基于多特征融合的转移粒子滤波红外小目标跟踪算法研究

Research on Infrared Small Target Tracking Algorithm Based on Multi-feature Fusion

针对红外跟踪系统中弱小目标的稳定跟踪需要满足抗干扰、抗遮挡要求,设计了基于目标运动、直方图、分形维数、能量等特征的多特征融合观测概率数学模型;通过对粒子滤波算法的改进,设计了转移受限粒子滤波跟踪算法,同时,将多特征融合观测概率与转移受限粒子相结合应用于红外弱小目标跟踪领域,实现了红外弱小目标稳定跟踪,并具备较好的抗干扰、抗遮挡性能。仿真实验结果验证了相关算法的有效性和实用性。

For the stable tracking of weak and small targets in infrared tracking systems, the requirements of anti-jamming and anti-occlusion are met. A mathematical model of multi-feature fusion observation probability based on the features of target motion, histogram, fractal dimension and energy is designed; Improvement of the algorithm, a transfer-limited particle filter tracking algorithm was designed. At the same time, the combination of multi-feature fusion observation probability and transfer-restricted particles was applied to the field of infrared weak target tracking. The stable tracking of infrared weak targets was achieved, and it had a good resistance. Disturbance, anti-blocking performance. The simulation experiment results verify the effectiveness and practicability of the related algorithms.