Driver Assistance in Fog Environment Based on Convolutional Neural Networks (CNN)

Driver Assistance Systems (ADAS) are designed to assist the driver and improve road safety. For this, various sensors are generally embedded in vehicles to alert the driver in case of danger present on the road. Unfortunately, the performance of such systems degrades in the presence of adverse weather conditions. In addition, eliminating the fog of a single image captured by a camera is a very difficult and ill-posed phenomenon in Advanced Driver Assistance Systems (ADAS). Recent developments in the field of deep learning have allowed researchers to build relevant models using various tools available. We propose in this paper a new architecture based on fast R-CNN for the detection of objects in fogged images, and a convolutional neuron network (CNN) is designed on the basis of a reformulated model of atmospheric diffusion for fog elimination to restore the sharp image.

[1]  Raanan Fattal.  Single image dehazing , 2008, SIGGRAPH 2008.

[2]  Ketan Tang,et al.  Investigating Haze-Relevant Features in a Learning Framework for Image Dehazing , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[3]  Michael Werman,et al.  Automatic recovery of the atmospheric light in hazy images , 2014, 2014 IEEE International Conference on Computational Photography (ICCP).

[4]  Heidrun Belzner,et al.  Image based fog detection in vehicles , 2012, 2012 IEEE Intelligent Vehicles Symposium.

[5]  Huazhu Fu,et al.  A Cascaded Convolutional Neural Network for Single Image Dehazing , 2018, IEEE Access.

[6]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[7]  Robby T. Tan,et al.  Visibility in bad weather from a single image , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

[8]  E. J. Mccartney,et al.  Optics of the Atmosphere: Scattering by Molecules and Particles , 1977 .

[9]  Ling Shao,et al.  A Fast Single Image Haze Removal Algorithm Using Color Attenuation Prior , 2015, IEEE Transactions on Image Processing.

[10]  Yann LeCun,et al.  Convolutional networks and applications in vision , 2010, Proceedings of 2010 IEEE International Symposium on Circuits and Systems.

[11]  Jian Sun,et al.  Single image haze removal using dark channel prior , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[12]  Je-Chang Jeong,et al.  Visibility Enhancement of Scene Images Degraded by Foggy Weather Conditions with Deep Neural Networks , 2016, J. Sensors.

[13]  Jizheng Xu,et al.  An All-in-One Network for Dehazing and Beyond , 2017, ArXiv.

[14]  Abdelhak Ezzine,et al.  Local Fog Detection Based on Saturation and RGB-Correlation , 2016, 2016 13th International Conference on Computer Graphics, Imaging and Visualization (CGiV).

[15]  Shree K. Nayar,et al.  Vision and the Atmosphere , 2002, International Journal of Computer Vision.

[16]  Xiaochun Cao,et al.  Single Image Dehazing via Multi-scale Convolutional Neural Networks , 2016, ECCV.

[17]  Ross B. Girshick,et al.  Fast R-CNN , 2015, 1504.08083.

[18]  Shree K. Nayar,et al.  Chromatic framework for vision in bad weather , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[19]  Gaofeng Meng,et al.  Efficient Image Dehazing with Boundary Constraint and Contextual Regularization , 2013, 2013 IEEE International Conference on Computer Vision.

[20]  Dacheng Tao,et al.  DehazeNet: An End-to-End System for Single Image Haze Removal , 2016, IEEE Transactions on Image Processing.