摘要
粒子滤波是一种在非线性和非高斯情形下进行状态估计的有效方法。提出一种基于粒子滤波的红外目标跟踪的新算法。阐述了粒子滤波算法的原理,将粒子滤波引入到红外目标跟踪中。考虑到传统的粒子滤波跟踪算法存在计算量大,误码多的缺点,对传统算法进行了改进。对采样粒子进行优化选择,改进了重采样环节。实验结果表明,改进算法较传统粒子滤波算法能更准确,更有效的跟踪红外目标。
Particle filter is an effective method under the condition of non - linear and non - gaussian, This paper presents a particle filter - based algorithm for IR target - tracking. Illustrated is the theory of the particle filter which is introduced to IR target - tracking, An improvement is made of the traditional particle fil- ter which suffers massive computation and frequent error - codes. Sampling particles are optimized and selected, and the re - sampling phase is improved. The results show that the improved algorithm can track the IR target with better precision and higher efficiency.
出处
《电子科技》
2007年第11期22-25,34,共5页
Electronic Science and Technology
