室內畫展導覽系統及參觀路徑追蹤

A Painting Exhibition Guide System and Tour Tracking

貝佳瑄(Chia-Hsuan Pei)

指導教授 ： 陳稔

國立交通大學/資訊學院/資訊學院產業研發碩士班/碩士(2010年)

https://doi.org/10.6842/NCTU.2010.00586

摘要

在本論文中，利用智慧型手機的照相功能，提出了一套基於影像檢索以及相機定位功能的室內畫作導覽系統及參觀路徑追蹤。本系統主要可分為兩部份，第一部份為針對單張獨立影像，當使用者對著感興趣的畫作拍照，系統會將所輸入的影像進行畫作特徵點擷取和特徵點比對，得到初步查詢結果後，再加以驗證查詢結果之正確性，並利用單張影像進行相機校正，估算出相機位置，依據使用者拍攝視角變化，回傳不同的畫作相關資訊解說，以增進參觀民眾對於展出作品的了解；第二部份主要是建立出展場中畫作配置情形，追蹤使用者相機位置與多幅畫作之相對關係，透過歐式座標空間轉換，將原本各自獨立的畫作串聯，呈現一完整的展場畫作空間配置關係，此功能不僅能當作室內導航系統，提示使用者目前在展場中的位置，提供個人化的參觀路徑記錄回顧及建議，對於館內工作人員統計熱門作品或是動線規劃等問題也將有很大的助益，如此的概念提供了有別於傳統導覽方式的全新體驗。

關鍵字

室內導覽 ； 路徑追蹤 ； 影像檢索 ； 相機校正

並列摘要

In this thesis, the proposed system based on image retrieval and camera calibration is used to provide the indoor painting exhibition guide and tour tracking. The system consists of two parts. The first part aims at user’s searching for images of paintings. Users can get the information about paintings of interest by simply inputting a picture of them. The system provides the inquiry service about the input query image. Once the query image identity is verified and the camera pose is estimated, the system returns the pertinent information of the query painting image. The second part is about constructing the location of the exhibited painting through the pose estimation and the recoding of the tour path. This service not only can be an indoor positioning system but also provides useful suggestions for viewing the missing painting exhibition. The proposed system provides a brand new experience in visiting galleries and museums.

並列關鍵字

indoor guide ； tour tracking ； image retrieval ； camera calibration

參考文獻

[1] H. Kato and M. Billinghurst, “Marker tracker and HMD calibration for a video-based augmented reality conferencing system,” in Proceedings of the 2nd International Workshop on Augmented Reality, San Francisco, USA, 1999.

[2] M. Fiala, “ARTag, a fiducial marker system using digital techniques,” in Proceedings of the IEEE International Conference on Computer Vision and Pattern Recognition, vol. 2, 20-25 June 2005, pp. 590-596.

[4] V. Ferrari, T. Tuytelaars, and L.J.V. Gool, “Markerless Augmented Reality with a Real-Time Affine Region Tracker,” in Proc. IEEE/ACM Int’l Symp. Augmented Reality (ISAR ’01), pp. 87-96, 2001.

[5] I. Skrypnyk and D.G. Lowe, “Scene Modelling, Recognition and Tracking with Invariant Image Features,” Proc. IEEE/ACM Int’l Symp. Mixed and Augmented Reality (ISMAR ’04), pp. 110-119, 2004.

[6] T. Lee and T. Höllerer, “Multithreaded hybrid feature tracking for markerless augmented reality,” IEEE Trans. Vis. Comput. Graph., vol. 15, no. 3, pp. 355–68, May–Jun. 2009.