Back to articles
Articles
Volume: 31 | Article ID: art00022
Image
Driver behavior recognition using recurrent neural network in multiple depth cameras environment
Ying-Wei Chuang
Chien-Hao Kuo
Shih-Wei Sun
Pao-Chi Chang
  DOI :  10.2352/ISSN.2470-1173.2019.15.AVM-056  Published Online :  January 2019
Abstract

To improve the driving safety triggered by driver’s behavior recognition in an in-car environment, we propose to use depth cameras mounted in a car to generate behavior models generated by a deep learning algorithm for a driver’s behavior classification. The contribution of this paper is trifold: 1) The proposed multi-view driver behavior recognition system can handle the occlusion problem happened in one of the cameras; 2) Using the recurrent neural network can effectively recognize the continuous time behavior; 3) the average recognition accuracy of proposed systems can achieve 83% and 88%, respectively.

Journal Title : Electronic Imaging
Publisher Name : Society for Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151 USA
Subject Areas :
Views 29
Downloads 1
 DOI 10.2352/ISSN.2470-1173.2019.15.AVM-056
 articleview.views 29
 articleview.downloads 1
  Cite this article 

Ying-Wei Chuang, Chien-Hao Kuo, Shih-Wei Sun, Pao-Chi Chang, "Driver behavior recognition using recurrent neural network in multiple depth cameras environment"  in Proc. IS&T Int’l. Symp. on Electronic Imaging: Autonomous Vehicles and Machines Conference,  2019,  pp 56-1 - 56-7,  https://doi.org/10.2352/ISSN.2470-1173.2019.15.AVM-056

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2019
72010604
Electronic Imaging
2470-1173
Society for Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151 USA
10.2352/ISSN.2470-1173.2019.15.AVM-056
2470-1173(20190113)2019:15L.561;1-
ei_24701173_v2019n15_input/s22.xml
/ist/ei/2019/00002019/00000015/art00022
Articles
Driver behavior recognition using recurrent neural network in multiple depth cameras environment
ChuangYing-Wei
KuoChien-Hao
SunShih-Wei
ChangPao-Chi
13012019
2019
15
56-1
56-7
2019
To improve the driving safety triggered by driver’s behavior recognition in an in-car environment, we propose to use depth cameras mounted in a car to generate behavior models generated by a deep learning algorithm for a driver’s behavior classification. The contribution of this paper is trifold: 1) The proposed multi-view driver behavior recognition system can handle the occlusion problem happened in one of the cameras; 2) Using the recurrent neural network can effectively recognize the continuous time behavior; 3) the average recognition accuracy of proposed systems can achieve 83% and 88%, respectively.
Driver behaviorBehavior RecognitionDeep LearningLSTMPoint CloudSkeleton