What You Can Learn by Staring at a Blank Wall
This provides a passive, non-line-of-sight sensing method for scenarios like surveillance or privacy-aware monitoring, though it is incremental as it builds on existing passive techniques.
The paper tackles the problem of inferring the number of people or their activity from a hidden scene by analyzing indirect illumination changes on a blank wall, achieving an accuracy of approximately 94% for classification tasks in unseen environments and real-time settings.
We present a passive non-line-of-sight method that infers the number of people or activity of a person from the observation of a blank wall in an unknown room. Our technique analyzes complex imperceptible changes in indirect illumination in a video of the wall to reveal a signal that is correlated with motion in the hidden part of a scene. We use this signal to classify between zero, one, or two moving people, or the activity of a person in the hidden scene. We train two convolutional neural networks using data collected from 20 different scenes, and achieve an accuracy of $\approx94\%$ for both tasks in unseen test environments and real-time online settings. Unlike other passive non-line-of-sight methods, the technique does not rely on known occluders or controllable light sources, and generalizes to unknown rooms with no re-calibration. We analyze the generalization and robustness of our method with both real and synthetic data, and study the effect of the scene parameters on the signal quality.