A Unified Hierarchical Convolutional Neural Network for Fine-grained Traffic Sign Detection

The real-world traffic signs are small objects and have hundreds of fine-grained classes, many of them are similar in appearance. This makes difficulties for detection. To solve the problem, this paper presents a novel two-stage fine-grained object detection network which utilizes the hyper-class of the traffic signs. The traffic signs can be divided into several hyper-class according to their appearance and functions, like ‘warning’ and ‘prohibitory’. An object detection network is used to detect the traffic signs with their hyper-class label first, with some adjustments for small objects. Then the fine-grained detection network shares the feature map of the trained hyper-class model and the hyper-class detections are input as proposals. The RoIPooling is conducted with labels. Then the RoIs with labels input to their corresponding hyper-class' classify branch and generate the final results. The experiments in the Tsinghua-Tencent 100K dataset demonstrate that the proposed method outperforms the state-of-the-art methods.

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

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

[3]  Fatin Zaklouta,et al.  Traffic sign classification using K-d trees and Random Forests , 2011, The 2011 International Joint Conference on Neural Networks.

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

[5]  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.

[6]  Zheng Liu,et al.  Efficient Traffic-Sign Recognition with Scale-aware CNN , 2017, BMVC.

[7]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[8]  Faliang Chang,et al.  Occlusion-robust Traffic Sign Detection via Cascaded Colour Cubic Feature , 2016 .

[9]  Wu Liu,et al.  LOCO: Local Context Based Faster R-CNN for Small Traffic Sign Detection , 2018, MMM.

[10]  Changshui Zhang,et al.  Traffic Sign Recognition With Hinge Loss Trained Convolutional Neural Networks , 2014, IEEE Transactions on Intelligent Transportation Systems.

[11]  Kang Kim,et al.  Simultaneous Traffic Sign Detection and Boundary Estimation Using Convolutional Neural Network , 2018, IEEE Transactions on Intelligent Transportation Systems.

[12]  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).

[13]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[14]  许华荣,et al.  Towards Real-Time Traffic Sign Detection and Classification , 2016 .

[15]  Rogério Schmidt Feris,et al.  A Unified Multi-scale Deep Convolutional Neural Network for Fast Object Detection , 2016, ECCV.

[16]  Yanyun Qu,et al.  Traffic-Sign Spotting in the Wild via Deep Features , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[17]  Pietro Perona,et al.  Integral Channel Features , 2009, BMVC.

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

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

[20]  Jiawei Xu,et al.  A saliency-based cascade method for fast traffic sign detection , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).