A Transfer Learning based approach for Pakistani Traffic-sign Recognition; using ConvNets

Several effective methods of traffic-sign recognition have been around for a lot of time now, starting with recognition using conventional Image Processing techniques which are very generic and sluggish. However, majority of state-of-the-art detectors are based on Convolutional Neural Networks (CNNs) which have been evidenced to be de facto leader in image processing and computer vision research over the past decade. This has been made possible by datasets being easily available, organized and maintained with German Traffic Sign Recognition Benchmark being of relevance. CNNs require colossal amounts of data to work well; unfortunately, no traffic-sign dataset exists in Pakistan to enable any detector based on CNNs. This paper presents an approach revolving around transfer learning whereby, a model is pre-trained using German Traffic-sign Dataset and is then fine-tuned over Pakistani Dataset: which is collected across Pakistan and amounts to 359 images. Preprocessing and regularization are used to improve overall performance of the model. The fine-tuned model reached training accuracies of around 41% with minimal overfitting. This presents an encouraging outcome as even with a dataset which is comparatively meager, we have achieved a respectable accuracy, something which can be built upon and bettered by boosting number of images collected.

[1]  Elvin J. Moore,et al.  Traffic Sign Recognition by Color Filtering and Particle Swarm Optimization , 2012 .

[2]  Ronald M. Summers,et al.  Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning , 2016, IEEE Transactions on Medical Imaging.

[3]  Sebastian Thrun,et al.  Learning to Learn , 1998, Springer US.

[4]  L. Bottou,et al.  COMPARISON OF LEARNING ALGORITHMS FOR , 1995 .

[5]  J. Khurshid,et al.  Road Sign Detection and Recognition using Colour Segmentation, Shape Analysis and Template Matching , 2007, 2007 International Conference on Machine Learning and Cybernetics.

[6]  Shun-Feng Su,et al.  Towards self-driving car using convolutional neural network and road lane detector , 2017, 2017 2nd International Conference on Automation, Cognitive Science, Optics, Micro Electro-­Mechanical System, and Information Technology (ICACOMIT).

[7]  Sancho Salcedo-Sanz,et al.  A decision support system for the automatic management of keep-clear signs based on support vector machines and geographic information systems , 2010, Expert Syst. Appl..

[8]  Dean A. Pomerleau,et al.  PANS: a portable navigation platform , 1995, Proceedings of the Intelligent Vehicles '95. Symposium.

[9]  Imran Siddiqi,et al.  Detection and Recognition of Traffic Signs from Road Scene Images , 2014, 2014 12th International Conference on Frontiers of Information Technology.

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

[11]  Artem V. Nikonorov,et al.  Traffic Sign Detection on GPU using Color Shape Regular Expressions , 2016 .

[12]  P. Yakimov,et al.  CNN Design for Real-Time Traffic Sign Recognition , 2017 .

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

[14]  Majid Mirmehdi,et al.  Real-Time Detection and Recognition of Road Traffic Signs , 2012, IEEE Transactions on Intelligent Transportation Systems.

[15]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[16]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[17]  Bodong Liang,et al.  The key technology toward the self-driving car , 2018 .

[18]  Masakazu Matsugu,et al.  Subject independent facial expression recognition with robust face detection using a convolutional neural network , 2003, Neural Networks.

[19]  Baoli Li,et al.  Traffic-Sign Detection and Classification in the Wild , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[20]  Thomas B. Moeslund,et al.  Vision-Based Traffic Sign Detection and Analysis for Intelligent Driver Assistance Systems: Perspectives and Survey , 2012, IEEE Transactions on Intelligent Transportation Systems.

[21]  Yoshua Bengio,et al.  Convolutional networks for images, speech, and time series , 1998 .

[22]  Xiaohui Liu,et al.  Detection, Tracking and Recognition of Traffic Signs from Video Input , 2008, 2008 11th International IEEE Conference on Intelligent Transportation Systems.

[23]  Jianxiong Xiao,et al.  Learning from Maps: Visual Common Sense for Autonomous Driving , 2016, ArXiv.

[24]  Ronald M. Summers,et al.  Detection of Sclerotic Spine Metastases via Random Aggregation of Deep Convolutional Neural Network Classifications , 2014, ArXiv.

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

[26]  Lorien Y. Pratt,et al.  Discriminability-Based Transfer between Neural Networks , 1992, NIPS.

[27]  Mohammad H. Mahoor,et al.  Going deeper in facial expression recognition using deep neural networks , 2015, 2016 IEEE Winter Conference on Applications of Computer Vision (WACV).

[28]  Hilario Gómez Moreno,et al.  Traffic sign shape classification and localization based on the normalized FFT of the signature of blobs and 2D homographies , 2008 .

[29]  Xin Zhang,et al.  End to End Learning for Self-Driving Cars , 2016, ArXiv.

[30]  Yu Qiao,et al.  Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks , 2016, IEEE Signal Processing Letters.

[31]  Christoph H. Lampert,et al.  Learning to detect unseen object classes by between-class attribute transfer , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[32]  Mohammed A. Hannan,et al.  An Automatic Traffic Sign Detection and Recognition System Based on Colour Segmentation, Shape Matching, and SVM , 2015 .