Privacy-Preserving Indoor Localization via Active Scene Illumination

Jinyuan Zhao, Natalia Frumkin, Janusz Konrad, Prakash Ishwar; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2018, pp. 1580-1589

Traditional camera-based indoor localization systems use visual information to resolve the position of an object or person. This approach, however, may not be acceptable in privacy-sensitive scenarios since high-resolution images may reveal room and occupant details to eavesdroppers. In this paper, we address privacy concerns by replacing cameras with a small network of extremely low resolution color sensors. To make the system robust to ambient lighting fluctuations, we modulate an array of LED light sources to actively control the illumination while recording the light received by the sensors. We quantitatively validate the performance of our localization approach through simulations and real testbed experiments. We quantify the impact of sensor noise and changes in ambient illumination on localization accuracy. Finally, we demonstrate the superior performance of localization via active illumination compared to passive illumination where LEDs produce constant light.