A Method of MRTD Parameter Measurement Based on CNN Neural Network

摘要

MRTD (Minimum Resolvable Temperature Difference) is an important parameter for comprehensive evaluation oftemperature resolution and spatial resolution of infrared imaging systems. It has become one of the necessary detectionparameters for manufacturers of thermal imaging cameras. The traditional subjective MRTD parameter test method isgradually replaced by objective test methods due to its long test time and high labor cost. At present, the objective testmethod has developed the video MTF method and the photometric camera method, but both methods have theircorresponding limitations. This paper proposes a new objective MRTD parameter test method based on CNN neuralnetwork. Firstly, the four-bar target image used to test the MRTD parameters is analyzed. It is concluded that the processof testing the MRTD parameters is essentially an image classification, which lays a foundation for the learning of CNNneural networks. Then the network model of CNN neural network interpretation of four-bar target image is expounded,and the accuracy of MRTD test results under different network models is analyzed. It was found that the network structureshould not be complicated in the classification process of the four-bar target image. Based on the classic CNN neuralnetwork LeNet model, this paper proposes a CNN neural network suitable for four-bar target image classification problemby optimizing the convolution layer size, changing the activation function and adjusting the network structure. Theexperimental results show that the optimized CNN neural network improves the accuracy and repeatability of the MRTDparameter test.