Object Detection and 3D Estimation via an FMCW Radar Using a Fully Convolutional Network

Typical sensors for object detection include cameras, radars,and LiDARs. In general, different sensors have their unique sensing properties, which brings each type of sensor an advantage overothers when performing object detection. For instance, cameras are able to capture rich texture information of objects in normal light conditions, which makes it possible to identify and distinguish objectsfrom background. Radars attempt to detect objects by continuously transmitting microwaves and then analyzing the received signalsreflected by the objects, which allow the sensors to work regardless of bad weather conditions or dark environments. In recent years, object detection based on cameras has made significant progressby using deep learning framework. The basic idea is to design and train a deep neural network (DNN) by feeding a large number of annotated image samples. The training process enables theDNN to effectively capture informative image features of interested objects via multiple neural layers [2]. As a result, the trained DNN is able to produce impressive performance for visual object detection and other similar tasks such as object classification and segmentation (e.g., Mask R-CNN [3], YOLO [4], and U-Net [5]). Researchon exploiting DNNs for analyzing radar signals is still at an early stage.