Lightweight salient foreground detection for embedded smart cameras分析和总结分析和总结.docx

Neah Neah unveils multi fuel/oxidant capability, beats 1000 h operation Available online 24 December 2009. US-based Neah Power Systems has opened up about the ability of its unique silicon-based, micro direct methanol fuel cell technology to utilize multiple fuel solutions. The company also announced that its methanol-powered fuel cell has passed 1000 h of continuous operation in testing. Fuel Cells Bulletin Volume 2009, Issue 12, December 2009, Pages 10-11 Neah Neah Power proves anaerobic DMFC prototype Available online 30 July 2009. US-based Neah Power Systems has unveiled a new type of liquid electrolyte-based direct methanol fuel cell, which does not require air to operate. The repeatable, reliable non-PEM based system has been successfully introduced and demonstrated in sustained operation. Fuel Cells Bulletin Volume 2009, Issue 7, July 2009, Page 1 Neah sells DMFC-powered air-con systems Fuel Cells Bulletin An An embedded smart camera is a stand-alone unit that not only captures images, but also includes a processor, memory and communication interface. Battery-powered, embedded smart cameras introduce many additional challenges since they have very limited resources, such as energy, processing power and memory. Computer vision algorithms running on these camera boards should be light-weight and efficient. Considering the memory requirements of an algorithm and its portability to an embedded processor should be an integral part of the algorithm design in addition to the accuracy requirements. This paper presents a light-weight and efficient background modeling and foreground detection algorithm that is highly robust against lighting variations and non-static backgrounds including scenes with swaying trees, water fountains and rain. Compared to many traditional methods, the memory requirement for the data saved for each pixel is very small in the proposed algorithm. Moreover, the number of memory accesses and instructions are adaptive, and are decreased dependi