近景攝影測量輔助技能競賽砌磚職類之評分工作

Assessment Methods of Bricklaying Competitions Assisted by Close-range Photogrammetry

湯佳豪(Jia-Hao Tang)

指導教授 ： 徐百輝

國立臺灣大學/工學院/土木工程學研究所/碩士(2019年)

https://doi.org/10.6342/NTU201900502

摘要

技能競賽是技職教育的年度盛事，砌磚職類更是歷史悠久的競賽項目之一。砌磚競賽的評分工作主要採人工量測方式，往往耗時費力，且砌磚作品不易保存。近景攝影測量是一項發展成熟的技術，透過影像密匹配可以生成三維點雲模型，精準地重建三維場景。本研究應用近景攝影測量輔助砌磚競賽之評分工作，透過建立可靠的模型坐標系統及控制資訊，搭配適當的拍攝規劃，採用非量測型相機獲取砌磚作品影像，並以三維建模軟體(ContextCapture)產製高密度點雲資料，最後應用本研究所開發的點雲量測程序，以半自動化的方式在點雲中進行砌磚作品之尺寸、垂直、水平、平整度等量測工作。經由實驗評估及測試所提研究方法之可行性，顯示半自動化的點雲量測確實可以減少人工量測作業，並降低人為因素影響。此外點雲能完整保存砌磚作品且方便於數位平台展示，亦可作為選手提出成績異議時重新審查的依據。本研究應用近景攝影測量技術為砌磚競賽提供一項低成本但具有高品質且提高現有量測作業效率之方案。

關鍵字

技能競賽 ； 砌磚 ； 近景攝影測量 ； 點雲模型

並列摘要

Skills competition is an annual event for vocational education, and bricklaying is one of the long-established competitions. The assessment methods of the bricklaying competition mainly adopts the manual measurement method, which is time consuming and laborious, and the brick walls are not easy to save. Close-range photogrammetry is a well-developed technology that can generate 3D point cloud models and accurately reconstruct 3D surface through dense image matching. This study applies the close-range photogrammetry to assist in the scoring of brickwork competitions. By establishing a reliable model coordinate system with control points, and a adequate mission planning, , the non-metric camera is used to obtain numerous overlapping images of the brickwork. Then the 3D modeling software (ContextCapture) is used to produce the high-density point cloud. Finally the point cloud measurement procedure developed by this study is applied to perform the measurement of the dimension, plumb, level and alignment of the brick walls in the point cloud in a semi-automatic manner. Through the experimental evaluation and testing of the feasibility of the proposed method, it is shown that semi-automated point cloud measurement can indeed reduce manual measurement and reduce the impact of human factors. In addition, the point cloud can completely preserve the brick wall and is convenient for digital platform display, and can also be used as a basis for re-assessment when the competitors raises the objection. This study uses close-range photogrammetry to provide a low-cost but high-quality measurement operations for bricklaying competition with improved efficiency in existing method.

並列關鍵字

Skills competition ； Bricklaying ； Close-range photogrammetry ； Point cloud

參考文獻

Arthur, D. and S. Vassilvitskii, 2007. k-means++: The Advantages of Careful Seeding. Proceedings of the eighteenth annual ACM-SIAM Symposium on Discrete Algorithms. 1027–1035.

Bouguet, 2019. Camera Calibration Toolbox for Matlab. URL：http://www.vision.caltech.edu/bouguetj/calib_doc/ (Last date accessed：7 January 2019)

ContextCapture, 2019. Reality Modeling Software. URL：https://www.bentley.com/en/products/brands/contextcapture (Last date accessed：7 January 2019)

Fischler, Martin A. and Robert C. Bolles, 1981. Random Sample Consensus：A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Communications of the ACM. 24(6)：381-395.

Fryer, John G. and Duane C. Brown, 1986. Lens Distortion for Close-Range Photogrammetry. Photogrammetric Engineering and Remote Sensing, 52：51-58.