Robust Baggage Detection and Classification Based on Local Tri-directional Pattern

TL;DR

This paper introduces a robust baggage detection method using a novel local tri-directional pattern descriptor, improving feature accuracy and size over traditional methods for surveillance applications.

Contribution

The paper proposes a new local tri-directional pattern descriptor for human feature extraction, enhancing baggage detection accuracy in surveillance videos.

Findings

LtriDP outperforms existing feature descriptors on INRIA and MSMT17 V1 datasets.

The method effectively detects humans with or without baggage.

Experimental results validate the robustness of the proposed approach.

Abstract

In recent decades, the automatic video surveillance system has gained significant importance in computer vision community. The crucial objective of surveillance is monitoring and security in public places. In the traditional Local Binary Pattern, the feature description is somehow inaccurate, and the feature size is large enough. Therefore, to overcome these shortcomings, our research proposed a detection algorithm for a human with or without carrying baggage. The Local tri-directional pattern descriptor is exhibited to extract features of different human body parts including head, trunk, and limbs. Then with the help of support vector machine, extracted features are trained and evaluated. Experimental results on INRIA and MSMT17 V1 datasets show that LtriDP outperforms several state-of-the-art feature descriptors and validate its effectiveness.