CNN-based Super-resolution Reconstruction for Traffic Sign Detection

Automatic identification for traffic signs is an important part of intelligent driving and traffic safety. Deep learning has already made a great achievement in traffic sign detection. However, the camera on a car may capture a low resolution and blurry image in certain environments, which make it inaccurate for traffic sign detection. Therefore, we propose a method based on image super-resolution reconstruction for improving the detection rate of traffic signs. Firstly, a low-resolution image is transformed by CNN-based super-resolution network into a high-resolution one. Then, to meet the requirements of on-line processing, we use the generated super-resolution image as input for the detection network with 16 filters in this layer. At last, we separately trained two CNNs for super-resolution reconstruction and traffic sign detection, which reduce the processing time. Experimental results demonstrate that our model can achieve better performance than the existing methods for traffic sign detection.

[1]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

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

[3]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Xuan Tang,et al.  Reconstructible Nonlinear Dimensionality Reduction via Joint Dictionary Learning , 2019, IEEE Transactions on Neural Networks and Learning Systems.

[5]  Hao Shen,et al.  Trace Quotient Meets Sparsity: A Method for Learning Low Dimensional Image Representations , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[6]  Thorsten Joachims,et al.  Making large scale SVM learning practical , 1998 .

[7]  Hao Shen,et al.  Trace Quotient with Sparsity Priors for Learning Low Dimensional Image Representations , 2018, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Johannes Stallkamp,et al.  The German Traffic Sign Recognition Benchmark: A multi-class classification competition , 2011, The 2011 International Joint Conference on Neural Networks.

[9]  David A. McAllester,et al.  A discriminatively trained, multiscale, deformable part model , 2008, 2008 IEEE Conference on Computer Vision and Pattern Recognition.

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

[11]  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).

[12]  Ali Farhadi,et al.  YOLOv3: An Incremental Improvement , 2018, ArXiv.

[13]  Ali Farhadi,et al.  YOLO9000: Better, Faster, Stronger , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Ali Farhadi,et al.  You Only Look Once: Unified, Real-Time Object Detection , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Wei Liu,et al.  SSD: Single Shot MultiBox Detector , 2015, ECCV.

[16]  Tim Salimans,et al.  Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks , 2016, NIPS.

[17]  Ross B. Girshick,et al.  Mask R-CNN , 2017, 1703.06870.

[18]  Ning Xu,et al.  Wide Activation for Efficient and Accurate Image Super-Resolution , 2018, ArXiv.

[19]  Xiaoou Tang,et al.  Learning a Deep Convolutional Network for Image Super-Resolution , 2014, ECCV.

[20]  Kaiming He,et al.  Feature Pyramid Networks for Object Detection , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[21]  Christian Ledig,et al.  Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  Yoshua Bengio,et al.  Generative Adversarial Nets , 2014, NIPS.

[23]  Jianming Zhang,et al.  A Real-Time Chinese Traffic Sign Detection Algorithm Based on Modified YOLOv2 , 2017, Algorithms.

[24]  Daniel Rueckert,et al.  Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[26]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.