Monocular road segmentation using slow feature analysis

In this paper a novel approach for road detection with a monocular camera is introduced. We propose a two step approach, combining a patch-based segmentation with additional boundary detection. We use Slow Feature Analysis (SFA) which leads to improved appearance descriptors for road and non-road parts on patch level. From the slow features a low order feature set is formed which is used together with color and Walsh Hadamard texture features to train a patch-based GentleBoost classifier. This allows extracting areas from the image that correspond to the road with a certain confidence. Typically the border regions between road and non-road have the highest classification error rates, because the appearance is hard to distinguish on the patch level. Therefore we propose a post-processing step with a specialized classifier applied to the boundary region of the image to improve the segmentation results. In order to evaluate the quality of road segmentation we propose an application-based quality measurement applying an inverse perspective mapping on the image to obtain a Birds Eye View (BEV). The advantage of this approach is that the important distant parts and boundaries of the road in the real world, which are only a low fraction in the perspective image, can be assessed in this metric measure significantly better than on the pixel level. In addition, we estimate the driving corridor width and boundary error, because for Advanced Driver Assistant Systems (ADAS) metric information is needed. For all evaluations in different road and weather conditions, our system shows an improved performance of the two step approach compared to the basic segmentation.

[1]  Amnon Shashua,et al.  Off-road Path Following using Region Classification and Geometric Projection Constraints , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[2]  Guoying Zhang,et al.  A Feature Selection Algorithm Based on Boosting for Road Detection , 2008, 2008 Fifth International Conference on Fuzzy Systems and Knowledge Discovery.

[3]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1997, EuroCOLT.

[4]  Bodo Rosenhahn,et al.  Fusion of clothoid segments for a more accurate and updated prediction of the road geometry , 2010, 13th International IEEE Conference on Intelligent Transportation Systems.

[5]  Terrence J. Sejnowski,et al.  Slow Feature Analysis: Unsupervised Learning of Invariances , 2002, Neural Computation.

[6]  Stefan Lüke,et al.  Map based road boundary estimation , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[7]  Jannik Fritsch,et al.  Adaptive multi-cue fusion for robust detection of unmarked inner-city streets , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[8]  A. López,et al.  Novel Index for Objective Evaluation of Road Detection Algorithms , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[9]  J. Little,et al.  Inverse perspective mapping simplifies optical flow computation and obstacle detection , 2004, Biological Cybernetics.

[10]  Niko Wilbert,et al.  Invariant Object Recognition with Slow Feature Analysis , 2008, ICANN.

[11]  Chunzhao Guo,et al.  Drivable road region detection using homography estimation and efficient belief propagation with coordinate descent optimization , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[12]  Yoav Freund,et al.  A decision-theoretic generalization of on-line learning and an application to boosting , 1995, EuroCOLT.

[13]  Jannik Fritsch,et al.  Towards a task dependent representation generation for scene analysis , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[14]  Wolfgang Förstner,et al.  Curb reconstruction using Conditional Random Fields , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[15]  Bernt Schiele,et al.  A Dynamic Conditional Random Field Model for Joint Labeling of Object and Scene Classes , 2008, ECCV.

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

[17]  A. Polychronopoulos,et al.  Accurate Road Geometry Estimation for a Safe Speed Application , 2006, 2006 IEEE Intelligent Vehicles Symposium.

[18]  Klaus C. J. Dietmayer,et al.  Road course estimation in occupancy grids , 2010, 2010 IEEE Intelligent Vehicles Symposium.

[19]  C. V. Jawahar,et al.  Scene Text Recognition using Higher Order Language Priors , 2009, BMVC.