Non-contact Gesture Recognition Technology Based on Low Frequency Electric Field

Abstract

At the scene of natural disasters, it is safer and more convenient to remotely control robot completing search and rescue mission by gestures, but currently robot gesture control systems are difficult to maintain high efficiency in complex environmental conditions. Therefore, the paper proposes a non-contact detection system based on low frequency electric field, which can recognize various gestures. The system is not only not susceptible to the surrounding environment (light, sound), but also low cost and low power consumption. Based on the principle of electric field detection, we design the system structure, and perform simulation analysis. Followed, according to the simulation results, the signal processing circuit is designed to collect the detection electrode signals under different gestures. gesture features are extracted from a set of data, and random forest algorithm is used to recognize gestures. The results show that the detection system has a correct recognition rate of more than 90% and a response speed of about 3ms, which satisfies the application requirements.