Recognizing Hand Gestures Using Solar Cells

We design a system, Solar Gest, which can recognize hand gestures near a solar-powered device by analyzing the patterns of the photocurrent. Solar Gest is based on the observation that each gesture interferes with incident light rays on the solar panel in a unique way, leaving its discernible signature in harvested photocurrent. Using solar energy harvesting laws, we develop a model to optimize design and usage of Solar Gest. To further improve the robustness of Solar Gest under non-deterministic operating conditions, we combine dynamic time warping with Z-score transformation in a signal processing pipeline to pre-process each gesture waveform before it is analyzed for classification. We evaluate Solar Gest with both conventional opaque solar cells as well as emerging see-through transparent cells. Our experiments demonstrate that Solar Gest achieves 99% for six gestures with a single cell and 95% for fifteen gesture with a 2x2 solar cell array. The power measuement study suggests that Solar Gest consume 44% less power compared to light sensor based systems.

Automated summary

We present Solar Gest, a system that utilizes photocurrent patterns to recognize hand gestures near a solar-powered device. By exploiting the unique interference caused by each gesture on the incident light rays, Solar Gest can identify the gestures with high accuracy. To enhance its robustness, we employ dynamic time warping and Z-score transformation for signal preprocessing. Evaluation results show that Solar Gest achieves high recognition rates for different solar cell types and consumes significantly less power compared to light sensor based systems.