Effective Object Tracking in Unstructured Crowd Scenes

TL;DR

This paper introduces a rotation variant OTC descriptor combined with a mean shift algorithm for effective object tracking in unstructured crowd scenes, demonstrating improved performance over existing methods.

Contribution

The paper presents a novel OTC descriptor and a mean shift-based tracking algorithm tailored for unstructured crowd scenes, addressing challenges of rotation and texture variability.

Findings

Effective tracking in challenging crowd scenes

Comparison shows advantages over state-of-the-art methods

Analysis highlights strengths and limitations

Abstract

In this paper, we are presenting a rotation variant Oriented Texture Curve (OTC) descriptor based mean shift algorithm for tracking an object in an unstructured crowd scene. The proposed algorithm works by first obtaining the OTC features for a manually selected object target, then a visual vocabulary is created by using all the OTC features of the target. The target histogram is obtained using codebook encoding method which is then used in mean shift framework to perform similarity search. Results are obtained on different videos of challenging scenes and the comparison of the proposed approach with several state-of-the-art approaches are provided. The analysis shows the advantages and limitations of the proposed approach for tracking an object in unstructured crowd scenes.