Driver Verification Using Eye Movements and Blinking

Slides:



Advertisements
Similar presentations
Fingerprint Verification Bhushan D Patil PhD Research Scholar Department of Electrical Engineering Indian Institute of Technology, Bombay Powai, Mumbai.
Advertisements

Face Recognition & Biometric Systems Support Vector Machines (part 2)
Designing a Multi-Biometric System to Fuse Classification Output of Several Pace University Biometric Systems Leigh Anne Clevenger, Laura Davis, Paola.
Secure Unlocking of Mobile Touch Screen Devices by Simple Gestures – You can see it but you can not do it Arjmand Samuel Microsoft Research Muhammad Shahzad.
A Comprehensive Study on Third Order Statistical Features for Image Splicing Detection Xudong Zhao, Shilin Wang, Shenghong Li and Jianhua Li Shanghai Jiao.
Face Recognition & Biometric Systems, 2005/2006 Face recognition process.
Accelerometer-based Transportation Mode Detection on Smartphones
UPM, Faculty of Computer Science & IT, A robust automated attendance system using face recognition techniques PhD proposal; May 2009 Gawed Nagi.
05/06/2005CSIS © M. Gibbons On Evaluating Open Biometric Identification Systems Spring 2005 Michael Gibbons School of Computer Science & Information Systems.
Distributed and Efficient Classifiers for Wireless Audio-Sensor Networks Baljeet Malhotra Ioanis Nikolaidis Mario A. Nascimento University of Alberta Canada.
Viewpoint Tracking for 3D Display Systems A look at the system proposed by Yusuf Bediz, Gözde Bozdağı Akar.
Oral Defense by Sunny Tang 15 Aug 2003
ETSC Best in Europe Conference 2006 Changing Human Machine Interfaces Towards the development of a testing regime Samantha Jamson University of Leeds.
Prognostics of Aircraft Bleed Valves Using a SVM Classification Algorithm Renato de Pádua Moreira Cairo L. Nascimento Jr. Instituto Tecnológico de Aeronáutica.
The Detection of Driver Cognitive Distraction Using Data Mining Methods Presenter: Yulan Liang Department of Mechanical and Industrial Engineering The.
1 Li Li [WSC17] Institute of Integrated Sensor Systems Department of Electrical and Computer Engineering Multi-Sensor Soft-Computing System for Driver.
Cognitive demands of hands-free- phone conversation while driving Professor : Liu Student: Ruby.
An Example of Course Project Face Identification.
An Introduction to Support Vector Machine (SVM) Presenter : Ahey Date : 2007/07/20 The slides are based on lecture notes of Prof. 林智仁 and Daniel Yeung.
Kernel Methods A B M Shawkat Ali 1 2 Data Mining ¤ DM or KDD (Knowledge Discovery in Databases) Extracting previously unknown, valid, and actionable.
Human Activity Recognition Using Accelerometer on Smartphones
1 Webcam Mouse Using Face and Eye Tracking in Various Illumination Environments Yuan-Pin Lin et al. Proceedings of the 2005 IEEE Y.S. Lee.
Signature with Text-Dependent and Text-Independent Speech for Robust Identity Verification B. Ly-Van*, R. Blouet**, S. Renouard** S. Garcia-Salicetti*,
Signature with Text-Dependent and Text-Independent Speech for Robust Identity Verification B. Ly-Van*, R. Blouet**, S. Renouard** S. Garcia-Salicetti*,
Object Recognition in Images Slides originally created by Bernd Heisele.
Spam Detection Ethan Grefe December 13, 2013.
SVMs for (x) Recognition (From Moghaddam / Yang’s “Gender Classification with SVMs”) Brian Whitman.
Histograms of Oriented Gradients for Human Detection(HOG)
An Introduction to Support Vector Machine (SVM)
Counting How Many Words You Read
Secure Unlocking of Mobile Touch Screen Devices by Simple Gestures – You can see it but you can not do it Muhammad Shahzad, Alex X. Liu Michigan State.
Statistical techniques for video analysis and searching chapter Anton Korotygin.
Towards Improved Sensitivity, Specificity, and Timeliness of Syndromic Surveillance Systems Anna L. Buczak, PhD, Linda J. Moniz, PhD, Joseph Lombardo,
Looking for statistical twins
In-Vehicle Driver Distractions & Eye Movements
23rd International Railway Safety Conference
Name Of The College & Dept
Predicting Visual Search Targets via Eye Tracking Data
Digital Image Processing - (monsoon 2003) FINAL PROJECT REPORT
Guillaume-Alexandre Bilodeau
Intelligent IVI with AI
Submitted by the experts of Japan Informal Document: ACSF-06-25
An Artificial Intelligence Approach to Precision Oncology
A Seminar Report On Face Recognition Technology
Improving the Performance of Fingerprint Classification
BLIND AUTHENTICATION: A SECURE CRYPTO-BIOMETRIC VERIFICATION PROTOCOL
Multimodal Biometric Security
Products/Solutions/Expertise of C-DAC Mumbai in Smart City Domain
Agenda Motivation & Goals „Out-of-the-Loop“-Phenomenon MINIMA Concept
When to engage in interaction – and how
Mixture of SVMs for Face Class Modeling
Implementing Boosting and Convolutional Neural Networks For Particle Identification (PID) Khalid Teli .
Biometrics Reg: AMP/HNDIT/F/F/E/2013/067.
Enhancing User identification during Reading by Applying Content-Based Text Analysis to Eye- Movement Patterns Akram Bayat Amir Hossein Bayat Marc.
Vijay Srinivasan Thomas Phan
Object detection as supervised classification
Human Activity Recognition Using Smartphone Sensor Data
Hu Li Moments for Low Resolution Thermal Face Recognition
Interior Camera - A solution to Driver Monitoring Status
Identifying Confusion from Eye-Tracking Data
Enhancing Diagnostic Quality of ECG in Mobile Environment
Multi-Sensor Soft-Computing System for Driver Drowsiness Detection
Non-Intrusive Monitoring of Drowsiness Using Eye Movement and Blinking
[# ] A Game Theoretical Approach to Model Decision Making for Merging Maneuvers at Freeway On-ramps Authors: Kyungwon K. and Hesham A. R. Session.
Machine Learning with Clinical Data
University of Wisconsin - Milwaukee
Modeling IDS using hybrid intelligent systems
Canadian Associate of Road Safety Professionals Conference May 2019
Outlines Introduction & Objectives Methodology & Workflow
Presentation transcript:

