An intelligent dimming method based on human expression and gesture fusion recognition for smart home

Haoyun Li; Kun Gao; Shuhao Zhang; Shuo Wang; Yunfan Bao; Ruitao Ding

doi:10.1117/12.2663035

4 April 2023 An intelligent dimming method based on human expression and gesture fusion recognition for smart home

Haoyun Li, Kun Gao, Shuhao Zhang, Shuo Wang, Yunfan Bao, Ruitao Ding

Proceedings Volume 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications; 126170G (2023) https://doi.org/10.1117/12.2663035
Event: 9th Symposium on Novel Photoelectronic Detection Technology and Applications (NDTA 2022), 2022, Hefei, China

Abstract

According to the demand of future smart home for lighting experience, an embedded intelligent LED dimming system based on the Raspberry Pi 4B is proposed. The system detects the human proximity distance and captures the gesture movements and other parameters through one ADPS-9960 sensor. An embedded miniature CSI camera OV5647 is used to collect the user's facial expression image data. PWM signal is generated from Raspberry Pi GPIO pin to control the LED illumination. PWM duty cycle range is determined by the fusion results of normalized weighted modulation from the expression type recognized from the facial images and the gesture detected byADPS-9960. Under the basic 3-tier CNN recognition model framework, the expression recognition is further enhanced by introducing the fusion with Face landmarks and HOG features. The experimental results show that the proposed dimming system can adaptively control the luminaire brightness according to the user's psychological state and behavior, and can light off when the person leaves the light, which meets the requirements of modern smart home for user light experience and energy saving.

Citation Download Citation

Haoyun Li, Kun Gao, Shuhao Zhang, Shuo Wang, Yunfan Bao, and Ruitao Ding "An intelligent dimming method based on human expression and gesture fusion recognition for smart home", Proc. SPIE 12617, Ninth Symposium on Novel Photoelectronic Detection Technology and Applications, 126170G (4 April 2023); https://doi.org/10.1117/12.2663035

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available