Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/8605
標題: 以快速霍夫轉換實現直線偵測
Line Detection Using Fast Hough Transform
作者: 曾榮諄
Tseng, Jung-Chun
關鍵字: line detection;直線偵測;Hough transform;霍夫轉換
出版社: 電機工程學系所
引用: 中文部分 [1] 黃國禎,“利用低空飛行器GPS羅盤定位和CCD攝影機技術對地面目標方位估算”“Rotocraft Low-Altitude Flight Using GPS Compass and CCD camera technique for ground object Azimuth Estimation “,國立中山大學,2004. [2]鄭錦峰,”C-arm 影像三維重建”,銘傳大學,機械工程研究所,2004 [3]陳冠臻,”以影像為依據建立三維立體模型”,”Image-based 3D Construction ”,國立中山大學資訊工程,2001. [4]趙昊昱,”基於視覺的無人機著陸導航”,”Vision Based Navigation for Unmanned Aircraft Landing”,華中科技大學計算數學組,2006. [5]Rafael C.Gonzalez, Richard E.Woods, Steven L.Eddins著;繆紹綱譯,“數位影像處理-運用Matlab,” 台灣東華書局股份有限公司出版,民國94年9月初版. 西文部份 [6]Homas B.Criss, Marilyn M.South(1998), “Multiple Image Coordinate Extraction (MICE) Technique for Rapid Targeting of Precision Guided Munitions, ” Jons Hopkins Apl Technical Degest, vol.19, no.4 [7]J. Canny,”A Computational Approach To Edge Detection”, IEEE Trans. Pattern Analysis and Machine Intelligence, 8(6) 679-698,1986. [8] P.V.C. Hough, “Methods and means for recognizing complex patterns”, U.S. Patent 3.069.654, 1962. [9]R.O. Duda, P.E. Hart, “Use of the Hough transformation to detect lines and curves in pictures”, Commun. ACM 15 (1) (1972) 11–15. [10]Leandro A.F. Fernandes and Manuel M. Oliveira, “Real-time line detection through an improved Hough transform voting scheme”, Pattern Recognition 41 299–314,2008. [11]A.R. Pope, D.G. Lowe, “Vista: a software environment for computer vision research”, in: Proceedings of Computer Vision and Pattern Recognition (CVPR’94), IEEE Computer Society, Seattle, WA, pp. 768–772, 1994. [12]D.G. Lowe, “Three-dimensional object recognition from single two-dimensional images”, Artif. Intell. 31 355–395 (section 4.6), 1987. [13]C.H. Messom,G.Sen Gupta,S. Demidenko,”Hough Transform Run Length Encoding for Real-time Image Processing”,IMT 2005-Instrumentation and Measurement Technology Conference ,Ottawa,Canada,17-19 May ,2005. [14]R.K. Satzoda,S. Suchitra ,and T. Srikanthan,Senior Member,IEEE,”Parallelizing the Hough Transform Computation”,IEEE signal processing letters,vol,15,2008. 網路資源 [15]Wikipedia,”Flight data recorder”, http://en.wikipedia.org/wiki/Flight_data_recorder [16]中央研究院地理資訊研究專題中, http://gis.rchss.sinica.edu.tw [17]Wikipedia,”Geodetic system”, http://en.wikipedia.org/wiki/Geodetic_system
摘要: 
在此論文中,我們利用快速霍夫轉換實做一個直線偵測系統,用來偵測連續影像中的直線目標物。在經過邊緣偵測後影像上,將可能共線的像素點集合成群;接著針對每一群像素點找出最佳線段,並估計各群像素點與對應最佳線段的偏移模式,並從各線段之偏移模式計算橢圓高斯kernel,用以代表各線段的重要性,只針對主要線段進行投票動作。

利用三維空間轉換的關係以及成像的原理,我們可以求出直線目標物於影像中之大略位置,再針對此一區域利用快速霍夫轉換尋找所需的直線,如此一來就可以大幅減少所需的計算量。實驗顯示,直線偵測的準確性及速度有不錯的效能。最後,系統分析影像的特徵,再和資料庫的特徵比對,取得直線目標物的空間資訊,並與影像作整合顯示。

In this thesis, we implement a line detection system based on fast Hough transform and use it to detect line objects in an image sequence. After edge detection, each collinear set of pixels is clustered together in the edge image. Next, we find a best fitting line for each cluster and estimate the uncertainties from pixels of each pixel set and corresponding to the best line. An elliptical Gaussian kernel of the fitting line is then calculated according to these uncertainties to represent the importance of it. The voting process will be performed on major lines only.

With transformations between 3D spaces and the imaging principal, we can estimate position of each line target in the image, and then perform fast Hough transformation on the region around the position and search the line. This can significantly reduce the computing consumption. According to experimental results, the line detection system is accurate and efficient in performance. Finally, the system extracts features of the image and compares with database to obtain the spatial information which is used to present the line target in the image.
URI: http://hdl.handle.net/11455/8605
其他識別: U0005-2108200914250800
Appears in Collections:電機工程學系所

Show full item record
 

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.