Road Boundary Estimation for Mobile Robot using Deep Learning and Particle Filter

This research aims to develop a method of estimating road boundaries by deep learning. Existing methods detect boundaries using specifically designed features, and if such features are not available, it is difficult to estimate road boundaries. On the other hand, estimation by deep learning does not require designing features beforehand because it can learn features by itself, and it could estimate boundaries for a more diverse set of roads. In this research, we propose a method of estimating road boundaries by a combination of deep learning and particle filter. By performing a temporal filtering with a particle filter, it is possible to deal with occasional failures in road boundary recognition by deep learning.

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

[2]  Sebastian Ramos,et al.  The Cityscapes Dataset for Semantic Urban Scene Understanding , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[4]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Jun Miura,et al.  On-line road boundary modeling with multiple sensory features, flexible road model, and particle filter , 2011, Robotics Auton. Syst..

[7]  Subhransu Maji,et al.  Semantic contours from inverse detectors , 2011, 2011 International Conference on Computer Vision.

[8]  Jun Miura,et al.  On-line road boundary estimation by switching multiple road models using visual features from a stereo camera , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Ming-Yu Liu,et al.  CASENet: Deep Category-Aware Semantic Edge Detection , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).