臺灣博碩士論文加值系統

由一對立體影像或是多張連續的影像中找出特徵點的對應是電腦視覺中一個經典且困難的問題。本篇論文提出了一個演算法來解決特徵點對應的問題，並設法減少計算量以期能夠達到機器人視覺中建構室內場景所需的即時性。在我們所提出的方法中，首先使用Harris演算法來擷取影像中的角點作為特徵點，接著分析在Harris計算過程中所得到的影像梯度，將影像梯度方向做分類並量化，再分別以不同的顏色來代表所量化的區域，最後所得到的這些彩色碼即可成為此角點所具有的特徵。對每一個特徵點找出其所對應的彩色碼之後，後續的比對工作便可經由彩色碼的比較來達成：若兩點的彩色碼越相似則表示此兩個角點非常有可能是互相對應的兩點。透過距離限制和雙向對應一致性的要求，以及與相鄰點關係的比較，並計算出一評估對應關係的分數，最佳的對應點即可被選擇出來。實驗結果顯示我們所提出的特徵點對應演算法是具有一定的正確性和效率性的。

Establishing feature point correspondences from a pair of stereo or a long sequence of images is a common and critical problem in computer vision. We propose an algorithm to solve this problem and hope to achieve real-time performance by reducing the amount of calculation of the vision system. According to the proposed algorithm, we first extract corner points from images as feature points by the Harris corner detector. The image gradient obtained from Harris corner detector is then classified it into 9 regions according their gradient directions and magnitude. The quantized gradient directions are represented as different colors for each feature point to form a color code. Finally, the point correspondences are obtained by comparing the color codes as well as the spatial relationships between neighboring feature points. Experiments show that the proposed algorithm is efficient and very robust for the matching of feature point.

摘要 I
ABSTRACT II
致謝 III
目錄 IV
圖目錄 VI
表目錄 VIII
第一章 簡介 1
第二章 相關文獻探討 5
2.1 特徵點的擷取 5
2.2 立體影像特徵點對應 7
2.2.1 以極線限制建立特徵點的對應 8
2.2.2 以灰階比較為基礎建立特徵點的對應 11
2.2.3 以特徵比較為基礎建立特徵點的對應 12
2.3 連續影像特徵點追蹤 14
第三章 特徵點的擷取 17
3.1 Harris特徵點擷取演算法 17
3.2 由Harris演算法中分析並量化梯度方向 22
3.3 彩色碼 26
第四章 由立體影像建立特徵點的對應 30
4.1 雙向對應一致性 30
4.2 彩色碼比對機制 32
4.2.1 彩色碼比對之觀察與分析 32
4.2.2 以彩色碼評估對應關係 35
4.3 由相鄰對應點解決模稜兩可的對應問題 38
4.4 以彩色碼為基礎的特徵點對應流程 44
第五章 由連續影像追蹤特徵點 49
5.1 空間時間變化緩和限制 49
5.2 特徵點追蹤流程 50
第六章 實驗結果 56
6.1 立體影像特徵點對應 56
6.2 模稜兩可對應點之實驗與分析 62
6.2.1 CMU影像實驗 63
6.2.2 校正板影像實驗 68
6.3 連續影像特徵點追蹤 73
6.4 以極線限制驗證對應結果之討論 76
第七章 結論與未來展望 79
附錄A 量化梯度方向總數選擇 80
附錄B 以彩色碼校正特徵點位置 82
參考文獻 84

[1] O. Faugeras, B. Hotz, H. Mathieu, T. Vieville, Z. Zhang, P. Eua, E. Theron, L. Moll, G. Berry, J. Vuillemin, P. Bertin, and C. Proy, “Real-Time Correlation-Based Stereo：Algorithm, Implementation and Applications,” Technical Report 2013, INRIA Sophia-Antipolis, August 1993.
[2] J. Weng, N. Ahuja, and T. S. Huang, “Matching Two Perspective Views,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 8, August1992.
[3] H. P. Moravec, “Toward Automatic Visual Obstacle Avoidance,” Proc. of 5th International Joint Conference on Artifitial Intelligence, pp. 584, August 1977.
[4] C. Harris and M. Stephens, ” A Combined Corner and Edge Detector,” Proc. 4th Alvery Vision Conf. Manchester, pp. 189-192, August 1988.
[5] S. M. Smith and J. M. Brady, “SUSAN: A New Approach to Low Level Image Processing,” International Journal of Computer Vision, pp. 45-78, 1997.
[6] H. Asada and M. Brady, “The Curvature Primal Sketch,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 8, pp. 2-14, 1986.
[7] R. Deriche and G. Giraudon, “2-D Curve Matching Using High Curvature Points : Application to Stereo Vision,” Pattern Recognition, pp. 240-242, June 1990.
[8] R. Horaud, F. Veillon, and T. Skordas, “Finding Geometric and Relational Structures in an Image,” Proc. First European Conference On Computer Vision, Antibes, France, pp. 374-384, April 1990.
[9] F. Mokhtarian and R. Suomela, “Robust Image Corner Detection Through Curvature Scale Space,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 12, 1998.
[10] Z. Zhang, R. Deriche, O. Faugeras and Q. T. Luong, “A Robust Technique for Matching Two Uncalibrated Images Through the Recovery of the Unknown Epipolar Geometry,” Research Report no. 2273, INRIA Sophia-Antipolis.
[11] A. Fusiello, V. Roberto, E. Trucco. “Efficient Stereo with Multiple Windowing,” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 858-863, June 1997.
[12] J. Weng, N. Ahuja, T. S. Huang. “Matching Two Perspective Views,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 14, no. 8, August 1992.
[13] N, Ichimura, “Feature Point Tracking Based on Feature Point Extraction by Frame,” IPSJ SIGNotes Computer Vision and Image Media Abstract, no. 130-005, 2002
[14] CMU VASC Image Database ,
http://vasc.ri.cmu.edu/idb/