Systems and methods to perform sensor fusion with a depth imager and a radar system involve transmitting radio frequency (RF) energy from the radar system to a region and simultaneously emitting light to the region using a light source, Reflected light is received at a depth imager aligned with the light source, and RF reflections are received at the radar system. The reflected light is processed to obtain azimuth, elevation, range, variance in range, and reflectivity to each pixel that makes up the region. Processing the RF reflections provides azimuth, elevation, range, variance in range, velocity, and variance in velocity to a subset of the pixels representing a region of interest. Performing the sensor fusion includes using the azimuth, the elevation, the variance in range, and the reflectivity resulting from the depth imager and the range, the velocity, and the variance in velocity resulting from the radar system.