Appearance invariant Entry-Exit matching using visual soft biometric traits

TL;DR

This paper introduces a semantic entry-exit matching model that uses soft biometric traits like height, build, complexion, and clothing color to improve appearance-invariant subject recognition in surveillance, enhancing accuracy and efficiency.

Contribution

The paper proposes a novel semantic matching model leveraging soft biometric traits for appearance-invariant recognition, improving rank-k accuracy in surveillance scenarios.

Findings

High rank-k accuracy achieved on benchmark datasets

Soft biometric traits help narrow down search space effectively

Model is robust to clothing variations

Abstract

The problem of appearance invariant subject recognition for Entry-Exit surveillance applications is addressed. A novel Semantic Entry-Exit matching model that makes use of ancillary information about subjects such as height, build, complexion and clothing color to endorse exit of every subject who had entered private area is proposed in this paper. The proposed method is robust to variations in clothing. Each describing attribute is given equal weight while computing the matching score and hence the proposed model achieves high rank-k accuracy on benchmark datasets. The soft biometric traits used as a combination though cannot achieve high rank-1 accuracy, it helps to narrow down the search to match using reliable biometric traits such as gait and face whose learning and matching time is costlier when compared to the visual soft biometrics.