Total Recall: Understanding Traffic Signs using Deep Hierarchical Convolutional Neural Networks

TL;DR

This paper introduces a novel deep hierarchical convolutional neural network architecture that significantly improves traffic sign recognition accuracy across multiple benchmarks, outperforming existing models.

Contribution

The paper presents a new residual convolutional architecture with hierarchical dilated skip connections and a low-memory dilated residual learning technique, achieving state-of-the-art results.

Findings

99.33% accuracy on German traffic sign benchmark

99.17% accuracy on Belgian traffic sign benchmark

Proposed model outperforms existing architectures

Abstract

Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening world-wide. With the arrival of Self-driving cars it has become a staple challenge to solve the automatic recognition of Traffic and Hand-held signs in the major streets. Various machine learning techniques like Random Forest, SVM as well as deep learning models has been proposed for classifying traffic signs. Though they reach state-of-the-art performance on a particular data-set, but fall short of tackling multiple Traffic Sign Recognition benchmarks. In this paper, we propose a novel and one-for-all architecture that aces multiple benchmarks with better overall score than the state-of-the-art architectures. Our model is made of residual convolutional blocks with hierarchical dilated skip connections joined in steps. With this we score 99.33% Accuracy in German sign recognition benchmark and 99.17% Accuracy in Belgian traffic sign classification benchmark. Moreover, we propose a newly devised dilated residual learning representation technique which is very low in both memory and computational complexity.