基于背景感知相关滤波跟踪器的目标快速跟踪方法

A Fast Target Tracking Method Based on BACF

图像跟踪算法是弹载图像末制导及光电侦查装备的关键技术,其高效低延时的实时实现可以极大提高光电载荷跟踪的稳定性和精确性。为解决弹载环境受体积、功耗等因素约束下图像末制导跟踪算法的高效性,基于背景感知的相关跟踪算法,提出一种基于数据驱动的多任务分配策略,并针对相关滤波计算是影响算法实时性的关键路径,提出Cache优化的快速傅里叶变换高效实现方法。通过将跟踪算法映射到多核DSP处理器平台上并行实现,相对原处理方法多核处理实时性能整体提升约56.3%。经无人机挂载试验验证表明,该优化方法可以满足空间约束条件下目标跟踪实时性需求,为智能化弹药的工程化应用提供了有力的技术支撑。

Image tracking algorithm is the key technology of imaging terminal guidance of missile and optoelectronic reconnaissance equipment.Its high efficiency and low latency extremely improve the accurate and stable tracking performance.In order to realize the high efficiency of imaging terminal guidance tracking algorithm of missile limited by volume,power,and so on,a data-driven multi-task allocation strategy is proposed based on the background-aware correlation filters(BACF)-based tracking algorithm.And a Cache-optimized fast Fourier transform(FFT)efficient method is proposed,considering that the correlation filtering calculation is key path to reduce the real-time capability of algorithm.The real-time capability of multi-core processing is improved by about 56.3%by mapping the algorithm to multi-core DSP processor platform for parallel processing.It is verified by UAV flight tests that the optimized method can meet the requirements of target tracking real-time capability under space constraints,which provides a strong technical support for engineering applications of smart munitions.