Estimating Motion and size of moving non-line-of-sight objects in cluttered environments

We present a technique for motion and size estimation of non-line-of-sight (NLOS) moving objects in cluttered environments using a time of flight camera and multipath analysis. We exploit relative times of arrival after reflection from a grid of points on a diffuse surface and create a virtual phased-array. By subtracting space-time impulse responses for successive frames, we separate responses of NLOS moving objects from those resulting from the cluttered environment. After reconstructing the line-of-sight scene geometry, we analyze the space of wavefronts using the phased array and solve a constrained least squares problem to recover the NLOS target location. Importantly, we can recover target's motion vector even in presence of uncalibrated time and pose bias common in time of flight systems. In addition, we compute the upper bound on the size of the target by backprojecting the extremas of the time profiles. Ability to track targets inside rooms despite opaque occluders and multipath responses has numerous applications in search and rescue, medicine and defense. We show centimeter accurate results by making appropriate modifications to a time of flight system.