有關RGB-D影像之立體影像生成方法

Stereoscopic Image Generation from RGB-D Images

許峯碩(Feng-Shuo Shiu)

指導教授 ： 杜維昌

義守大學/電機資訊學院/資訊工程學系/碩士(2017年)

摘要

傳統的立體影像生成經常使用多台彩色攝影機拍攝而成，隨著各式各樣深度擷取設備的上市，使用彩色與深度影像成為立體影像生成的另一途徑。在生成過程中，容易因視點遮蔽或反射材質等問題而產生空洞。本研究以RGB-D攝影機取得彩色與深度影像為基礎，探討生成立體影像之技術並對空洞進行填補。首先深度影像經過前處理後，將深度影像與彩色影像採用深度繪圖法，分別生成左右眼影像。接著，將左右眼影像運用改良後的修補方法修復空洞，並利用頭戴顯示器觀看修補後的左右眼影像，以驗證其立體成效。

關鍵字

RGB-D感測裝置 ； 空洞填補 ； 影像修補 ； 深度繪圖法 ； 立體影像

並列摘要

Traditional stereoscopic images are generated using multiple color-cameras. With the popularity of depth capture devices, it becomes a possible way to generate stereoscopic images by use of color and depth images. During the generating process, holes are created because of visual occlusion or reflective material. Based on color and depth images from RGB-D camera, this study explores the technology of generating stereoscopic images and filling the holes. First, use the DIBR algorithm to generate the left-eye and right-eye images respectively, and then propose an improved inpainting method to fill the hole. To verify the actual effect of stereoscopic images, the head-mounted display is used to view the inpainted stereoscopic images.

並列關鍵字

RGB-D sensing device ； holes filling ； image inpainting ； DIBR ； stereoscopic image

參考文獻

[6] 黃怡菁、黃乙白、謝漢萍，3D立體顯示技術，科學發展，第451冊，46-52頁，2010年。

[24] Sang-Beom Lee and Yo-Sung Ho, “Real-time Stereo View Generation Using Kinect Depth Camera,” Asia Pacific Signal Information Processing Association Annual Summit and Conference, 2011.

[1] Safae Elhoufi, Maha Jazouli, Aicha majda, Arsalane Zarghili and Rachid Aalouane, “Automatic Recognition of Facial Expressions using Microsoft Kinect with artificial neural network,” International Conference on Engineering & MIS (ICEMIS), Sep. 2016.

[5] K. Khoshelham and S. O. Elberink, “Accuracy and Resolution of Kinect Depth Data for Indoor Mapping Applications,” Sensors, vol. 12, no. 2, pp. 1437-1454, 2012.

[9] A. Crimibisi, P. Pérez and K. Toyama, “Region Filling and Object Removal by Exemplar-based Image Inpainting,” IEEE Transactions on Image Processing, vol. 13, no. 9, pp. 1200-1212, 2004.