Recognizing Human Gestures Using Ambient Light
Shakir Mahmood, Raghav H. Venkatnarayan, Muhammad Shahzad · 2020
In this paper, we present LiGeR, a gesture recognition system that leverages ambient light to recognize human gestures in indoor environments. LiGeR is based on the observation that when a user performs a gesture in a room that is lit with light, the amount of light that he/she reflects and blocks changes, resulting in changes in the intensity of light in all parts of the room. The patterns of changes in the intensity of light are different for different gesture. LiGeR first learns these patterns for different gestures by applying machine learning techniques on the training samples of those gestures, and then recognizes the gestures in real-time when the user performs them. In designing LiGeR, we overcame several challenges such as automatic detection of gestures, handling changes in the intensity of light, and handling varying gesture speeds. We implemented LiGeR using cheap commercially available light sensors and Arduino boards and evaluated it in several real-world environments. Our results show that LiGeR achieves an average gesture recognition accuracy of over 95%.