Yolo V4 for advanced Traffic Sign Recognition with synthetic training data generated by various GAN

Traffic Sign Recognition (TSR) is a crucial component in many automotive applications, such as driver assistance, sign maintenance, and vehicle autonomy. In this paper, we present an efficient approach to training a machine learning-based TSR solution. In our choice of recognition method, we have opted for convolutional neural networks, which have demonstrated best-in-class performance in previous works on TSR. One of the challenges related to training deep neural networks is the requirement for a large amount of training data. To circumvent the tedious process of acquiring and manually labelling real data, we investigate the use of synthetically generated images. Our networks, trained on only synthetic data, are capable of recognising traffic signs in challenging real-world footage. The classification results achieved on the GTSRB benchmark are seen to outperform existing state-of-the-art solutions.

Download Full-text

Transfer Learning Based Traffic Sign Recognition Using Inception-v3 Model

Periodica Polytechnica Transportation Engineering ◽

10.3311/pptr.11480 ◽

2018 ◽

Vol 47 (3) ◽

pp. 242-250 ◽

Cited By ~ 3

Author(s):

Chunmian Lin ◽

Lin Li ◽

Wenting Luo ◽

Kelvin C. P. Wang ◽

Jiangang Guo

Keyword(s):

Transfer Learning ◽

Recognition Performance ◽

Processing Technique ◽

Learning Rate ◽

Training Data ◽

Fine Tuning ◽

Traffic Sign Recognition ◽

Traffic Sign ◽

Sign Recognition ◽

High Level

Traffic sign recognition is critical for advanced driver assistant system and road infrastructure survey. Traditional traffic sign recognition algorithms can't efficiently recognize traffic signs due to its limitation, yet deep learning-based technique requires huge amount of training data before its use, which is time consuming and labor intensive. In this study, transfer learning-based method is introduced for traffic sign recognition and classification, which significantly reduces the amount of training data and alleviates computation expense using Inception-v3 model. In our experiment, Belgium Traffic Sign Database is chosen and augmented by data pre-processing technique. Subsequently the layer-wise features extracted using different convolution and pooling operations are compared and analyzed. Finally transfer learning-based model is repetitively retrained several times with fine-tuning parameters at different learning rate, and excellent reliability and repeatability are observed based on statistical analysis. The results show that transfer learning model can achieve a high-level recognition performance in traffic sign recognition, which is up to 99.18 % of recognition accuracy at 0.05 learning rate (average accuracy of 99.09 %). This study would be beneficial in other traffic infrastructure recognition such as road lane marking and roadside protection facilities, and so on.

Download Full-text

Traffic Sign Recognition based on Synthesised Training Data

Big Data and Cognitive Computing ◽

10.3390/bdcc2030019 ◽

2018 ◽

Vol 2 (3) ◽

pp. 19

Author(s):

Alexandros Stergiou ◽

Grigorios Kalliatakis ◽

Christos Chrysoulas

Keyword(s):

Real World ◽

Road Traffic ◽

Recognition System ◽

Training Data ◽

Traffic Sign Recognition ◽

Traffic Sign ◽

Real World Data ◽

Visual Appearance ◽

Sign Recognition ◽

High Recognition Accuracy

To deal with the richness in visual appearance variation found in real-world data, we propose to synthesise training data capturing these differences for traffic sign recognition. The use of synthetic training data, created from road traffic sign templates, allows overcoming the problems of existing traffic sing recognition databases, which are only subject to specific sets of road signs found explicitly in countries or regions. This approach is used for generating a database of synthesised images depicting traffic signs under different view-light conditions and rotations, in order to simulate the complexity of real-world scenarios. With our synthesised data and a robust end-to-end Convolutional Neural Network (CNN), we propose a data-driven, traffic sign recognition system that can achieve not only high recognition accuracy, but also high computational efficiency in both training and recognition processes.

Download Full-text

Application of Improved LeNet-5 Network in Traffic Sign Recognition

Proceedings of the 3rd International Conference on Video and Image Processing ◽

10.1145/3376067.3376102 ◽

2019 ◽

Author(s):

Wenlong Li ◽

Xingguang Li ◽

Yueya Qin ◽

Wenjun Song ◽

Wei Cui

Keyword(s):

Traffic Sign Recognition ◽

Traffic Sign ◽

Sign Recognition

Download Full-text

Traffic Sign Recognition Using YOLOv3

2020 International Conference Quality Management, Transport and Information Security, Information Technologies (IT&QM&IS) ◽

10.1109/itqmis51053.2020.9322986 ◽

2020 ◽

Author(s):

Anastasiia Perkova ◽

Vitalii Varkentin ◽

Aleksandr Fedorov

Keyword(s):

Traffic Sign Recognition ◽

Traffic Sign ◽

Sign Recognition

Download Full-text

Learning Region-Based Attention Network for Traffic Sign Recognition

Sensors ◽

10.3390/s21030686 ◽

2021 ◽

Vol 21 (3) ◽

pp. 686

Author(s):

Ke Zhou ◽

Yufei Zhan ◽

Dongmei Fu

Keyword(s):

High Resolution ◽

Traffic Sign Recognition ◽

Traffic Sign ◽

Attention Network ◽

Sign Recognition ◽

Learning Region ◽

Robust Network ◽

Traffic Sign Classification

Traffic sign recognition in poor environments has always been a challenge in self-driving. Although a few works have achieved good results in the field of traffic sign recognition, there is currently a lack of traffic sign benchmarks containing many complex factors and a robust network. In this paper, we propose an ice environment traffic sign recognition benchmark (ITSRB) and detection benchmark (ITSDB), marked in the COCO2017 format. The benchmarks include 5806 images with 43,290 traffic sign instances with different climate, light, time, and occlusion conditions. Second, we tested the robustness of the Libra-RCNN and HRNetv2p on the ITSDB compared with Faster-RCNN. The Libra-RCNN performed well and proved that our ITSDB dataset did increase the challenge in this task. Third, we propose an attention network based on high-resolution traffic sign classification (PFANet), and conduct ablation research on the design parallel fusion attention module. Experiments show that our representation reached 93.57% accuracy in ITSRB, and performed as well as the newest and most effective networks in the German traffic sign recognition dataset (GTSRB).

Download Full-text