摘要
红外弱小目标的探测与跟踪对运算硬件和算法的性能提出较高的要求。针对传统背景预测算法串行运算耗时较长的问题,以及经典的通用GPU(Graphic Processing Unit)体积与功耗过大难于整合到红外设备中的问题,提出在嵌入式GPU平台NVIDIA Jetson TK1中实现并行分离卷积的方法,利用CUDA(Compute Unified Device Architecture)实时执行背景预测算法,实现了在嵌入式GPU平台上高效的红外背景预测算法。实验结果表明,在保证正确预测背景的前提下,利用小体积、低功耗的嵌入式GPU平台可以将运算性能提高到串行运算的15倍以上。
For infrared small target detection and tracking, it requires very high efficiency of both hardware and algorithm. Since the classic background prediction algorithm is a serial one, which is very time consuming. Considering that common GPUs（Graphic Processing Units） are big in size and too power consuming to be integrated into an infrared device. The implement background prediction algorithm was proposed with separable convolution template method on the embedded GPU platform, named NVIDIA Jetson TK1. Taking advantage of CUDA（Compute Unified Device Architecture） programming language to execute background prediction algorithm in parallel, an operable and high performance result on board was achieved, which gained a 15x speedup comparing to the serial way with a CPU.
出处
《红外与激光工程》
EI
CSCD
北大核心
2015年第9期2615-2621,共7页
Infrared and Laser Engineering
基金
国家自然科学基金(61301290)
