Open Access
Research Article
Smart Elevator Control System Based on Human Hand Gesture Recognition
1 School of Automation, Guangdong University of Technology, Guangzhou 510006, China
2 Department of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China
3 Intelligent Robotics Lab, Hong Kong University of Science and Technology, Hong Kong
Keywords
computer vision; hand gesture recognition; convolutional neural network; human-computer interaction; smart elevator
Abstract
Abstract—The rapid development of computer vision and deep learning has enabled robust hand gesture recognition for human-computer interaction. This paper proposes a smart elevator control system that interprets user hand gestures to invoke floor commands without physical contact. A convolutional neural network is trained on a custom gesture dataset and deployed on an embedded platform with real-time inference. Experimental results demonstrate high recognition accuracy and responsive elevator control in laboratory and field tests.
