Predicting driver maneuvers by learning holistic features
Authors:
- 1 June 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19310587,p. 719-724
Abstract
In this work, we propose a framework for the recognition and prediction of driver maneuvers by considering holistic cues. With an array of sensors, driver's head, hand, and foot gestures are being captured in a synchronized manner together with lane, surrounding agents, and vehicle parameters. An emphasis is put on real-time algorithms. The cues are processed and fused using a latent-dynamic discriminative framework. As a case study, driver activity recognition and prediction in overtaking situations is performed using a naturalistic, on-road dataset. A consequence of this work would be in development of more effective driver analysis and assistance systems.Keywords
This publication has 15 references indexed in Scilit:
- Fast Feature Pyramids for Object DetectionIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Continuous Head Movement Estimator for Driver Assistance: Issues, Algorithms, and On-Road EvaluationsIEEE Transactions on Intelligent Transportation Systems, 2014
- Driver hand activity analysis in naturalistic driving studies: challenges, algorithms, and experimental studiesJournal of Electronic Imaging, 2013
- Towards automated drive analysis: A multimodal synergistic approach2013
- In-vehicle hand activity recognition using integration of regions2013
- Supervised Descent Method and Its Applications to Face Alignment2013
- Driver intent inference at urban intersections using the intelligent driver model2012
- Modeling and prediction of driver behavior by foot gesture analysisComputer Vision and Image Understanding, 2012
- Lane change intent prediction for driver assistance: On-road design and evaluation2011
- On-road prediction of driver's intent with multimodal sensory cuesIEEE Pervasive Computing, 2011