Robust rear-view ground surface detection with hidden state conditional random field and confidence propagation

We address the problem of detecting rear-view (obstacle free) ground surface using a vehicle production camera. This task is considerably more challenging than general front-view road detection, as the associated challenges widely range from low picture quality, fisheye distortion and large objects, to the absence of useful priors such as vanishing points and road structure. Regarding the challenges, we propose a feature that can simultaneously capture local appearance and context information. In addition, the task suffers from strong appearance variations such as shadows and ground markers. Therefore, we propose a novel conditional random field (CRF) model which includes hidden states indicating confident nodes and propagate their confidence to neighboring nodes. We show that our proposed feature and model can jointly achieve robustness against large objects and shadows/markers, showing excellent detection performance under low quality inputs.

[1]  Charles E. Thorpe,et al.  SCARF: a color vision system that tracks roads and intersections , 1993, IEEE Trans. Robotics Autom..

[2]  R. B. Potts.  Some generalized order-disorder transformations , 1952, Mathematical Proceedings of the Cambridge Philosophical Society.

[3]  Pascal Fua,et al.  SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[4]  Theo Gevers,et al.  Shadow edge detection using geometric and photometric features , 2009, 2009 16th IEEE International Conference on Image Processing (ICIP).

[5]  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.

[6]  Ludek Zalud,et al.  Robust detection of shady and highlighted roads for monocular camera based navigation of UGV , 2011, 2011 IEEE International Conference on Robotics and Automation.

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

[8]  Honggang Zhang,et al.  Adaptive Learning of Region-based pLSA Model for Total Scene Annotation , 2013, ArXiv.

[9]  Oscar C. Au,et al.  Bag of textons for image segmentation via soft clustering and convex shift , 2012, 2012 IEEE Conference on Computer Vision and Pattern Recognition.

[10]  许春景.  Nonparametric Density Estimation on A Graph: Learning Framework, Fast Approximation and Application in Image Segmentation , 2011 .

[11]  Deyu Meng,et al.  Joint recognition / segmentation with cascaded multi-level feature classification and confidence propagation , 2013, 2013 IEEE International Conference on Multimedia and Expo Workshops (ICMEW).

[12]  Qi Wu,et al.  Camera-based clear path detection , 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Jitendra Malik,et al.  Context by region ancestry , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[14]  Fengxia Li,et al.  Discriminative Random Fields for Behavior Modeling , 2009, 2009 WRI World Congress on Computer Science and Information Engineering.

[15]  M. Hebert,et al.  Efficient temporal consistency for streaming video scene analysis , 2013, 2013 IEEE International Conference on Robotics and Automation.

[16]  Stephen Gould,et al.  Decomposing a scene into geometric and semantically consistent regions , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[17]  Honggang Zhang,et al.  Region-based high-level semantics extraction with CEDD , 2010, 2010 2nd IEEE InternationalConference on Network Infrastructure and Digital Content.

[18]  刘健庄,et al.  Automatic Object Segmentation from Large Scale 3D Urban Point Clouds through Manifold Embedded Mode Seeking , 2011 .

[19]  Alexei A. Efros,et al.  Detecting Ground Shadows in Outdoor Consumer Photographs , 2010, ECCV.

[20]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[21]  Martial Hebert,et al.  Stacked Hierarchical Labeling , 2010, ECCV.

[22]  Cheng Lu,et al.  Entropy Minimization for Shadow Removal , 2009, International Journal of Computer Vision.

[23]  Qi Wu,et al.  Strong shadow removal via patch-based shadow edge detection , 2012, 2012 IEEE International Conference on Robotics and Automation.

[24]  Sanja Fidler,et al.  Analyzing Semantic Segmentation Using Hybrid Human-Machine CRFs , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

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

[26]  Martial Hebert,et al.  Discriminative Random Fields , 2006, International Journal of Computer Vision.

[27]  Tao Wu,et al.  Robust road detection from a single image using road shape prior , 2013, 2013 IEEE International Conference on Image Processing.

[28]  Gareth Funka-Lea,et al.  Graph Cuts and Efficient N-D Image Segmentation , 2006, International Journal of Computer Vision.

[29]  Charles E. Thorpe,et al.  UNSCARF-a color vision system for the detection of unstructured roads , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.

[30]  Urbano Nunes,et al.  Trainable classifier-fusion schemes: An application to pedestrian detection , 2009, 2009 12th International IEEE Conference on Intelligent Transportation Systems.

[31]  Qiang Ji,et al.  Image Segmentation with a Unified Graphical Model , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[32]  Qi Wu,et al.  Example-based clear path detection assisted by vanishing point estimation , 2011, 2011 IEEE International Conference on Robotics and Automation.