基于BP神经网络的运动目标红外图像仿真

Infrared Images Simulation of Locomotive Object Based on BP Neural Network

针对国内外红外图像仿真中采用热力学方法对物体温度场建模的不足,将基于BP神经网络的机器学习算法应用到物体的红外图像仿真中。根据车辆的红外特性将其表面划分为若干区域,并对所划区域的表面温度进行多次测量,得到训练样本集合,然后运用神经网络建立车辆的温度场模型,并对车辆在设定气候条件下的静止和运动状态进行仿真。根据仿真结果分析,此模型能够根据所设定的气候条件较准确地实时仿真运动目标的红外图像。

As to the shortcomings of the temperature field modeling, based on the thermodynamics method in the infrared images simulation throughout the world, the machine learning algorithm based on the BP neural network was brought into the infrared images simulation. Through frequent testing on the temperature of the vehicle’s surface, which was divided into certain area according to the vehicle’s infrared signature, the training sample assemblies were obtained. Then with the neural network, the temperature field modeling of the vehicle was built and the infrared images of the vehicle in the static state or dynamic state under set weather conditions were simulated. According to the analysis of the results of the simulation, it’s proved that this model can simulate the infrared images of the locomotive object under set weather conditions more accurately in real time.