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
- EP ID EP93793
- DOI 10.7708/ijtte.2013.3(4).08
- Views 157
- Downloads 0
SPEED-FLOW ANALYSIS FOR INTERRUPTED OVERSATURATED TRAFFIC FLOW WITH HETEROGENEOUS STRUCTURE FOR URBAN ROADS
Speed–flow functions have been developed by several transportation experts to predict accurately the speed of urban road network. HCM Speed-Flow Curve, BPR Curve, MTC Speed-Flow Curve, Akçelik Speed-Flow Curve are some e...
SEARCH STRATEGY FOR NESTED LOGIT TREE STRUCTURE: A CASE STUDY OF RURAL FEEDER SERVICE TO BUS STOP
Several approaches have been suggested by researchers for identifying the best feasible tree structure for Nested Logit (NL) model. This paper demonstrates an experience of applying those approaches while identifying th...
MODELLING OF DAILY ACTIVITY SCHEDULE OF WORKERS USING UNSUPERVISED MACHINE LEARNING TECHNIQUE
Travel demand models are used to replicate the real world travel demand and to predict the future travel demand. A behavioural oriented approach in travel demand analysis is provided by activity based travel demand model...
DETERMINANTS OF PASSENGERS’ CHOICE: A CASE STUDY OF MALLAM AMINU KANO INTERNATIONAL AIRPORT (NIGERIA)
Airports vary in their ability to attract traffic especially when such airports have competitors for air traffic. This study examines choice factors that air travelers consider most as determinants of their choice for an...
CORRELATION BETWEEN THE SHORT SEA SHIPPING CAPABILITY (POTENTIAL) OF A PORT AND PORT MACHINERY FLEXIBILITY
The promotion of environmentally friendly modes of transport, in particular Short Sea Shipping, and their effective integration in multimodal transport chains and networks is one from the group of central objectives of t...