A robust approach for road users classification using the motion cues

Video monitoring of traffic is a common practice in major cities. The data generated by video monitoring has practical uses such as traffic analysis for city planning. However, the usefulness of video monitoring of traffic is limited unless there is also a reliable way to automatically classify road users. This paper presents an automated method of road users’ classification into vehicles, cyclists, and pedestrians by using their motion cues. In this method, the movement of road users was captured on sequences of video frames. The videos were analysed using a feature-based tracking system, which has returned the tracks of road users. The separate pieces of information gained from these tracks are hereafter called Classifiers. There are nineteen classifiers included in this method. The classifiers’ values were assessed and integrated into a fuzzy membership framework, which in turn required prior configurations to be available. This led to the final classification of road users. The performance of this method demonstrated promising results. An important contribution of this paper is the creation of a robust approach that can integrate different classifiers using fuzzy membership framework. The developed method also uses parametric classifiers, which do not depend on the specific geometry or traffic operation of the intersection. This is a key advantage because it enables transferability and improves the practicality and usefulness of the method.