BENCHMARK EVALUATION OF HOG DESCRIPTORS AS FEATURES FOR CLASSIFICATION OF TRAFFIC SIGNS

Journal Title: INTERNATIONAL JOURNAL FOR TRAFFIC AND TRANSPORT ENGINEERING - Year 2013, Vol 3, Issue 4

Abstract

The purpose of this paper is to analyze the performance of the Histograms of Oriented Gradients (HOG) as descriptors for traffic signs recognition. The test dataset consists of speed limit traffic signs because of their high inter-class similarities. HOG features of speed limit signs, which were extracted from different traffic scenes, were computed and a Gentle AdaBoost classifier was invoked to evaluate the different features. The performance of HOG was tested with a dataset consisting of 1727 Swedish speed signs images. Different numbers of HOG features per descriptor, ranging from 36 features up 396 features, were computed for each traffic sign in the benchmark testing. The results show that HOG features perform high classification rate as the Gentle AdaBoost classification rate was 99.42%, and they are suitable to real time traffic sign recognition. However, it is found that changing the number of orientation bins has insignificant effect on the classification rate. In addition to this, HOG descriptors are not robust with respect to sign orientation.

Authors and Affiliations

Hasan Fleyeh, Janina Roch

Keywords

Related Articles

MATERIALS AND TECHNOLOGICAL DEVELOPEMENT OF SCREEN PRINTING IN TRANSPORTATION

Screen printing is a widely used technology in electronic technology. Even though there were many developments in the technology, it is still being under improvement. This paper deals with the automotive industry related...

[sub][/sub]REVERSE LOGISTICS RETAIL LEVEL RETURN

Conducting scientific research regarding reverse logistics systems includes certain difficulties. Developed logistics systems are aimed at analysing reverse logistics issues and tend to continuously detect differences an...

PREVAILING SATURATION FLOW RATE FOR LANE GROUPS IN AN URBAN AREA

This study focused on determining the prevailing Saturation Flow Rate (SFR) for specific lane groups in an urban area: District of Columbia (DC). The lane groups considered were Through (T), shared Through and Right (TR)...

RISK FACTORS AFFECTING FATAL VERSUS NON-FATAL ROAD TRAFFIC ACCIDENTS: THE CASE OF KARS PROVINCE, TURKEY

The aim of this paper is to determine risk factors affecting the fatal versus non-fatal accidents in a rural region of Turkey, during 2008-2012, considering variables associated with the individual, the environment, and...

SELECTION OF OPTIMUM MAINTENANCE AND REHABILITATION STRATEGY FOR MULTILANE HIGHWAYS

Pavements which are left to deteriorate without timely maintenance treatments are likely to require major rehabilitation and reconstruction much sooner than those which are properly maintained. In developing countries li...

Download PDF file
  • EP ID EP93793
  • DOI 10.7708/ijtte.2013.3(4).08
  • Views 195
  • Downloads 0

How To Cite

Hasan Fleyeh, Janina Roch (2013). BENCHMARK EVALUATION OF HOG DESCRIPTORS AS FEATURES FOR CLASSIFICATION OF TRAFFIC SIGNS. INTERNATIONAL JOURNAL FOR TRAFFIC AND TRANSPORT ENGINEERING, 3(4), 448-464. https://europub.co.uk/articles/-A-93793