A multi-modal system for road detection and segmentation

Reliable road detection is a key issue for modern Intelligent Vehicles, since it can help to identify the driv-able area as well as boosting other perception functions like object detection. However, real environments present several challenges like illumination changes and varying weather conditions. We propose a multi-modal road detection and segmentation method based on monocular images and HD multi-layer LIDAR data (3D point cloud). This algorithm consists of three stages: extraction of ground points from multilayer LIDAR, transformation of color camera information to an illumination-invariant representation, and lastly the segmentation of the road area. For the first module, the core function is to extract the ground points from LIDAR data. To this end a road boundary detection is performed based on histogram analysis, then a plane estimation using RANSAC, and a ground point extraction according to the point-to-plane distance. In the second module, an image representation of illumination-invariant features is computed simultaneously. Ground points are projected to image plane and then used to compute a road probability map using a Gaussian model. The combination of these modalities improves the robustness of the whole system and reduces the overall computational time, since the first two modules can be run in parallel. Quantitative experiments carried on the public KITTI dataset enhanced by road annotations confirmed the effectiveness of the proposed method.

[1]  Cheng Lu,et al.  On the removal of shadows from images , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Tommy Chang,et al.  Color model-based real-time learning for road following , 2006, 2006 IEEE Intelligent Transportation Systems Conference.

[3]  Bo Zhang,et al.  Color-based road detection in urban traffic scenes , 2004, IEEE Transactions on Intelligent Transportation Systems.

[4]  Sebastian Thrun,et al.  Model Based Vehicle Tracking for Autonomous Driving in Urban Environments , 2008, Robotics: Science and Systems.

[5]  Danilo Alves de Lima,et al.  A 2D/3D Vision Based Approach Applied to Road Detection in Urban Environments , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[6]  Andreas Geiger,et al.  Probabilistic Models for 3D Urban Scene Understanding from Movable Platforms , 2013 .

[7]  Antonio M. López,et al.  Road Detection Based on Illuminant Invariance , 2011, IEEE Transactions on Intelligent Transportation Systems.

[8]  Vincent Frémont,et al.  Fast road detection from color images , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[9]  Joan Serrat,et al.  Vision-based road detection via on-line video registration , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[10]  Alberto Broggi,et al.  Vision-Based Road Detection in Automotive Systems: A Real-Time Expectation-Driven Approach , 1995, J. Artif. Intell. Res..

[11]  Theo Gevers,et al.  3D Scene priors for road detection , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[12]  Junsong Yuan,et al.  Curb detection and tracking using 3D-LIDAR scanner , 2012, 2012 19th IEEE International Conference on Image Processing.

[13]  Luis Magdalena,et al.  A Color Vision-Based Lane Tracking System for Autonomous Driving on Unmarked Roads , 2004, Auton. Robots.

[14]  Sebastian Thrun,et al.  A probabilistic framework for car detection in images using context and scale , 2012, 2012 IEEE International Conference on Robotics and Automation.

[15]  Alberto Broggi,et al.  A morphological model-driven approach to real-time road boundary detection for vision-based automotive systems , 1994, Proceedings of 1994 IEEE Workshop on Applications of Computer Vision.

[16]  Stefano Messelodi,et al.  Switching Models for Vision-based On-Board Road Detection , 2005 .

[17]  Rodriguez Florez,et al.  Contributions by vision systems to multi-sensor object localization and tracking for intelligent vehicles , 2010 .

[18]  V. Cherfaoui,et al.  Tracking objects using a laser scanner in driving situation based on modeling target shape , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[19]  Andreas Geiger,et al.  Vision meets robotics: The KITTI dataset , 2013, Int. J. Robotics Res..

[20]  D. Burschka,et al.  Motion segmentation and scene classification from 3D LIDAR data , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[21]  Theo Gevers,et al.  Vision-based road detection using road models , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[22]  Theo Gevers,et al.  Geographic information for vision-based road detection , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[23]  Sebastian Thrun,et al.  Self-supervised Monocular Road Detection in Desert Terrain , 2006, Robotics: Science and Systems.

[24]  Isabelle Fantoni,et al.  Real-time estimation of drivable image area based on monocular vision , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[25]  Jean Ponce,et al.  General Road Detection From a Single Image , 2010, IEEE Transactions on Image Processing.

[26]  Jannik Fritsch,et al.  A new performance measure and evaluation benchmark for road detection algorithms , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

[27]  Takashi Naito,et al.  Road region estimation using a sequence of monocular images , 2008, 2008 19th International Conference on Pattern Recognition.