. The first step was to build datasets by taking 3695 photos of harvested soybean plants under the fixed and defined light condition and blue background described. And the training set was randomly changed by images translation, rotation and scaling to expand the datasets. Then training datasets were used to train and construct network model. To study the effect of base network and the input size of networks, one contrast experiment was designed on SSD and IM-SSD. Through the analysis of the experimental results,the average accuracy of IM-SSD was 7.79 percentage points higher than that of SSD300 and 3.83 percentage points higher than that of SSD512, respectively. Compared with SSD, IM-SSD was improved in soybean pod and stem detection. Nevertheless, the location of the stem by IM-SSD was discontinuous. A method of stem extraction was proposed, which used IM-SSD results and ant colony optimization (ACO) algorithm to extract the whole stem. The experimental results showed that the IM-SSD and the stem extraction method could accurately locate pod and stem of soybean plants. Finally, some phenotypic information of soybean plants was obtained, including the number of pods of the whole plant, plant height, effective branch number, main stem and plant type.

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

寧姍,陳海濤,趙秋多,王業(yè)成.基于IM-SSD+ACO算法的整株大豆表型信息提取[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2021,52(12):182-190. NING Shan, CHEN Haitao, ZHAO Qiuduo, WANG Yecheng. Detection of Pods and Stems in Soybean Based on IM-SSD+ACO Algorithm[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(12):182-190.

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:2020-12-08
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-03-13
  • 出版日期:
文章二維碼