A practical approach for detection and classification of traffic signs using Convolutional Neural Networks
| Autor: | Elnaz Jahani Heravi, Hamed Habibi Aghdam, Domenec Puig |
|---|---|
| Přispěvatelé: | Robòtica i Visió Intel.ligents, Enginyeria Informàtica i Matemàtiques, Universitat Rovira i Virgili |
| Rok vydání: | 2016 |
| Předmět: |
Computer science
General Mathematics Ingeniería informática 0921-8890 Stability (learning theory) 02 engineering and technology Convolucions (Matemàtica) Convolutional neural network symbols.namesake Computer engineering Sliding window protocol 0502 economics and business 0202 electrical engineering electronic engineering information engineering Senyalització viària Xarxes neuronals (Informàtica) Simulation 050210 logistics & transportation business.industry 05 social sciences Process (computing) Pattern recognition neural networks Computer Science Applications Benchmarking Enginyeria informàtica Control and Systems Engineering Gaussian noise Benchmark (computing) symbols 020201 artificial intelligence & image processing Artificial intelligence business Software |
| Zdroj: | Robotics and Autonomous Systems |
| ISSN: | 0921-8890 |
| DOI: | 10.1016/j.robot.2016.07.003 |
| Popis: | Automatic detection and classification of traffic signs is an important task in smart and autonomous cars. Convolutional Neural Networks has shown a great success in classification of traffic signs and they have surpassed human performance on a challenging dataset called the German Traffic Sign Benchmark. However, these ConvNets suffer from two important issues. They are not computationally suitable for real-time applications in practice. Moreover, they cannot be used for detecting traffic signs for the same reason. In this paper, we propose a lightweight and accurate ConvNet for detecting traffic signs and explain how to implement the sliding window technique within the ConvNet using dilated convolutions. Then, we further optimize our previously proposed real-time ConvNet for the task of traffic sign classification and make it faster and more accurate. Our experiments on the German Traffic Sign Benchmark datasets show that the detection ConvNet locates the traffic signs with average precision equal to 99.89 % . Using our sliding window implementation, it is possible to process 37.72 high-resolution images per second in a multi-scale fashion and locate traffic signs. Moreover, single ConvNet proposed for the task of classification is able to classify 99.55 % of the test samples, correctly. Finally, our stability analysis reveals that the ConvNet is tolerant against Gaussian noise when ź < 10 . Implementing the scanning window technique on ConvNets using dilated convolutions.Proposing a highly optimized and accurate ConvNet for classification of traffic signs.Analyzing stability of the proposed ConvNet on noisy images. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect