Human Emotion Based Interior Lighting Control using Machine Learning Techniques

Paper #:
  • 2018-01-1042

Published:
  • 2018-04-03
Abstract:
In recent years, research on Human Computer Interaction (HCI) based on emotion recognition using Behavioral and Physiological signals have attracted immense interest in research circles. Lighting inside the automotive make us feel differently about our driving and how we feel or behave. From the literature, it is observed that ambient lighting makes an impact on the driving experience and it delivers an emotional atmosphere inside the automotive. Driving fatigue can be reduced if the lighting is controlled properly. These days, ambient interior lighting can be considered to be the point of fashion for high end automotives. There are different types of automotive based lighting automation systems available but emotion based control is in early or nascent stages of research. Speech controlled light control systems control the lighting by the recognition of speech of the user and also using facial expressions also, lighting can be controlled. Facial/speech signals consist of both outward physical expression and the inborn emotions. These emotional signals thus exhibited vary from situation to situation and are mostly dependent on the conditions. In this work, we attempted an emotion based interior lighting control. Based on the emotions observed through the Emotion Recognition System (ERS), the lighting can be modified in a predefined fashion. In the proposed ERS system, fives types of emotions are considered, like happy, sad, angry, neutral and disgust. Live image expression and voice data of the driver/passengers are considered as inputs to the system and based on the output from the ERS, interior lighting is controlled. Standard databases are used for training ERS system. The proposed algorithm is tested, and the results demonstrate the approach and the reliability of the method to obtain the solution for lighting control. Machine Learning methods like Convolution Neural Networks are used for classification of features in ERS system.
Access
Now
SAE MOBILUS Subscriber? You may already have access.
Buy
Attention: This item is not yet published. Pre-Order to be notified, via email, when it becomes available.
Select
Price
List
Download
$22.00
Mail
$22.00
Members save up to 36% off list price.
Share
HTML for Linking to Page
Page URL

Related Items

Event
2018-04-10
Technical Paper / Journal Article
2011-05-17
Training / Education
2005-11-15
Training / Education
2009-12-15