Traffic Sign Classification Using Deep Inception Based Convolutional Networks

TL;DR

This paper introduces a novel deep convolutional network with spatial transformer and inception modules for traffic sign classification, achieving state-of-the-art accuracy on GTSRB while addressing issues of parameter explosion and data augmentation.

Contribution

The proposed network combines spatial transformer layers and a modified inception module to improve robustness and accuracy in traffic sign classification, reducing reliance on hand-crafted features and extensive data augmentation.

Findings

Achieved 99.81% accuracy on GTSRB dataset.

Outperformed all previous methods in traffic sign classification.

Enhanced robustness to deformations like translation, rotation, and scaling.

Abstract

In this work, we propose a novel deep network for traffic sign classification that achieves outstanding performance on GTSRB surpassing all previous methods. Our deep network consists of spatial transformer layers and a modified version of inception module specifically designed for capturing local and global features together. This features adoption allows our network to classify precisely intraclass samples even under deformations. Use of spatial transformer layer makes this network more robust to deformations such as translation, rotation, scaling of input images. Unlike existing approaches that are developed with hand-crafted features, multiple deep networks with huge parameters and data augmentations, our method addresses the concern of exploding parameters and augmentations. We have achieved the state-of-the-art performance of 99.81\% on GTSRB dataset.