結合十字區塊匹配之半全域匹配法優化作業

The Optimization of Integrating Cross-based Matching into Semi-Global Matching

丁皓偉(Hao-Wei Ting)

指導教授 ： 趙鍵哲

國立臺灣大學/工學院/土木工程學研究所/碩士(2014年)

https://doi.org/10.6342/NTU.2014.03177

摘要

近年來，電腦視覺廣泛運用立體視覺技術於各種領域，其中，藉由計算核線影像對中共軛點的視差值，以重建目標物三維資訊的方法稱為立體匹配演算法，根據執行步驟的細節可分為：局部式、全域式以及半全域匹配法，立體匹配演算法可訴諸於逐像元之匹配，以產製出高密度點雲。
考量匹配效能及品質，本研究採用以半全域匹配法為主的立體匹配演算法來進行高密度點雲產製的任務，然由於此演算法本身對於懲罰參數設定具有高度敏感性，本研究藉由結合十字區塊匹配法以降低前述效應。除此之外，本研究提出的因應策略為作業參數的設定方式，以完備實務操作面並充分支援視差匹配及生產高品質的三維場景。

關鍵字

高密度點雲 ； 立體匹配 ； 十字區塊匹配法 ； 半全域匹配法

並列摘要

In recent years, there is an extensive use of computer vision and stereo vision techniques in various fields. Among them, stereo matching algorithm aims to reconstruct 3D models by calculating conjugate points’ disparity in epipolar image pairs. Based on the detailedness it would involve, the stereo matching can be divided into the following: Local algorithm, Global algorithm and Semi-Global Matching (SGM), when it comes to performing pixel-wise matching, the stereo matching technique can be utilized to generate dense point clouds of the interested scene.
This study employs a SGM based stereo matching algorithm with a good trade-off between runtime and accuracy to generate dense point clouds. Cross-based Matching, a local algorithm is to be integrated into SGM to ease the high sensitivity of parameters chosen in penalty function. In addition, the ranges of parameters needed in carrying out the matching operation have been suggested to support practical as well as quality disparity estimation, and thus a satisfactory 3-D scene reconstruction.

並列關鍵字

Dense Point Clouds ； Stereo Matching ； Cross-based Matching ； Semi-Global Matching

參考文獻

鄭傑文，2007。射影幾何於攝影測量之應用，國立臺灣大學土木工程研究所，碩士論文，175p。

謝幸宜，2011。以自率光束法提升四旋翼UAV航拍影像之定位精度，國立政治大學地政研究所，碩士論文，91p。

姚長昆、陳育菘、楊志弘，2014。以FPGA實現三維深度影像估算的低複雜性方法， 理工研究國際期刊，4(1):149-152。

Gehrke, S., K. Morin, M. Downey, N. Bowhrer, and T. Fuchs, 2010. Semi-global matching: An alternative to LIDAR for DSM generation?, Proceedings of the Canadian Geomatics Conference and Symposium of Commission I, Calgary, Canada, pp. 15-18.

Hermann, S., S. Morales, and R. Klette, 2011. Half-resolution semi-global stereo matching, Proceedings of the IEEE Intelligent Vehicles Symposium, pp. 201–206.