使用模糊理論基於格式塔心理學原理對立體視覺匹配之研究

A Study on Stereo Matching Using Fuzzy Theory Based on Gestalt Principles

鄭超鴻(Chau-Hung Cheng)

指導教授 ： 駱榮欽

國立臺北科技大學/機電學院/自動化科技研究所/碩士(2012年)

https://doi.org/10.6841/NTUT.2012.00319

摘要

在立體視覺中，如何產生正確且清晰的視差影像是現今熱烈被探討的議題。在傳統局部區域匹配演算法上，如何依據不同的影像特性選擇適合的搜尋視窗大小是一個讓人難以取捨的問題。本論文導入格式塔心理學來增加基於局部區域匹配演算法所完成的視差圖之精確性，利用模糊理論在解決對於人類語言特有的模糊性現象有頗佳的效果，將其用以更精確的描述完形心理學上對於相似度及相近度之探討。實驗結果顯示，我們所提出的演算法成功的結合了模糊理論及格式塔心理學原理，並且在重覆紋理的地區所產生之錯誤率較一般自適應性搜尋視窗演算法來得低。

關鍵字

立體 ； 立體場景分析 ； 視差影像 ； 格式塔心理學 ； 模糊理論

並列摘要

One of most popular issues in stereo vision is how to increase the accuracy of the disparity map. On the traditional area-based local methods, selection on the appropriate search window size based on different image features still debate in recently. This study aims to adopt the Gestalt psychology to increase the accuracy of the disparity map by using fuzzy theory. Fuzzy theory has great effects in solving the ambiguity of linguistic. Therefore, we apply Fuzzy theory to explain the Gestalt psychology on the character of the similarity and the proximity. The result indicated that our method successfully combines the fuzzy theory and Gestalt psychology. The proposed method is better than other window-based methods in the repetitive pattern region.

並列關鍵字

Stereo ； Stereo scene analysis ； Disparity map ； Gestalt psychology ； Fuzzy theory

參考文獻

[1] T. Kanade and M. Okutomi, “A Stereo Matching Algorithm with an Adaptive Window: Theory and Experiment,” IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 16, no. 9, pp. 920-932, 1994.

[2] A. Fusiello and V. Roberto, “Efficient Stereo with Multiple Windowing,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 858-863, 1997

[3] K.J. Yoon and I.S. Kweon, “Adaptive Support Weight Approach for Stereo Correspondence Search,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 650-656, 2005.

[5] Y. Boykov, O. Veksler, and R. Zabih, “A Variable Window Approach to Early Vision,” IEEE Transactions Pattern Analysis and Machine Intelligence, Vol. 20, No. 12, pp. 1283-1294, 1998.

[11] O. Veksler, “Stereo Correspondence with Compact Windows via Minimum Ratio Cycle,” IEEE Transactions Pattern Analysis and Machine Intelligence, vol. 24, no. 12, pp. 1654-1660, 2002.