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

基于語音識(shí)別的蔬菜病害視頻語義標(biāo)注與分割方法
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號(hào):

基金項(xiàng)目:

國家自然科學(xué)基金資助項(xiàng)目(31271618)、現(xiàn)代農(nóng)業(yè)產(chǎn)業(yè)技術(shù)體系北京市葉類蔬菜創(chuàng)新團(tuán)隊(duì)建設(shè)專項(xiàng)科研資金資助項(xiàng)目(blvt-20)、中央高校基本科研業(yè)務(wù)費(fèi)專項(xiàng)資金資助項(xiàng)目(2013XJ021)和北京市大學(xué)生科學(xué)研究與創(chuàng)業(yè)行動(dòng)計(jì)劃資助項(xiàng)目(014bj091)


Video Semantic Annotation and Segmentation Method of Vegetable Disease Knowledge Based on Voice Recognition
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:

    為了向農(nóng)民提供蔬菜病害知識(shí),基于語音識(shí)別技術(shù)設(shè)計(jì)了一種蔬菜病害視頻標(biāo)注與分割方法,可將科研機(jī)構(gòu)錄制的蔬菜病害視頻分割成適合手機(jī)播放的小視頻段落。在前期設(shè)計(jì)的視頻鏡頭切分方法基礎(chǔ)上,進(jìn)一步設(shè)計(jì)出基于語音識(shí)別技術(shù)的視頻語義標(biāo)注及視頻鏡頭聚類方法,即首先采用成熟的語音識(shí)別技術(shù),將視頻鏡頭的語音講解識(shí)別為文本形式;進(jìn)而基于本體對識(shí)別文本進(jìn)行相應(yīng)的語義處理,從中提取出能起到指示作用的關(guān)鍵語義實(shí)體,并將其恰當(dāng)?shù)慕M織形式作為視頻鏡頭的語義標(biāo)注;最終根據(jù)用戶提供的關(guān)鍵詞并結(jié)合視頻鏡頭的語義標(biāo)注,對視頻鏡頭進(jìn)行聚類和重組,從而實(shí)現(xiàn)對于蔬菜病害視頻的最終分割。所設(shè)計(jì)的視頻鏡頭語義標(biāo)注方法對2個(gè)測試視頻的查全率分別達(dá)到96.08%、94.93%,查準(zhǔn)率分別達(dá)到94.31%、95.98%,F-1測度也分別達(dá)到0.93和0.92;視頻鏡頭聚類方法使得2個(gè)視頻的分割查全率分別達(dá)到94.9%、98.7%,查準(zhǔn)率分別達(dá)到92.1%、90.2%,查全率平均大于95%,查準(zhǔn)率大于90%。證明所設(shè)計(jì)的蔬菜病害視頻標(biāo)注與分割方法具有理論和實(shí)用價(jià)值。

    Abstract:

    To provide farmers with vegetable diseases knowledge, this paper proposes a method based on voice recognition technology to label and split vegetable diseases videos. Through this method, videos about vegetable diseases can be split into several smaller segments which are more suitable for cell phone. The methods of semantic annotation and video shot clustering were based on video segmentation and voice recognition. In this method, the audio signals of videos were transformed into text strings firstly by voice recognition. Then key semantic entities for labelling video shots semantically were split from the text strings. Finally different video shots were clustered and recombined based on keywords provided by user and the semantic labels of video shots. When applying the method of semantic annotation to two videos, the recall ratios were up to 96.08% and 94.93%, the precision ratios were up to 94.31% and 95.98%, and the F-1 measures were up to 0.93 and 0.92. As for method of video shot clustering, the recall ratios were up to 94.9% and 98.7%, and the precision ratios were up to 92.1% and 90.2%. Results of comparative experiments show that the proposed method is valuable both in theory and practice.

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

李鑫星,劉春迪,溫皓杰,蘇 葉,傅澤田,張領(lǐng)先.基于語音識(shí)別的蔬菜病害視頻語義標(biāo)注與分割方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(9):308-313. Li Xinxing, Liu Chundi, Wen Haojie, Su Ye, Fu Zetian, Zhang Lingxian. Video Semantic Annotation and Segmentation Method of Vegetable Disease Knowledge Based on Voice Recognition[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(9):308-313.

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:2015-01-22
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2015-09-10
  • 出版日期: