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

自然場景下樹上柑橘實時識別技術(shù)
作者:
作者單位:

作者簡介:

通訊作者:

中圖分類號:

基金項目:

國家自然科學(xué)基金資助項目（30771243）和國家“863”高技術(shù)研究發(fā)展計劃資助項目（2006AA10Z263）


Real-time Recognition of Citrus on Trees in Natural Scene
Author:
Affiliation:

Fund Project:

  • 摘要
    • |
  • 圖/表
    • |
  • 訪問統(tǒng)計
    • |
  • 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:

    采用G—B色差分量，通過Otsu自適應(yīng)閾值分割算法分割成熟柑橘圖像，采用基于距離變換的分水嶺分割將遮擋、重疊柑橘逐個分開，利用凸包算法修復(fù)遮擋區(qū)域，設(shè)定圓度閾值去除誤分割區(qū)域，然后提取柑橘輪廓，并運用基于Tukey權(quán)重函數(shù)的最小二乘圓擬合特征圓，提取了柑橘的中心坐標(biāo)及半徑。對87幅圖像中592個柑橘進(jìn)行了識別試驗，總體識別率達(dá)87.2%，遮擋或重疊柑橘識別率均超過80%。

    Abstract:

    Using the gray image of color difference G-B, Otsu algorithm was employed to segment the images of mature citrus and background. Then the occluded fruits and overlapped fruits were separated by watersheds method with distance transform. Convex hull algorithm was used to repair the occluded regions. Roundness threshold was set to remove the error segmented regions. After the citrus contours were extracted, the contours was fitted by means of the least-squares circle fit with Tukey weight function, and the centroid coordinates and radius were gained. The recognition results of 592 fruits in 87 images showed that the total correct recognition rate is up to 87.2%, and the correct recognition rate of occluded citrus and overlapped citrus are more than 80%. 

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

呂強,蔡健榮,趙杰文,王鋒,湯明杰.自然場景下樹上柑橘實時識別技術(shù)[J].農(nóng)業(yè)機械學(xué)報,2010,41(2):185-188,170. Lü Qiang, Cai Jianrong, Zhao Jiewen, Wang Feng, Tang Mingjie. Real-time Recognition of Citrus on Trees in Natural Scene[J]. Transactions of the Chinese Society for Agricultural Machinery,2010,41(2):185-188,170.

復(fù)制
分享
文章指標(biāo)
  • 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:
  • 最后修改日期:
  • 錄用日期:
  • 在線發(fā)布日期:
  • 出版日期: