论文信息 - Automatic lane change data extraction from car data sequence

Automatic lane change data extraction from car data sequence

An automatic real driving data extraction method for lane change behavior is proposed in this paper which can efficiently detect the accurate start and end timestamp of lane change behaviors from long time driving data sequence. The objective of this work is to efficiently collect lane change data samples for behavior model building or intelligent ADAS system training. The proposed machine leaning based approach shows robustness against confusion from similar driving behaviors and results in highly accurate performance in extracting lane change behavior data segments in a fully automatic way.

[1] K. Ahmed. Modeling drivers' acceleration and lane changing behavior , 1999 .

[2] Tomohiro Yamamura,et al. A Driver Behavior Recognition Method Based on a Driver Model Framework , 2000 .

[3] Alex Pentland,et al. Graphical models for driver behavior recognition in a SmartCar , 2000, Proceedings of the IEEE Intelligent Vehicles Symposium 2000 (Cat. No.00TH8511).

[4] Erwin R. Boer,et al. Toward an Integrated Model of Driver Behavior in Cognitive Architecture , 2001 .

[5] Dario D. Salvucci,et al. The time course of a lane change: Driver control and eye-movement behavior , 2002 .

[6] Suzanne E. Lee,et al. Modeling Slow Lead Vehicle Lane Changing , 2003 .

[7] Benjamin Coifman,et al. Lane Change Maneuver Detection from Probe Vehicle DGPS Data , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[8] Tomohiro Yamamura,et al. Lane-Change Detection Using a Computational Driver Model , 2007, Hum. Factors.

[9] Ioannis Iossifidis,et al. Towards a Driver Model: Preliminary Study of Lane Change Behavior , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[10] Anup Doshi,et al. Lane change intent prediction for driver assistance: On-road design and evaluation , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).