Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/6950
標題: 一個多方位船艦辨識系統雛型之研究
A study of a multi-view ship recognition prototype system
作者: 鄭富元
Cheng, Mu-Zuan
關鍵字: Gradient Vector Flow;動態梯度向量流;Ship Recognition;Fourier Descriptor;船艦辨識;傅立葉描述子
出版社: 電機工程學系所
引用: [1] A. Pope and D. Lowe, “Learning object recognition models from images,” ICCV, pp. 296-301, 1993. [2] I. Weiss and M. Ray, “Model-based recognition of 3D objects from single images,” PAMI, vol.23, no.2, pp. 116-128, 2001. [3] P. Flynn and A. Jain, “BONSAI: 3D object recognition using constrained search,” PAMI, vol.13, no.10, pp. 1066-1075, 1991. [4] F. Leymarie and B.B. Kimia, “The shock scaffold for representing 3D shapes,” Proc. of the Int. Workshop on Visual Form, Springer: Capri, Italy, pp. 216-228, 2001. [5] P. J. Besl and R. C. Jain, “Three-dimensional object recognition,”Comput. Surveys, vol. 1, no. 1, pp. 11-23, 1985. [6] R. T. Chin and C. R. Dyer, “Model-based recognition in robot vision,”ACM Computi. Surveys, vol. 18, no. 1, 1986. [7] J. T. Feddema, C. S. G. Lee, and O. R. Mitchell, “Weighted selection of image features for resolved rate visual feedback control,” IEEE Trans.Robot. Automat., vol. 7, pp. 31-47, Feb. 1991. [8] L. E.Weiss, A. C. Sanderson, and C. P. Neuman, “Dynamic sensor-based control of robots with visual feedback,” IEEE Trans. Robot. Automat.,vol. RA-3, no. 5, pp. 404-417, Oct. 1987. [9] H. Murase and S. K. Nayar, “Visual learning and recognition of 3-d objects from appearance,” Int. J. Comput. Vision, vol. 14, no. 1, pp. 5-24, 1995. [10] S. K. Nayar, S. A. Nene, and H. Murase, “Subspace methods for robot vision,” IEEE Trans. Robot. Automat., vol. 12, p. 750, Oct. 1996. [11] T. Poggio and S. Edelman, “A network that learns to recognize 3D objects,” Nature, vol. 343, pp. 263-266, 1990. [12] M. Turk and A. Pentland, “Eigenfaces for recognition,” J. Cognitive Neurosci., vol. 3, no. 1, pp. 71-86, 1991. [13] M. A. Turk and A. P. Pentland, “Face recognition using eigenfaces,” Proc. IEEE Computer Society Conf. Computer Vision Pattern Recognition, Maui, HI, 1991, pp. 586-591. [14] J.Weng, N. Ahuja, and T. S. Huang, “Learning recognition and segmentation of 3-D objects from 2-D images,” Proc.4th Int. Conf. Computer Vision, Berlin, Germany, May 1993, pp. 121-128. [15] L. Sirovich and M. Kirby, “Low-dimensional procedure for the characterization of human faces,” J. Opt. Soc. Amer., vol. 4, no. 3, pp. 519-524,Mar. 1987. [16] J. J Koenderink, and A. van Doorn, “The internal representation of solid shape with respect to vision”, Biological Cybernetics , vol. 32, pp. 211-216, 1979. [17] M. Kass, A. Witkin, and D. Terzopoulos, “Snake: active contour models,” Int. Journal of Computer Vision, pp. 321-331,1988. [18] C. Y. Xu and J. L. Prince, “Snakes, shapes, and gradient vector flow,” IEEE Trans. Image Processing, vol. 7, no. 3, pp. 359-369, 1998. [19] J. F. Canny, “A computational approach to edge detection,” IEEE Trans. on Pattern Analysis and Machine Intelligence, vol. 8, no. 6, pp. 679-698, 1986.
摘要: 
在電腦視覺之研發領域,三維物體辨識(3D object recognition)是相當重要之一項技術,使電腦能像人類一樣只單純的看到一個三維物體的某一個方向的影像,就能判斷出那是一個什麼東西。如果可以的話,我們便能將其應用在國防科技上例如:移動目標物之辨識,敵我戰車之識別,海防監視應用系統等,那麼我們就擁有快速反應和全天候監控的能力。
建立船艦辨識系統的目的,是為了研發出能在自然海域中有效之船艦擷取技術,配合已建立好之船艦影像特徵資料庫,開發出一套可靠並且能快速辨識的立體船艦辨識系統。在本論文中我們提出了一個應用於船艦辨識的系統。這個系統先使用動態梯度向量流(GVF)來擷取船艦影像的輪廓,並從船艦影像輪廓計算出其幾何特徵值和傅立葉描述子,並分別使用這些特徵值進行粗比對和細比對。本系統使用Matlab軟體建立了一個圖形界面,使用者可以透過這個界面,以互動的方式來進行船艦的辨識過程。

In the field of research and development of the vision of the computer, 3D objects recognition is quite important a technology. It make computer like mankind to see a certain direction of 3D objects then to recognize a 3D object. If all right, we can apply it in military defense applications for example: Moving target recognition、the identification of enemy/non-enemy tanks、the coast defense surveillance system etc. Then we have a fast reaction and all-weather ability to control.
The purpose of ship recognition system is that we can have a technology to research and develop for gathering contour of ship in the natural sea area. We can develop a set of ship recognition system which is reliable and fast to cooperate with a good ship characteristic database. We have proposed in this paper a system for ship recognition. This system uses gradient vector flow (GVF ) to gather the contour of ship image first and calculate out its geometry characteristic value by using this contour and fourier descriptor. We use these characteristic values to do rough and detail recognition separately. In this system we use Matlab software to set up graphic user interface and user can through this interface carry out recognition of ship by the way of interaction.
URI: http://hdl.handle.net/11455/6950
其他識別: U0005-2606200611063100
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.