A full-3D voxel-based dynamic obstacle detection for urban scenario using stereo vision

Autonomous Ground Vehicles designed for dynamic environments require a reliable perception of the real world, in terms of obstacle presence, position and speed. In this paper we present a flexible technique to build, in real time, a dense voxel-based map from a 3D point cloud, able to: (1) discriminate between stationary and moving obstacles; (2) provide an approximation of the detected obstacle's absolute speed using the information of the vehicle's egomotion computed through a visual odometry approach. The point cloud is first sampled into a full 3D map based on voxels to preserve the tridimensional information; egomotion information allows computational efficiency in voxels creation; then voxels are processed using a flood fill approach to segment them into a clusters structure; finally, with the egomotion information, the obtained clusters are labeled as stationary or moving obstacles, and an estimation of their speed is provided. The algorithm runs in real time; it has been tested on one of VisLab's AGVs using a modified SGM-based stereo system as 3D data source.

[1]  Friedrich Fraundorfer,et al.  Visual Odometry Part I: The First 30 Years and Fundamentals , 2022 .

[2]  Uwe Franke,et al.  Towards a Global Optimal Multi-Layer Stixel Representation of Dense 3D Data , 2011, BMVC.

[3]  Hans P. Moravec.  Robot spatial perception by stereoscopic vision and 3D evidence grids , 1996 .

[4]  Heiko Hirschm,et al.  Accurate and Efcient Stereo Processing by Semi-Global Matching and Mutual Information , 2005 .

[5]  Christophe Debain,et al.  Digital Elevation Map estimation by vision-lidar fusion , 2009, 2009 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[6]  Wolfram Burgard,et al.  OctoMap : A Probabilistic , Flexible , and Compact 3 D Map Representation for Robotic Systems , 2010 .

[7]  Alberto Broggi,et al.  Stereo obstacle detection in challenging environments: The VIAC experience , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[8]  Masahiro Fujita,et al.  3D Perception and Environment Map Generation for Humanoid Robot Navigation , 2008, Int. J. Robotics Res..

[9]  Massimo Bertozzi,et al.  GOLD: A Framework for Developing Intelligent-Vehicle Vision Applications , 2008, IEEE Intelligent Systems.

[10]  Uwe Franke,et al.  6D-Vision: Fusion of Stereo and Motion for Robust Environment Perception , 2005, DAGM-Symposium.

[11]  Sergiu Nedevschi,et al.  Processing Dense Stereo Data Using Elevation Maps: Road Surface, Traffic Isle, and Obstacle Detection , 2010, IEEE Transactions on Vehicular Technology.

[12]  Julius Ziegler,et al.  StereoScan: Dense 3d reconstruction in real-time , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[13]  Luca Gatti,et al.  VIAC: An out of ordinary experiment , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).