Driver Verification Using Eye Movements and Blinking CARSP ACPSER Conference 2018 Driver Verification Using Eye Movements and Blinking Azhar Quddus, Ph.D. Ali Zandi, Ph.D. Laura Prest Felix Comeau

Background https://internationalbanker.com/banking/putting-right-finger-forward-consumer-technologies-encouraging-biometric-banking/ Need to authenticate driver identity from safety point of view: Verification of people operating in-vehicle safety devices, e.g. alcohol interlocks Identification of drivers in connected vehicles Self-driving mode Various technologies available for identification/verification of people Many are not robust against circumvention/spoofing and/or or interfere with the driver activity http://transportationtech.com/qualcomm-unveils-next-gen-connected-vehicle-chipset/ acs-corp.com

Alcohol Countermeasure System Corp. (ACS) Research collaborations with academic sector In-house R & D An international group of companies (beginning in 1970) with a Canadian headquarter Pioneer in alcohol detection technology and road safety Scientific research, product development, and manufacturing

Objective To develop non-intrusive real-time techniques for reliable and practical identification/verification of the driver, using eye movements and blinking.

Methods Simulated Driving Task (SDT) More real-world situation using a driving simulator Two separate sessions (different conditions & time of the day): 10-min control driving (CD) 30-min monotonous driving (MD) 30 subjects (age 40.13±9.69 years; 8 females) Alcohol Countermeasure System Corp., Toronto, Canada Smart Eye Pro system (60 Hz; two IR-based cameras) SmartEye Pro Eye Tracker

Methods Classification: Evaluation: General Gaze Feature Extraction (28 features): 10-sec window with 50% overlap General Gaze Average, median, standard deviation, duration, frequency, percentage, scanpath, velocity, similarity index Fixation Saccade Blinking Classification: Non-linear support vector machine (SVM) with RBF kernel Gradient boosted tree (GBT) with maximum depth of 5 Evaluation: CD alone MD alone Mixed CD and MD

Feature extraction (Left), Training (Middle), Verification (Right) Methods Feature extraction (Left), Training (Middle), Verification (Right) Feature vectors (training set) SVM classifier GBT classifier Eye tracking data timing window (10 sec) Time (testing) Fusion Models Fused score Training Testing

Results CD Session:

Results MD Session:

Results Mixed Sessions:

Conclusion & Discussion A machine learning based approach for driver verification using eye tracking data. A simulated driving task (SDT). The proposed methodology is suitable for practical implementation using simple features extracted in real-time. The verification scheme can be easily implemented on embedded platforms. Next steps: Real driving conditions Larger number of subjects Other AI technologies including deep learning techniques Extension to identification

Thank you! Ali Zandi, Ph.D. aszandi@acs-corp.com Azhar Quddus, Ph.D. aquddus@acs-corp.com Q & A