透過GPU加速使用色彩濾波器之單張影像深度估計

GPU-Accelerated Single Image Depth Estimation with Color-Filtered Aperture

陳俊傑(Chun-Chieh Chen)

指導教授 ： 曾恕銘

國立臺北科技大學/電資學院/電腦與通訊研究所/碩士(2014年)

https://doi.org/10.6841/NTUT.2014.00208

摘要

目前主要有兩個方法實現深度檢測，分別是多影像深度檢測以及單影像深度檢測。前者由於需要多攝影機，因此擁有較高的硬體成本，不過軟體演算法相對簡單。後者雖然有較低的硬體成本，但軟體演算法卻相當複雜。這個領域近年來有著讓整個系統精簡、可攜，並且精巧化附於傳統攝影機的光學元件的趨勢。在這篇論文裡，我們使用桌上型電腦藉由圖形處理單元來實現單影像深度檢測，並且透過我們進化後的演算法及compute shader 的平行處理技術達到即時應用。這些方法大大地加速了高計算複雜度地單影像深度檢測，從原先幀率 0.003fps(在MATLAB實現)提升至幀率53fps(在compute shader 實現)，幾乎是即時標準幀率30fps的兩倍。在先前的文獻，就我們所知沒有文獻討論單影像深度檢測的優化。

關鍵字

Real time ； 圖形處理單元 ； 平行處理技術 ； Compute shader

並列摘要

There are two major ways to implement depth estimation, multiple image depth estimation and single image depth estimation, respectively. The former has a high hardware cost because it uses multiple cameras but it has a simple software algorithm. Conversely, the latter has a low hardware cost but the software algorithm is complex. One of the recent trends in this field is to make a system compact, or even portable, and to simplify the optical elements to be attached to the conventional camera. In this paper, we present an implementation of depth estimation with a single image using a graphics processing unit (GPU) in a desktop PC, and achieve real-time application via our evolutional algorithm and parallel processing technique, employing a compute shader. The methods greatly accelerate the compute-intensive implementation of depth estimation with a single view image from 0.003 frames per second (fps) (implemented in MATLAB) to 53 fps, which is almost twice the real-time standard of 30 fps. In the previous literature, to the best of our knowledge, no paper discusses the optimization of depth estimation using a single image.

並列關鍵字

Real time ； graphics processing unit ； parallel processing technique ； compute shade MIMO

參考文獻

[1] Rongchun Li, Yong Dou, Jie Zhou, Baofeng Li and Jinbo Xu, “From WiFi to WiMAX: Efficient GPU-based Parameterized Transceiver across Different OFDM Protocols,” KSII Transactions on Internet and Information systems, vol. 7, no. 8, pp. 1911-1932, August, 2013.

[2] J. Kim and S. Hyeon, “Implementation of an SDR System Using Graphics Processing Unit,” IEEE Communications Magazine, vol. 48, no. 3, pp. 156-162, March, 2010.

[7] Y. Bando, B. Chen and T. Nishita, “Extracting Depth and Matte Using a Color-filtered Aperture,” ACM Transactions on Graphics (TOG), vol. 27, no. 5, pp.1–9, December, 2008.

[9] S. H. Lai, C. W. Fu & S. Chang, "A Generalized Depth Estimation Algorithm with a Single Image," IEEE Transactions on Pattern Analysis ans Machine Intelligence (PAMI), vol.14, no. 4, pp. 405-411, April, 1992.

[11] A. Veeraraghavan, R. Raskar, A. Agrawal, A. Mohan and J. Tumblin, “Dappled photography: mask enhanced cameras for heterodyned light fields and coded aperture refocusing,” ACM Transactions on Graphics (TOG), vol. 26, no. 3, pp. 1-12, 2007.