Vehicles Recognition Using Fuzzy Descriptors of Image Segments

TL;DR

This paper introduces a vision-based vehicle recognition method using fuzzy descriptors of image segments, which considers geometrical and shape features for automatic vehicle identification in traffic scenes.

Contribution

It presents a novel fuzzy rule-based algorithm for vehicle recognition that accounts for shape and arrangement of image segments, adaptable to various vehicle shapes and models.

Findings

Effective vehicle recognition in traffic scenes

Applicable to video sensors for traffic control

Flexible with different vehicle shapes

Abstract

In this paper a vision-based vehicles recognition method is presented. Proposed method uses fuzzy description of image segments for automatic recognition of vehicles recorded in image data. The description takes into account selected geometrical properties and shape coefficients determined for segments of reference image (vehicle model). The proposed method was implemented using reasoning system with fuzzy rules. A vehicles recognition algorithm was developed based on the fuzzy rules describing shape and arrangement of the image segments that correspond to visible parts of a vehicle. An extension of the algorithm with set of fuzzy rules defined for different reference images (and various vehicle shapes) enables vehicles classification in traffic scenes. The devised method is suitable for application in video sensors for road traffic control and surveillance systems.