對線掃描影像處理使用CUDA加速

CUDA Acceleration on Image Processing for Line-Scan Image

蘇唯誠(Wei-Cheng Su)

指導教授 ： 傅楸善

國立臺灣大學/電機資訊學院/資訊工程學研究所/碩士(2015年)

https://doi.org/10.6342/NTU.2015.02411

摘要

本論文中探討了如何有效率的使用統一計算架構對線掃描影像進行加速處理。統一計算架構是一種在圖形處理器上實現平行化的工具，平行化過的程式可以有更好的執行速度。本論文中，我們比較了各種平行圖形處理的實現並將其技巧應用在工業缺陷檢測上。

關鍵字

線掃瞄影像 ； 統一計算架構(CUDA)

並列摘要

We discuss how to accelerate the line-scan image processing by Compute Unified Device Architecture (CUDA) efficiently in this thesis. CUDA is a parallel implementation on Graphics Processing Unit (GPU). The parallel program could be faster than Central Processing Unit (CPU). In this thesis, we compare the performance of some parallel image processing implementations and apply the technology on Automatic Optical Inspection (AOI).

並列關鍵字

line-scan image ； Compute Unified Device Architecture (CUDA)

參考文獻

[3] K. M. He, J. Sun, and X. O. Tang, “Single Image Haze Removal Using Dark Channel Prior,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 33, No. 12, pp. 2341-2353, 2011.

[4] K. M. He, J. Sun, and X. O. Tang, “Guided Image Filtering,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 31, No. 6, pp. 1397-1409, 2013.

[1] Basler, “raL8192-80km,” http://www.baslerweb.com/en/products/line-scan-cameras/racer/ral8192-80km, 2015.

[2] A. Burnes, “Kepler for Every Gamer: Meet the New GeForce GTX 660 & 650,” http://www.geforce.com/whats-new/articles/geforce-gtx-660-650-launch, 2012.

[5] NVIDIA, “NVIDIA’s Next Generation CUDATM Compute Architecture: FermiTM,” http://www.nvidia.com/content/pdf/fermi_white_papers/nvidia_fermi_compute_architecture_whitepaper.pdf, 2009.