在SOPC上实现Mean Shift的改进算法  

Improved Algorithm of Mean Shift Based on SOPC

作　　者：信科[1] 

机构地区：[1]滨州学院信息工程系,滨州256600

出　　处：《单片机与嵌入式系统应用》2015年第10期33-36,共4页Microcontrollers & Embedded Systems

基　　金：滨州学院青年人才创新基金

摘　　要：为了解决Mean Shift算法基于浮点运算计算复杂、难以实时实现及跟踪窗固定的问题,提出一种适合在FPGA上实现的改进的Mean Shift算法。实验结果表明,本文提供的算法能自适应地更新跟踪窗的大小,在4ms内实现对目标的稳定跟踪,程序执行效率比用DSP实现提高5倍左右。Mean Shift algorithm based on floating point arithmetic calculation makes it very difficult to be implemented on real-time system and the tracking window is not adaptive. In order to solve the problems,an improved algorithm of Mean Shift which can be implemented on FPGA is proposed. The experimental results show that the method can adaptively update target windows and track target in 4 ms stably and improve the efficiency of program by 5 times than that of DSP.

关 键 词：Mean SHIFT 硬件加速 实时处理 SOPC 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]