mm-wave FMCW Radar Based Object Classification Using Deep Neural Networks

Classification of objects using radars can be useful for a wide range of applications including surveillance systems, autonomous vehicles and collision avoidance systems for drones. This paper presents deep neural networks based object classification technique using a 77-81 GHz frequency modulated continuous wave (FMCW) radar. The data is acquired in a variety of real-world scenarios with various objects including humans and cars at various distances between 5 to 20 meters. The work assesses two types of data sets namely range plots and range-angle heat-maps on which Deep Learning Models are developed and trained. Transfer learning is used to incorporate use of multiple pre-trained models including ResNet34, InceptionV3, GoogleNet2 and a less complex self designed Convolutional Neural Network (CNN) is developed for comparison. The proposed technique uses confusion matrix as the performance metric and achieves an overall average classification accuracy of 94% using range-angle heat maps and 93% using range profile for all classes.