使用彩色暨深度攝影機製作鏡面物體之三維掃描儀

人們可以利用許多種類的攝影器材來為真實物件拍攝其可在電腦中使用的三維模型 (3-D volumetric model),但是沒有任何一種現存可以用來拍攝三維模型的攝影機可以從鏡面反射物體 (specular object) 上得到良好的三維模型,因此我們利用可同時獲取色彩資訊 (color map) 與深度資訊 (depth map) 的彩色暨深度攝影機 (RGB-D camera) 製作針對鏡面實物的三維掃瞄架構。既使彩色暨深度攝影機獲取的深度資訊存在以下兩個主要的問題:雜訊 (noise) 與空洞 (hole),而且這些問題在鏡面實物的拍攝時會更加嚴重,但是我們提出的系統可以整合我們在色彩資訊中得到的視覺線索 (visual cue) 來重建這些被破壞的深度資訊。我們的實驗結果顯示我們提出的系統能夠比其它先前的相關研究重建出更接近於原實物的三維模型。

關鍵字

三維物件掃瞄；圖形處理器；深度攝影機；彩色攝影機；訊號重建；鏡面反射物體；雙邊濾波器；圖形切割演算法

並列摘要

3-D volumetric models for real objects can be obtained through many types of cameras; however, none of them operates well when the scanning target is a specular object. The proposed 3-D scanning system uses a RGB- D camera in which both color values (color map) and depth values (depth map) are acquired simultaneously. Even though the depth maps captured by RGB-D cameras are both noisy and hole-existing and the specular surfaces of objects deteriorate these negative properties, the proposed system integrates visual cues from color maps to rebuild the ruined depth maps. Experimental results show that the rebuilt 3-D models are closer to the original objects than other previously related works did, and even if laser scanners are used.

並列關鍵字

3D scanning ； GPU ； Depth Cameras ； RGB Camera ； Signal Reconstruction ； Specular Objects ； Bilateral Filter ； Graph Cut Algorithm

參考文獻

[1] P. J. Besl and N. D. McKay. A method for registration of 3-d shapes. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 14(2):239–256, Feb. 1992.

[2] Y. Boykov and V. Kolmogorov. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(9):1124–1137, 2004.

[3] Y. Boykov, O. Veksler, and R. Zabih. Fast approximate energy minimization via graph cuts. IEEE Transactions on Pattern Analysis and Machine Intelligence, 23(11):1222–1239, Nov. 2001.

[4] M.CamplaniandL.Salgado.Efficientspatio-temporalholefillingstrategyforkinect depth maps. In SPIE International Conference on 3D Image Processing (3DIP) and Applications, volume 8290, pages 82900E 1–10, 2012.

[9] V. Gandhi, J. Cech, and R. Horaud. High-resolution depth maps based on tof-stereo fusion. In Proceedings of the 2012 IEEE International Conference on Robotics and Automation (ICRA), pages 4742–4749. IEEE, 2012.

國際替代計量

使用彩色暨深度攝影機製作鏡面物體之三維掃描儀

全文下載

主題瀏覽