Consistent ground-plane mapping: A case study utilizing low-cost sensor measurements and a satellite image

Vision-aided localization systems are often utilized in urban settings to take advantage of structured environment, high availability of unique visual features, as well as complimenting aiding measurements from Global Navigation Satellite System (GNSS). In this paper, we present a case study for roadway texture mapping that combines low-cost sensor measurements that are already available on many production vehicles (e.g. single frequency GPS, wheel odometry, and a forward looking camera) together with a satellite image. The aim of the method presented here is to obtain high resolution texture of the ground plane that is consistent with the low-resolution satellite image through an optimization process that estimates the smooth vehicle trajectory using Maximum-a-Posteriori (MAP). The main benefit of this system comes from the facts that: (1) it utilizes only low-cost sensors and information that are readily available, (2) it can be easily embedded into existing maps. Data and analysis of a drive captured around a block is used in this study.

[1]  Yoshiko Kojima,et al.  Road ortho-image generation based on accurate vehicle trajectory estimation by GPS Doppler , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[2]  C. Lawrence Zitnick,et al.  Structured Forests for Fast Edge Detection , 2013, 2013 IEEE International Conference on Computer Vision.

[3]  Ahmed M. Elgammal,et al.  A framework for global vehicle localization using stereo images and satellite and road maps , 2011, 2011 IEEE International Conference on Computer Vision Workshops (ICCV Workshops).

[4]  Javier Ibanez Guzman,et al.  Accurate visual odometry from a rear parking camera , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[5]  F. Dellaert.  Factor Graphs and GTSAM: A Hands-on Introduction , 2012 .

[6]  Yoshiko Kojima,et al.  Automatic lane-level map generation for advanced driver assistance systems using low-cost sensors , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[7]  Wolfram Burgard,et al.  Large scale graph-based SLAM using aerial images as prior information , 2009, Auton. Robots.

[8]  Christoph Stiller,et al.  Automated map generation from aerial images for precise vehicle localization , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[9]  Simon J. Julier,et al.  Towards the exploitation of prior information in SLAM , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  Jay A. Farrell,et al.  Centimeter-Accuracy Smoothed Vehicle Trajectory Estimation , 2013, IEEE Intelligent Transportation Systems Magazine.

[11]  Gerd Wanielik,et al.  High-accurate vehicle localization using digital maps and coherency images , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[12]  Paul Newman,et al.  Generation and exploitation of local orthographic imagery for road vehicle localisation , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[13]  Frank Dellaert,et al.  Square Root SAM: Simultaneous Localization and Mapping via Square Root Information Smoothing , 2006, Int. J. Robotics Res..

[14]  Andreas Geiger,et al.  Monocular road mosaicing for urban environments , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[15]  Shiyu Song,et al.  Robust Scale Estimation in Real-Time Monocular SFM for Autonomous Driving , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Georg Maier,et al.  Generation of high precision digital maps using circular arc splines , 2012, 2012 IEEE Intelligent Vehicles Symposium.