You Have a Point There: Object Selection Inside an Automobile Using Gaze, Head Pose and Finger Pointing

被引:18
作者
Aftab, Abdul Rafey [1 ,2 ,3 ]
von der Beeck, Michael [2 ]
Feld, Michael [3 ]
机构
[1] Univ Saarland, Saarbrucken, Germany
[2] BMW Grp, Munich, Germany
[3] German Res Ctr Artificial Intelligence DFKI, Saarbrucken, Germany
来源
PROCEEDINGS OF THE 2020 INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, ICMI 2020 | 2020年
关键词
Data fusion; Late fusion; Neural Networks; CNN; RNN; SVR;
D O I
10.1145/3382507.3418836
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Sophisticated user interaction in the automotive industry is a fast emerging topic. Mid-air gestures and speech already have numerous applications for driver-car interaction. Additionally, multimodal approaches are being developed to leverage the use of multiple sensors for added advantages. In this paper, we propose a fast and practical multimodal fusion method based on machine learning for the selection of various control modules in an automotive vehicle. The modalities taken into account are gaze, head pose and finger pointing gesture. Speech is used only as a trigger for fusion. Single modality has previously been used numerous times for recognition of the user's pointing direction. We, however, demonstrate how multiple inputs can be fused together to enhance the recognition performance. Furthermore, we compare different deep neural network architectures against conventional Machine Learning methods, namely Support Vector Regression and Random Forests, and show the enhancements in the pointing direction accuracy using deep learning. The results suggest a great potential for the use of multimodal inputs that can be applied to more use cases in the vehicle.
引用
收藏
页码:595 / 603
页数:9
相关论文
共 33 条
[1]   How Does Eye-Gaze Relate to Gesture Movement in an Automotive Pointing Task? [J].
Ahmad, Bashar I. ;
Langdon, Patrick M. ;
Skrypchuk, Lee ;
Godsill, Simon J. .
ADVANCES IN HUMAN ASPECTS OF TRANSPORTATION, 2018, 597 :423-434
[2]  
[Anonymous], 2019, BMW Natural Interaction Unveiled at MWC 2019
[3]  
[Anonymous], 2014, Measuring cognitive distraction in the automobile II: Assessing in-vehicle voice-based interactive technologies
[4]  
BMW Group, 2019, Press Release
[5]  
Bolt R. A., 1980, Computer Graphics, V14, P262, DOI 10.1145/965105.807503
[6]   Pointing at the HUD: Gesture Interaction Using a Leap Motion [J].
Brand, Daniel ;
Meschtscherjakov, Alexander ;
Buechele, Kevin .
AUTOMOTIVEUI 2016: 8TH INTERNATIONAL CONFERENCE ON AUTOMOTIVE USER INTERFACES AND INTERACTIVE VEHICULAR APPLICATIONS, 2016, :167-172
[7]   Gaze plus Gesture: Expressive, Precise and Targeted Free-Space Interactions [J].
Chatterjee, Ishan ;
Xiao, Robert ;
Harrison, Chris .
ICMI'15: PROCEEDINGS OF THE 2015 ACM INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION, 2015, :131-138
[8]   A review of data fusion models and architectures: Towards engineering guidelines [J].
Esteban, J ;
Starr, A ;
Willetts, R ;
Hannah, P ;
Bryanston-Cross, P .
NEURAL COMPUTING & APPLICATIONS, 2005, 14 (04) :273-281
[9]   Suggesting Gaze-based Selection for Surveillance Applications [J].
Hild, Jutta ;
Peinsipp-Byma, Elisabeth ;
Voit, Michael ;
Beyerer, Juergen .
2019 16TH IEEE INTERNATIONAL CONFERENCE ON ADVANCED VIDEO AND SIGNAL BASED SURVEILLANCE (AVSS), 2019,
[10]  
Jacob R. J. K., 1990, SIGCHI Bulletin, P11