The accuracy and timing of pedestrian warnings at intersections: The acceptance from drivers and their preferences

The safety of vulnerable road users at traffic intersections is critical. Driver assistance systems can improve safety but have to rely on accurate detection of hazardous situations. Given the complexity of pedestrian movement, detection of pedestrian presence and prediction of their behaviour are not always without error. Drivers' attitude towards such errors is an important issue for the effectiveness of the system. An online questionnaire survey has been carried out to investigate drivers' acceptance of the system under different reliability and accuracy configurations. The results show that safety warnings of pedestrians are generally found to be useful, although false positives and false negatives tend to reduce its pleasantness. The system is found to be most useful for right turn movement at a busy intersection, compared to through movements and quiet intersections. Drivers also find false alarms more acceptable than false negatives. In terms of timing of the warning message, drivers prefer to receive it earlier rather than later.

[1]  Jaap Vreeswijk,et al.  Driving Simulator Study to Support Design of Intersection Safety Application , 2009 .

[2]  Sarah Schmidt,et al.  Pedestrians at the kerb – Recognising the action intentions of humans , 2009 .

[3]  Dick de Waard,et al.  A simple procedure for the assessment of acceptance of advanced transport telematics , 1997 .

[4]  Charles Rodgers,et al.  Design and Testing of a Pedestrian Alert System (PAS) , 2002 .

[5]  Massimo Bertozzi,et al.  Pedestrian detection by means of far-infrared stereo vision , 2007, Comput. Vis. Image Underst..

[6]  Timothy C. Coburn,et al.  Statistical and Econometric Methods for Transportation Data Analysis , 2004, Technometrics.

[7]  Charles Tijus,et al.  Pedestrian crossing decision-making: A situational and behavioral approach , 2009 .

[8]  Michel Bierlaire,et al.  Specification, estimation and validation of a pedestrian walking behaviour model , 2007 .

[9]  Sophie Midenet,et al.  Pedestrian crossing detection based on evidential fusion of video-sensors , 2009 .

[10]  U. Lages,et al.  A multi-sensor approach for the protection of vulnerable traffic participants the PROTECTOR project , 2001, IMTC 2001. Proceedings of the 18th IEEE Instrumentation and Measurement Technology Conference. Rediscovering Measurement in the Age of Informatics (Cat. No.01CH 37188).

[11]  Bart van Arem,et al.  Investigation of user needs for driver assistance: results of an Internet questionnaire , 2005 .

[12]  Dariu Gavrila,et al.  Multi-cue Pedestrian Detection and Tracking from a Moving Vehicle , 2007, International Journal of Computer Vision.

[13]  Marika Hoedemaeker,et al.  Impacts of a Congestion Assistant on driving behaviour and acceptance using a driving simulator , 2007 .

[14]  M. Hamed Analysis of pedestrians’ behavior at pedestrian crossings , 2001 .

[15]  Janne Heikkilä,et al.  A real-time system for monitoring of cyclists and pedestrians , 2004, Image Vis. Comput..

[16]  Liang Zhao,et al.  Stereo- and neural network-based pedestrian detection , 2000, IEEE Trans. Intell. Transp. Syst..

[17]  P. Mathias,et al.  Vulnerable Road User Protection at Intelligent Intersection , 2008 .