Towards Contactless Elevators with TinyML using CNN-based Person Detection and Keyword Spotting

TL;DR

This paper demonstrates a contactless elevator system using tinyML with CNN-based person detection and keyword spotting, achieving high accuracy and low latency on a microcontroller, promising safer and more efficient elevator operations.

Contribution

The study introduces a novel tinyML-based contactless elevator system utilizing CNNs for person detection and keyword spotting, with optimized accuracy and response time on low-power devices.

Findings

Person detection accuracy of 83.34%

Keyword spotting efficacy of 80.5%

Latency under 5 seconds

Abstract

This study presents a proof of concept for a contactless elevator operation system aimed at minimizing human intervention while enhancing safety, intelligence, and efficiency. A microcontroller-based edge device executing tiny Machine Learning (tinyML) inferences is developed for elevator operation. Using person detection and keyword spotting algorithms, the system offers cost-effective and robust units requiring minimal infrastructural changes. The design incorporates preprocessing steps and quantized convolutional neural networks in a multitenant framework to optimize accuracy and response time. Results show a person detection accuracy of 83.34% and keyword spotting efficacy of 80.5%, with an overall latency under 5 seconds, indicating effectiveness in real-world scenarios. Unlike current high-cost and inconsistent contactless technologies, this system leverages tinyML to provide a cost-effective, reliable, and scalable solution, enhancing user safety and operational efficiency without significant infrastructural changes. The study highlights promising results, though further exploration is needed for scalability and integration with existing systems. The demonstrated energy efficiency, simplicity, and safety benefits suggest that tinyML adoption could revolutionize elevator systems, serving as a model for future technological advancements. This technology could significantly impact public health and convenience in multi-floor buildings by reducing physical contact and improving operational efficiency, particularly relevant in the context of pandemics or hygiene concerns.