To compete with online shopping, retailers are constantly looking for ways to improve the display of their products and to track customers to obtain shopping patterns. We propose a general framework that exploits simple color sensors on ceilings to tackle the above-mentioned challenges. Our first contribution is a tunable lighting system that estimates accurately the true color of a product, and then, adjusts automatically the type of lighting to increase the product's appeal. Based on this accurate estimation of color, our second contribution is a system to track people anonymously. Relying solely on the reflections coming from people's clothes, hair and skin, we use color sensors to generate unique optical signatures for individuals. Our evaluation shows that, in spite of the limited information provided by color sensors, the optical signatures are precise enough to differentiate people with very similar appearance except for some minor differences in their clothing.
|Name||Annual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops|
|Conference||17th IEEE International Conference on Sensing, Communication and Networking, SECON 2020|
|Period||22/06/20 → 25/06/20|
- Indoor Tracking
- Tunable lighting
- Visible light