The generation of complete databases of infrared (IR) data is extremely useful for training human observers and testing automatic pattern recognition algorithms. Field data may be used for realism, but require expensive and time-consuming procedures. Infrared scene simulation methods have emerged as a more economical and efficient alternative for the generation of JR databases. A novel approach to IR target simulation is presented in this paper. Model vehicles at 1:24 scale are used for the simulation of real targets. The temperature profile of the model vehicles is controlled using resistive circuits which are embedded inside the models. The infrared target is recorded using an Inframetrics dual channel IR camera system. Using computer processing we place the recorded JR target in a prerecorded background. The advantages of this approach are: (i) the range and 3-D target aspect can be controlled by the relative position between the camera and model vehicle; (ii) the temperature profile can be controlled by adjusting the power delivered to the resistive circuit; (iii) the IR sensor effects are directly incorporated in the recording process, because the real sensor is used; (iv) the recorded target can be embedded in various types of backgrounds recorded under different weather conditions, times of day etc. The effectiveness of this approach is demonstrated by generating an JR database of three vehicles which is used to train a back propagation neural network. The neural network is capable of classifying vehicle type, vehicle aspect, and relative temperature with a high degree of accuracy.
Department, Program, or Center
Chester F. Carlson Center for Imaging Science (COS)
Infrared Imaging Systems: Design, Analysis, Modeling, and Testing V 2224 (1994) 190-198
RIT – Main Campus