Total recall understanding traffic signs using deep hierarchical convolutional neural network

German sign recognition benchmark (GTSRB)   99.33%

Belgian traffic sign classification benchmark    99.17%

 

1. Introduction

In this paper, we propose a noval deep convolutional neural network architecture.It is accompanied by hierarchical structure with customized skip connections in steps. The skip connections are made with dilated convolutions with different filter sizes to increase the receptive field of the feature extractors.

2. Literature review

A  Feature Extracter as classificationtechnique

Total recall understanding traffic signs using deep hierarchical convolutional neural network

B  Orthodox machine learning techniques

C  Deep learning approaches

Total recall understanding traffic signs using deep hierarchical convolutional neural network

Total recall understanding traffic signs using deep hierarchical convolutional neural network

 

3. Proposed methodology

A skip connections in convolutional neural network

Total recall understanding traffic signs using deep hierarchical convolutional neural network

Total recall understanding traffic signs using deep hierarchical convolutional neural network

B Dilated convolutional operation

C Inner residual dilated skip convolution

 

4 Experimentation

Total recall understanding traffic signs using deep hierarchical convolutional neural network

Total recall understanding traffic signs using deep hierarchical convolutional neural network

相关文章:

  • 2021-09-17
  • 2021-07-19
  • 2021-05-11
  • 2021-05-07
  • 2021-11-14
  • 2021-08-25
猜你喜欢
  • 2021-04-13
  • 2021-05-17
  • 2021-04-03
  • 2021-10-19
  • 2021-09-06
  • 2021-11-17
  • 2021-06-21
相关资源
相似解决方案