Look at Me: Augmented Reality Pedestrian Warning System Using an In-Vehicle Volumetric Head Up Display

Current pedestrian collision warning systems use either auditory alarms or visual symbols to inform drivers. These traditional approaches cannot tell the driver where the detected pedestrians are located, which is critical for the driver to respond appropriately. To address this problem, we introduce a new driver interface taking advantage of a volumetric head-up display (HUD). In our experimental user study, sixteen participants drove a test vehicle in a parking lot while braking for crossing pedestrians using different interface designs on the HUD. Our results showed that spatial information provided by conformal graphics on the HUD resulted in not only better driver performance but also smoother braking behavior as compared to the baseline.

[1]  Bernt Schiele,et al.  Ten Years of Pedestrian Detection, What Have We Learned? , 2014, ECCV Workshops.

[2]  Takashi Sasaki,et al.  Depth Perception Effect of Dynamic Depth Cues for Monocular Head-up Display Realizing Augmented Reality , 2012 .

[3]  Carlo Tomasi.  Pedestrian Detection , 2009, Encyclopedia of Biometrics.

[4]  Alexander Gepperth,et al.  Robust visual pedestrian detection by tight coupling to tracking , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[5]  Yili Liu,et al.  Investigation of Driver Performance With Night Vision and Pedestrian Detection Systems—Part I: Empirical Study on Visual Clutter and Glance Behavior , 2010, IEEE Transactions on Intelligent Transportation Systems.

[6]  Koji Nakamura,et al.  Super-multiview windshield display for driving assistance , 2011 .

[7]  Joseph L. Gabbard,et al.  Behind the Glass: Driver Challenges and Opportunities for AR Automotive Applications , 2014, Proceedings of the IEEE.

[8]  Kay Fitzpatrick,et al.  Driver Braking Performance in Stopping Sight Distance Situations , 2000 .

[9]  Martin P Langham,et al.  Pedestrian conspicuity research: a review , 2003, Ergonomics.

[10]  Gary E. Burnett,et al.  Optical see-through HUDs effect on depth judgments of real world objects , 2015, 2015 IEEE Virtual Reality (VR).

[11]  Daniel R. Tufano,et al.  Automotive HUDs: The Overlooked Safety Issues , 1997, Hum. Factors.

[12]  Barry G. Blundell.  Volumetric 3D Displays , 2012, Handbook of Visual Display Technology.

[13]  Albrecht Schmidt,et al.  Exploring Design Parameters for a 3D Head-Up Display , 2014, PerDis.

[14]  Steven K. Feiner,et al.  Perceptual issues in augmented reality revisited , 2010, 2010 IEEE International Symposium on Mixed and Augmented Reality.

[15]  Victor Ng-Thow-Hing,et al.  A left-turn driving aid using projected oncoming vehicle paths with augmented reality , 2013, AutomotiveUI.

[16]  E. Salas,et al.  Human Factors : The Journal of the Human Factors and Ergonomics Society , 2012 .

[17]  Daniel J Weintraub,et al.  Human factors issues in head-up display design : the book of HUD , 1992 .

[18]  Krister Wolff,et al.  A Review of Near-Collision Driver Behavior Models , 2012, Hum. Factors.

[19]  Mehdi Saffarian,et al.  Enhancing Driver Car-Following Performance with a Distance and Acceleration Display , 2013, IEEE Transactions on Human-Machine Systems.

[20]  Gary Burnett,et al.  Optical see-through head up displays' effect on depth judgments of real world objects , 2015, 2015 IEEE Virtual Reality (VR).

[21]  Richard J. Hanowski,et al.  Human Performance Evaluation of Light Vehicle Brake Assist Systems: Final Report , 2010 .

[22]  Erhardt Barth,et al.  Gaze guidance reduces the number of collisions with pedestrians in a driving simulator , 2012, TIIS.

[23]  Yasuhiro Takaki,et al.  Super multi-view windshield display for long-distance image information presentation. , 2011, Optics express.

[24]  Victor Ng-Thow-Hing,et al.  Personal Navi: Benefits of an Augmented Reality Navigational Aid Using a See-Thru 3D Volumetric HUD , 2014, AutomotiveUI.

[25]  Xuefang Wu,et al.  Exploring head-up augmented reality interfaces for crash warning systems , 2013, AutomotiveUI.