CUDA加速建立地理資訊系統 -- 原本要三天才能完成的運算, 能夠用CUDA加速到不到一小時的運算時間即完成

CUDA加速建立地理資訊系統 -- 原本要三天才能完成的運算, 能夠用CUDA加速到不到一小時的運算時間即完成
Speeding Up GIS (Geographic Information Systems)

全球地理資訊系統專家都在注意墨西哥灣嚴重的原油溢出與污染. 地理資訊系統幫助這些專家判斷原油污染面積與位置, 以期快速反應並規劃危機處理方案. 加拿大安大略湖畔的Incogna公司, 推出了一個應用程式, 名叫”GIS Image Analysis On-Demand”(隨選式地理資訊系統圖像分析). 這個應用程式以GPU圖形處理器的高速運算為基礎, 用在需要龐大運算能力的GIS地面分類領域上, 使得原本要三天才能完成的運算, 能夠用CUDA加速到不到一小時的運算時間即完成. 附帶一提的是, Incogna的GIS應用程式是以ICRE(Image Content Recognition Engine)這家公司的圖形運算電腦為核心的雲端計算技術.

GIS experts around the world have been monitoring the huge oil spill in the Gulf of Mexico. GIS technology helps specialists interpret oil slicks in order to assist in response, planning and damage assessment. Incogna GIS of Ontario, Canada has developed an application called "GIS Image Analysis On-Demand," which uses GPU-based image analysis techniques for computationally-intensive tasks such as surface classification. These techniques leverage CUDA to process three days worth of data in less than one hour. The core technology behind Incogna GIS is ICRE (Image Content Recognition Engine), a cloud-computing, GPU-based computer vision system. See: http://gis.incogna.com/.