Mean shift and log-polar transform for road sign detection

Road sign detection is an important function for driver assistance systems. Although it has been studied for many years, it still has some performance limitations. This paper proposes a new method for road sign detection by employing both color and shape cues. The proposed method consists of three steps. First, the initial image is pre-processed using mean shift clustering algorithm. The clustering is carried out based on color information. Second, a random forest classifier is used to segment the clustered image. In the final step, a shape based classification is performed using a log-polar transform and cross correlation technique. The proposed detection method has been tested on both the German traffic sign detection benchmark (GTSDB) and the Swedish traffic signs (STS) datasets, and yields to 93.50 % and 94.22 % on the GTSDB dataset in terms of F-measure and area under curve(AUC), respectively. These results are satisfactory when compared to recent state-of-the-art methods.

[1]  Michael Felsberg,et al.  Using Fourier Descriptors and Spatial Models for Traffic Sign Recognition , 2011, SCIA.

[2]  Young-Woo Seo,et al.  Kernel-based traffic sign tracking to improve highway workzone recognition for reliable autonomous driving , 2013, 16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013).

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

[4]  Guanghui Ren,et al.  Hole-based traffic sign detection method for traffic signs with red rim , 2013, The Visual Computer.

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

[6]  Fatin Zaklouta,et al.  Warning traffic sign recognition using a HOG-based K-d tree , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[7]  Lars Petersson,et al.  Boosting a heterogeneous pool of fast HOG features for pedestrian and sign detection , 2009, 2009 IEEE Intelligent Vehicles Symposium.

[8]  Anjan Gudigar,et al.  A review on automatic detection and recognition of traffic sign , 2014, Multimedia Tools and Applications.

[9]  Saturnino Maldonado-Bascón,et al.  Goal Evaluation of Segmentation Algorithms for Traffic Sign Recognition , 2010, IEEE Transactions on Intelligent Transportation Systems.

[10]  Luc Van Gool,et al.  Multi-view traffic sign detection, recognition, and 3D localisation , 2014, 2009 Workshop on Applications of Computer Vision (WACV).

[11]  Antonio Fernández-Caballero,et al.  An optimization on pictogram identification for the road-sign recognition task using SVMs , 2010, Comput. Vis. Image Underst..

[12]  Luming Zhang,et al.  Integrating 3D structure into traffic scene understanding with RGB-D data , 2015, Neurocomputing.

[13]  Xiaohui Liu,et al.  Real-time traffic sign recognition from video by class-specific discriminative features , 2010, Pattern Recognit..

[14]  Weigong Zhang,et al.  Traffic sign detection and classification for Advanced Driver Assistant Systems , 2015, 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[15]  袁雪,et al.  Traffic Sign Detection via Graph-Based Ranking and Segmentation Algorithms , 2015 .

[16]  Anjan Gudigar,et al.  Multiple thresholding and subspace based approach for detection and recognition of traffic sign , 2017, Multimedia Tools and Applications.

[17]  Jiujun Cheng,et al.  Traffic sign detection based on cascaded convolutional neural networks , 2016, 2016 17th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD).

[18]  Alexandre Bernardino,et al.  A review of log-polar imaging for visual perception in robotics , 2010, Robotics and Autonomous Systems.

[19]  Sebastian Houben,et al.  A single target voting scheme for traffic sign detection , 2011, 2011 IEEE Intelligent Vehicles Symposium (IV).

[20]  Dorin Comaniciu,et al.  Mean shift analysis and applications , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[21]  José Luis Rojo-Álvarez,et al.  Traffic sign segmentation and classification using statistical learning methods , 2015, Neurocomputing.

[22]  Kuei-Chung Chang,et al.  Design of real-time speed limit sign recognition and over-speed warning system on mobile device , 2015, 2015 IEEE International Conference on Consumer Electronics - Taiwan.

[23]  Johannes Stallkamp,et al.  Proposal for IJCNN 2013 competition: The German Traffic Sign Detection Benchmark , 2013 .

[24]  Wen-Jia Kuo,et al.  Two-Stage Road Sign Detection and Recognition , 2007, 2007 IEEE International Conference on Multimedia and Expo.

[25]  Mohamed El Ansari,et al.  Traffic sign detection and recognition based on random forests , 2016, Appl. Soft Comput..

[26]  Hadi Seyedarabi,et al.  Combination of high-level features with low-level features for detection of pedestrian , 2016, Signal Image Video Process..

[27]  Huchuan Lu,et al.  Saliency Detection via Graph-Based Manifold Ranking , 2013, 2013 IEEE Conference on Computer Vision and Pattern Recognition.

[28]  Wenyu Liu,et al.  Traffic sign detection and recognition using fully convolutional network guided proposals , 2016, Neurocomputing.

[29]  Lahcen Koutti,et al.  Fast edge-based stereo matching approach for road applications , 2017, Signal Image Video Process..

[30]  Xin Xu,et al.  Mutual information optimization based dynamic log-polar image registration , 2015 .

[31]  Olac Fuentes,et al.  Color-Based Road Sign Detection and Tracking , 2007, ICIAR.