Research Papers

Automated Classification Based on Video Data at Intersections with Heavy Pedestrian and Bicycle Traffic: Methodology and Application

Filename 6C-Zangenehpour_FP_Automated-Classification-in-Traffic-Video-at-Intersections.pdf
Filesize 689 KB
Version 1
Date added June 16, 2014
Downloaded 11 times/fois
Category 2014 CMRSC XXIV Vancouver
Tags Research and Evaluation, Session 6C, Student Paper Award Winner
Author/Auteur Sohail Zangenehpour, Luis F. Miranda-Moreno, Nicolas Saunier
Stream/Volet Research and Evaluation
Award/Prix Étudiant 2 Student

Slidedeck Presentation

6C Zangenehpour Automated Classification in Traffic Video at Intersections

Abstract

Pedestrians and cyclists are amongst the most vulnerable road users. Pedestrian and cyclist
collisions involving motor-vehicles result in high injury and fatality rates for these two modes.
Data for pedestrian and cyclist activity at intersections such as volumes, speeds, and space-time
trajectories are essential in the field of transportation in general, and road safety in particular.
However, automated data collection for these two road user types remains a challenge. Due to
the constant change of orientation and appearance of pedestrians and cyclists, detecting and
tracking them using video sensors is a difficult task. This paper presents a method based on
Histogram of Oriented Gradients to extract features of an image box containing the tracked
object and Support Vector Machine to classify moving objects in crowded traffic scenes. Moving
objects are classified into three categories: pedestrians, cyclists, and motor vehicles. The
proposed methodology is composed of three steps: i) detecting and tracking each moving object
in video data, ii) classifying each object according to its appearance in each frame, and iii)
computing the probability of belonging to each class based on both object appearance and its
speed. For the last step, Bayes’ rule is used to fuse appearance and speed in order to predict
the object category. Using various video datasets collected in different intersections, the
methodology was developed and tested. The developed methodology shows an overall
classification accuracy of more than 90 %. However, the classification accuracy varies across
modes and is highest for vehicles and lower for pedestrians and cyclists. The applicability of the
proposed methodology is illustrated using a simple case study to analyse cyclist-vehicle conflicts
at intersections with and without cycle tracks.

Sohail Zangenehpour, Luis F. Miranda-Moreno, Nicolas Saunier