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K-SSD-F的東亞飛蝗視頻檢測(cè)與計(jì)數(shù)方法
CSTR:
作者:
作者單位:

作者簡(jiǎn)介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:

國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2016YFD0300710)


Video Detection and Counting Method of East Asian Migratory Locusts Based on K-SSD-F
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)目前國(guó)內(nèi)蝗蟲(chóng)監(jiān)測(cè)主要以人工監(jiān)測(cè)為主,、監(jiān)測(cè)效率低且計(jì)數(shù)不準(zhǔn)確的問(wèn)題,,以5齡東亞飛蝗為實(shí)驗(yàn)對(duì)象,提出了一種蝗蟲(chóng)視頻計(jì)數(shù)方法K-SSD-F算法,。該方法可以實(shí)時(shí),、連續(xù)、自動(dòng)監(jiān)測(cè)蝗蟲(chóng)的數(shù)量,。首先利用背景分離法中的KNN算法提取視頻前后幀的時(shí)空特征,;然后通過(guò)標(biāo)注好的數(shù)據(jù)訓(xùn)練SSD模型,并對(duì)視頻進(jìn)行檢測(cè),,提取視頻的靜態(tài)特征,,二者結(jié)合以提高計(jì)數(shù)準(zhǔn)確率;最后利用補(bǔ)幀算法識(shí)別因姿態(tài)變化導(dǎo)致的漏計(jì)數(shù)的幀,。實(shí)驗(yàn)結(jié)果表明,,蝗蟲(chóng)識(shí)別準(zhǔn)確率為97%,召回率為89%,,平均檢測(cè)精度(mAP)為88.94%,,F(xiàn)1值為92.82%,且檢測(cè)速度達(dá)到了19.78f/s,。本文方法具有較好的魯棒性,,可以實(shí)現(xiàn)蝗蟲(chóng)的實(shí)時(shí)和自動(dòng)計(jì)數(shù),其精度優(yōu)于其他模型,,也可為其他種類的昆蟲(chóng)自動(dòng)識(shí)別計(jì)數(shù)提供理論基礎(chǔ),。

    Abstract:

    At present, domestic locust monitoring is mainly based on manual monitoring, with low monitoring efficiency and inaccurate counting. In response to the above problems, the K-SSD-F algorithm, a video counting method of locusts, was proposed with the 5th instar migratory locust as the experimental object. This method can monitor the number of locusts in real time, continuously and automatically. Firstly, the KNN algorithm in the background separation method was used to extract the spatiotemporal features of the frames before and after the video; then the SSD model was trained through the labeled data, the video was detected, and the static features of the video were extracted, and the two were combined to improve the counting accuracy; finally, the frame compensation algorithm was used to recognize missing frames due to posture changes. The experimental results showed that the precision of locust identification was 97%, the recall rate was 89%, the average detection accuracy (mAP) was 88.94%, the F1 value was 92.82%, and the detection speed reached 19.78f/s. The proposed method had good robustness, which can realize real-time and automatic counting of locusts, its accuracy was better than that of other models, and it can also provide a theoretical basis for automatic identification and counting of other kinds of insects.

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

李 林,柏 召,刁 磊,唐 詹,郭旭超.基于K-SSD-F的東亞飛蝗視頻檢測(cè)與計(jì)數(shù)方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2021,52(S0):261-267. LI Lin, BAI Zhao, DIAO Lei, TANG Zhan, GUO Xuchao. Video Detection and Counting Method of East Asian Migratory Locusts Based on K-SSD-F[J]. Transactions of the Chinese Society for Agricultural Machinery,2021,52(S0):261-267.

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:2021-07-13
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2021-11-10
  • 出版日期: 2021-12-10
文章二維碼