A probabilistic distribution approach for the classification of urban roads in complex environments

Navigation in urban environments has been receiving considerable attention over the past few years, especially for self-driving cars. Road detection for Autonomous Systems, and also for ADAS (Advanced Driving Assistance Systems) remains a major challenging in inner-city scenarios motivated by the high complexity in scene layout with unmarked or weakly marked roads and poor lightning conditions. This paper introduces a novel method that creates a classifier based on a set of probability distribution. The classifier, created using a Joint Boosting algorithm, aims at detecting semantic information in roads. This approach is composed of a set of parallel processes to calculate the superpixel using the Watershed Transform method and the construction of feature maps based on Textons and Disptons. As a result, a set of probability distribution is generated. It will be used as an input to model the week classifier by our Joint Boosting algorithm. The experimental results using the Urban-Kitty benchmark are comparable to the state-of-the-art approaches and can largely improve the effectiveness of the detection in several conditions.

[1]  Teuvo Kohonen,et al.  Self-Organizing Maps, Third Edition , 2001, Springer Series in Information Sciences.

[2]  Antonio Criminisi,et al.  TextonBoost for Image Understanding: Multi-Class Object Recognition and Segmentation by Jointly Modeling Texture, Layout, and Context , 2007, International Journal of Computer Vision.

[3]  Fadi Dornaika,et al.  A New Framework for Stereo Sensor Pose Through Road Segmentation and Registration , 2011, IEEE Transactions on Intelligent Transportation Systems.

[4]  C. Laurgeau,et al.  Vehicle yaw, pitch, roll and 3D lane shape recovery by vision , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[5]  Takeo Kanade,et al.  Vision and Navigation for the Carnegie-Mellon Navlab , 1987 .

[6]  Mathias Perrollaz,et al.  Free Space Estimation for Autonomous Navigation , 2007, ICVS 2007.

[7]  Alberto Broggi,et al.  Obstacle Detection with Stereo Vision for Off-Road Vehicle Navigation , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops.

[8]  Philip H. S. Torr,et al.  Combining Appearance and Structure from Motion Features for Road Scene Understanding , 2009, BMVC.

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

[10]  Antonio Torralba,et al.  Sharing features: efficient boosting procedures for multiclass object detection , 2004, CVPR 2004.

[11]  N. A. Rawashdeh,et al.  Multi-sensor input path planning for an autonomous ground vehicle , 2013, 2013 9th International Symposium on Mechatronics and its Applications (ISMA).

[12]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[13]  N. Hautiere,et al.  Road Segmentation Supervised by an Extended V-Disparity Algorithm for Autonomous Navigation , 2007, 2007 IEEE Intelligent Vehicles Symposium.

[14]  Mathias Perrollaz,et al.  Road Scene Analysis by Stereovision: a Robust and Quasi-Dense Approach , 2006, 2006 9th International Conference on Control, Automation, Robotics and Vision.

[15]  Vladlen Koltun,et al.  Efficient Inference in Fully Connected CRFs with Gaussian Edge Potentials , 2011, NIPS.

[16]  J.M. Alvarez,et al.  Illuminant-invariant model-based road segmentation , 2008, 2008 IEEE Intelligent Vehicles Symposium.

[17]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

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

[19]  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).

[20]  Danilo Alves de Lima,et al.  A disparity map refinement to enhance weakly-textured urban environment data , 2013, 2013 16th International Conference on Advanced Robotics (ICAR).

[21]  Michel Bilodeau,et al.  Road segmentation and obstacle detection by a fast watershed transformation , 1994, Proceedings of the Intelligent Vehicles '94 Symposium.

[22]  Paolo Zani,et al.  Robust monocular lane detection in urban environments , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[23]  Theo Gevers,et al.  Learning photometric invariance from diversified color model ensembles , 2009, CVPR.

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

[25]  Jean-Philippe Tarel,et al.  Real time obstacle detection in stereovision on non flat road geometry through "v-disparity" representation , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[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]  Christopher Rasmussen,et al.  Grouping dominant orientations for ill-structured road following , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[28]  Pushmeet Kohli,et al.  Associative hierarchical CRFs for object class image segmentation , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[29]  Z. Hu,et al.  U-V-disparity: an efficient algorithm for stereovision based scene analysis , 2005, IEEE Proceedings. Intelligent Vehicles Symposium, 2005..

[30]  Patricio A. Vela,et al.  Depth invariant visual servoing , 2011, IEEE Conference on Decision and Control and European Control Conference.