改善整合深度感測技術之擴增實境應用

近年來擴增實境技術發展迅速，已成功應用於工程、行銷、娛樂與醫療等不同領域，然而在即時性視覺化內容呈現上，仍有許多難題尚未解決。本研究針對結合深度攝影機（RGB-D Camera）的擴增實境，特別是虛擬產品展示的應用，進行不同面向的效能改善。以 RGB-D 攝影機取得真實場景的三維資訊，根據使用者由場景中選擇的定位參考，可自動進行無標籤定位追蹤初始化，再藉由不同座標系的轉換計算，將虛擬模型準確擺置於實際場景影像中。此外根據即時性的場景深度資料，可正確處理虛擬模型與真實物件的遮蔽關係，產生更真實的虛實互動內容。現行的 RGB-D 攝影機存在隨機雜訊與深度缺失的問題，故提出改善深度資訊品質的計算流程，除可修補缺失之深度資訊點外，亦可降低因連續畫面的差異，所導致的遮蔽邊緣跳動。另一方面，為提高虛擬產品展示的應用價值，發展一項分散式擴增實境系統雛形，結合雲端服務與平行處理技術，實現大量遠端虛擬試穿的使用情境。本研究針對現行擴增實境技術的缺失，提出可行的改善方法，將可有效提升虛實內容的互動性。

關鍵字

RGB-D 攝影機；虛實互動；擴增實境；虛擬試穿

並列摘要

Progressing rapidly in recent years, augmented reality (AR) technologies have successfully found applications in engineering, marketing, entertainment, and medical industries. However, to render high-quality visualization contents in AR remains a challenging task with several technical barriers. Recent development of RGB-D cameras may provide an effective approach to solving those difficulties by capturing real-time depth data of a real scene. This research attempts to improve the effectiveness of product display in AR from multiple perspectives. First, a virtual model can be precisely positioned into a real scene according to the reference geometry selected by users from the scene, without use of markers. Mutual occlusions between real and virtual objects can be precisely estimated using the depth data. This information enables realistic interactions in an AR environment with intuitive rendering of both. In addition, a computational framework is developed to overcome data deterioration induced by random noises and missing pixels in the data captured by RGB-D cameras. The framework effectively reduces the jitter problem occurring along the occlusion boundaries. In addition, we implement a distributed AR system to realize the concept of mass virtual try-on. This system integrates cloud computing and parallel processing technologies to increase the computation efficiency involving in the try-on application. A use scenario of shoes try-on demonstrates the feasibility of the system. This work enhances the realistic extent of interactions between real and virtual contents by integrating RGB-D cameras into AR applications.

並列關鍵字

RGB-D cameras ； Augmented Reality ； Real-Virtual Interactions ； Virtual Try-On

參考文獻

[3] 陳坤淼，陳玲鈴，(2007)，「即時繪圖虛擬原型與實體模型之產品造形真實度認知研究-以汽車造形設計為例」，設計學報，第12卷，第1期。

[9] 鄭珏珉，(2009)，「一套衣物搭配的即時互動系統」，臺灣大學資訊工程學研究所，碩士論文。

[1] Norman, D. A. (2005) "Human-centered design considered harmful," Interactions, Vol. 12, Issue 4, pp. 14-19.

[4] Norman, D. A. (2004) "Introduction to this special section on beauty, goodness, and usability," Human-Computer Interaction, Vol. 19, Issue 4, pp. 311-318.

[5] Chryssolouris, G., Mavrikios, D., and Fragos, D. (2000) "A virtual reality-based experimentation environment for the verification of human-related factors in assembly processes," Robotics and Computer-Integrated Manufacturing, Vol. 16, Issue 4, pp. 267-276.

國際替代計量

改善整合深度感測技術之擴增實境應用

全文下載

主題瀏覽