利用彩色深度攝影機修補深度影像

Depth Image Inpainting with RGB-D Camera

杜介民(Chieh-Min Tu)

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(2015年)

https://doi.org/10.6343/ISU.2015.00388

摘要

隨著微軟公司推出平價Kinect體感設備，立體成像的來源從以往多視點彩色影像的合成，如今發展成彩色與深度影像的結合。但是受限於深度感測儀器所擷取到的深度影像經常會有空洞的情況發生，使得立體視點成效不佳。本研究即以Kinect上的彩色深度攝影機為基礎，探討以物件為基礎的深度影像修補問題。首先採用背景差分、畫面差分與深度閥值之判別方法，作為前景物件與背景影像分離的判別依據。接著，背景空洞利用背景深度影像來修補，前景空洞則採用物件內最佳鄰近點來修補。實驗結果顯示，這樣的策略有助於深度影像上空洞的填補，並可改善物件的輪廓邊緣與影像品質。

關鍵字

深度影像 ； 空洞填補 ； 影像修補

並列摘要

Since Microsoft released the cheap Kinect sensors as a new natural user interface, stereo imaging is made from previous multi-view color image synthesis, to now synthesis of color image and depth image. But the captured depth images may lose some depth values so that stereoscopic effect is often poor in general. This thesis is based on Kinect RGB-D camera to develop an object-based depth inpainting method. Firstly, the background differencing, frame differencing and depth thresholding strategies are used as a basis for segmenting foreground objects from a dynamic background image. Then, the task of hole inpainting is divided into background area and foreground area, in which background area is inpainted by background depth image and foreground area is inpainted by a best-fit neighborhood depth value. Experimental results show that such an inpainting method is helpful to fill holes, and to improve the contour edges and image quality.

並列關鍵字

Kinect ； depth image ； depth inpainting ； image inpainting

參考文獻

[6]M. Bertalmio, G. Sapiro, V. Caselles and C. Ballester, “Image Inpainting,” Proceedings of the 27th Annual Conference on Computer Graphics and Interactive Techniques, pp. 417-424, 2000.

[14]K. Wang, P. An, Z. Y. Zhang, H. Cheng and H. J. Lee, “Fast Inpainting Algorithm for Kinect Depth Map,” Journal of Shanghal University (Natural Science), pp. 454-458, 2012.

[2]M. Stommel, M. Beetz and W. Xu, “Inpainting of Missing Values in the Kinect Sensor’s Depth Maps based on Background Estimates,” IEEE Sensors Journal, vol. 14, no. 4, pp. 1107-1116, 2014.

[3]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.

[5]M. M. Oliveira, B. Brown, R. McKenna and Y. S. Chang, “Fast Digital Image Inpainting,” Proceedings of the International Conference on Visualization, Imaging and Image Processing (VIIP 2001), Marbella, Spain, pp. 261-266, 2001.