Research on contactless control of elevator based on machine vision

Abstract

Aiming at the problem of cross-infection caused by elevator public buttons during the COVID-19 epidemic, a non-contact elevator button control gesture recognition system based on machine vision is designed. In order to improve the detection speed of gesture recognition, combined with the Spatial Pyramid Pooling (SPP) and replaced the Backbone in YOLOv5 with the lightweight model ShuffleNetV2, an improved YOLOv5_shff algorithm was proposed. After testing, in the task of recognizing gestures, the detection speed of the YOLOv5_shff algorithm is 14% higher than the original model, and the detection accuracy is 0.1% higher than the original model. Taking the improved YOLOv5_shff algorithm as the core, a gesture recognition system that can be applied to elevator button control is designed. The experimental data shows that the gesture recognition accuracy for controlling elevator buttons reaches 99.3%, which can meet the requirements of non-contact control of public elevators. Aiming at the problem of cross-infection caused by elevator public buttons during the COVID-19 epidemic, a non-contact elevator button control gesture recognition system based on machine vision is designed. In order to improve the detection speed of gesture recognition, combined with the Spatial Pyramid Pooling (SPP) and replaced the Backbone in YOLOv5 with the lightweight model ShuffleNetV2, an improved YOLOv5_shff algorithm was proposed. After testing, in the task of recognizing gestures, the detection speed of the YOLOv5_shff algorithm is 14% higher than the original model, and the detection accuracy is 0.1% higher than the original model. Taking the improved YOLOv5_shff algorithm as the core, a gesture recognition system that can be applied to elevator button control is designed. The experimental data shows that the gesture recognition accuracy for controlling elevator buttons reaches 99.3%, which can meet the requirements of non-contact control of public elevators.