SimHumalator is an end-to-end simulation tool for generating human micro-Doppler radar data. The radar scatterings are simulated by integrating the animation data of humans with primitive shapes based electromagnetic modelling. SimHumalator uses human animation data that is captured using two motion capture technologies- a marker-based motion capture system called PhaseSpace and a marker-less Microsoft’s Kinect v2 sensor system. The PhaseSpace system capture three-dimensional time varying positions of several markers placed on the live actor’s body parts such as head, torso, arms, and legs using eight infrared cameras as shown in Fig.1. The real advantage of using marker-based technology lies in the fact that it can capture more accurate, more realistic, and complex human motions. A Kinect v2 sensor on the other hand uses infrared depth cameras to track the three-dimensional location of the 25 joints on the human body. It can detect up to 6 humans and is very easy to deploy.

We believe simulator will assist the radar and sensing communities to benchmark future algorithms and generate large volumes of high quality and diverse radar datasets.