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

基于條件隨機(jī)場(chǎng)的梨園場(chǎng)景圖像分割方法
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:

高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金資助項(xiàng)目(20130097110043)和國家自然科學(xué)基金資助項(xiàng)目(61203327,、31071325)


Pear Orchard Scene Segmentation Based on Conditional Random Fields
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(píng)論
    摘要:

    提出一種基于條件隨機(jī)場(chǎng)模型的梨園場(chǎng)景分割方法,,條件隨機(jī)場(chǎng)模型直接對(duì)分割目標(biāo)的后驗(yàn)概率建模,,融入圖像空間上下文信息,,使得條件隨機(jī)場(chǎng)模型可以獲得更精確的分割結(jié)果,。將已標(biāo)記的場(chǎng)景圖像劃分為超像素,,超像素的特征向量和標(biāo)記的類別作為學(xué)習(xí)樣本整合到類別數(shù)據(jù)庫中,;將未標(biāo)記場(chǎng)景圖像劃分為超像素,,利用條件隨機(jī)場(chǎng)和類別數(shù)據(jù)庫對(duì)未標(biāo)記圖像超像素的特征向量和空間關(guān)系進(jìn)行建模,;訓(xùn)練獲得模型參數(shù),,利用最大后驗(yàn)邊緣準(zhǔn)則對(duì)未標(biāo)記超像素進(jìn)行類別推理。實(shí)驗(yàn)結(jié)果表明,,與改進(jìn)的K-最近鄰方法相比該算法可以更加準(zhǔn)確地進(jìn)行梨園場(chǎng)景分割,。

    Abstract:

    A pear orchard scene segmentation based on conditional random fields (CRFs) was proposed. The CRFs modeled posterior probabilities directly, and had an ability to fuse context information of images. Therefore, it was a suitable method to solve images segmentation of the pear orchard scene whose structures are often very complicated. Firstly, labeled images of the pear orchard scene were segmented into superpixels, and feature vectors of the superpixels and their corresponding labels were integrated into a label database as training samples. Secondly, unlabeled images of the pear orchard scene were also segmented into the superpixels, and their features and spatial relationships between these unlabeled superpixels were modeled by using the CRFs. Moreover, parameters of the CRFs model were obtained by taking the label database as the training samples. Finally, labels of the unlabeled superpixels were inferred through the maximum posterior marginal (MPM) algorithm. The experimental results showed that the proposed algorithm could provide more accurate segmentation results of the pear orchard scene compared with the mutual K-nearest neighbor method (MKNN). 

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

周俊,朱金榮,王明軍.基于條件隨機(jī)場(chǎng)的梨園場(chǎng)景圖像分割方法[J].農(nóng)業(yè)機(jī)械學(xué)報(bào),2015,46(2):8-13. Zhou Jun, Zhu Jinrong, Wang Mingjun. Pear Orchard Scene Segmentation Based on Conditional Random Fields[J]. Transactions of the Chinese Society for Agricultural Machinery,2015,46(2):8-13.

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:2014-02-23
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期: 2015-02-10
  • 出版日期: 2015-02-10
文章二維碼