Package Theft Detection from Smart Home Security Cameras

TL;DR

This paper introduces a novel framework called GLF-PTDE for detecting package theft in videos, addressing challenges like limited training data and diverse theft scenarios, and demonstrates its effectiveness on a new dataset.

Contribution

The paper presents a new GLF-PTDE framework and a dedicated dataset for package theft detection, advancing research in this area.

Findings

Achieved 80% AUC on the new dataset.

Demonstrated robustness across different real-world scenes.

Proposed a novel fusion embedding for theft detection.

Abstract

Package theft detection has been a challenging task mainly due to lack of training data and a wide variety of package theft cases in reality. In this paper, we propose a new Global and Local Fusion Package Theft Detection Embedding (GLF-PTDE) framework to generate package theft scores for each segment within a video to fulfill the real-world requirements on package theft detection. Moreover, we construct a novel Package Theft Detection dataset to facilitate the research on this task. Our method achieves 80% AUC performance on the newly proposed dataset, showing the effectiveness of the proposed GLF-PTDE framework and its robustness in different real scenes for package theft detection.