Title:
METHOD FOR CRASH PREVENTION FOR AN AUTOMOTIVE VEHICLE COMPRISING A DRIVING SUPPORT SYSTEM
Document Type and Number:
WIPO Patent Application WO/2019/137913
Kind Code:
A1
Abstract:
The invention relates to a method for crash prevention for an automotive vehicle (1) comprising a driving support system (2) comprising the steps of: - providing features that comprise a) camera-based features of the driver and/or b) driving pattern features, using one or more detectors (3), - modelling the underlying joint probability distribution of the features using a Deep Boltzmann Machine (DBM) as a generative model, wherein the features are used as input for the DBM, - reconstructing the input based on the learning result of the Deep Boltzmann Machine (DBM), and - generating an alert if the reconstruction error exceeds a predefined threshold.
Inventors:
FERNANDEZ JOSEPH (IE)
ENRIGHT CATHERINE (IE)
ENRIGHT CATHERINE (IE)
Application Number:
PCT/EP2019/050341
Publication Date:
July 18, 2019
Filing Date:
January 08, 2019
Export Citation:
Assignee:
CONNAUGHT ELECTRONICS LTD (IE)
International Classes:
B60W30/09; B60K28/06; B60W40/08; B60W50/14; B60W50/16; G06K9/00
Foreign References:
| CN205680247U | 2016-11-09 | |||
| US6070098A | 2000-05-30 | |||
| US20070280505A1 | 2007-12-06 | |||
| US20080069403A1 | 2008-03-20 | |||
| US20140097957A1 | 2014-04-10 |
Other References:
LI PINYI ET AL: "Single-channel EEG-based mental fatigue detection based on deep belief network", 2016 38TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), IEEE, 16 August 2016 (2016-08-16), pages 367 - 370, XP032979170, DOI: 10.1109/EMBC.2016.7590716
LI FENG ET AL: "Deep Models for Engagement Assessment With Scarce Label Information", IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 47, no. 4, 1 August 2017 (2017-08-01), pages 598 - 605, XP011656590, ISSN: 2168-2291, [retrieved on 20170713], DOI: 10.1109/THMS.2016.2608933
FROBA B ET AL: "Face detection with the modified census transform", AUTOMATIC FACE AND GESTURE RECOGNITION, 2004. PROCEEDINGS. SIXTH IEEE INTERNATIONAL CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 17 May 2004 (2004-05-17), pages 91 - 96, XP010949416, ISBN: 978-0-7695-2122-0
LI FENG ET AL: "Deep Models for Engagement Assessment With Scarce Label Information", IEEE TRANSACTIONS ON HUMAN-MACHINE SYSTEMS, IEEE, PISCATAWAY, NJ, USA, vol. 47, no. 4, 1 August 2017 (2017-08-01), pages 598 - 605, XP011656590, ISSN: 2168-2291, [retrieved on 20170713], DOI: 10.1109/THMS.2016.2608933
FROBA B ET AL: "Face detection with the modified census transform", AUTOMATIC FACE AND GESTURE RECOGNITION, 2004. PROCEEDINGS. SIXTH IEEE INTERNATIONAL CONFERENCE ON, IEEE, PISCATAWAY, NJ, USA, 17 May 2004 (2004-05-17), pages 91 - 96, XP010949416, ISBN: 978-0-7695-2122-0
Attorney, Agent or Firm:
JAUREGUI URBAHN, Kristian (DE)
Download PDF: