Exploring Pose-Based Anomaly Detection for Retail Security: A Real-World Shoplifting Dataset and Benchmark

2025-01-11

AI Summary

To address privacy leakage and identity bias in shoplifting detection within retail environments, this paper proposes a novel unsupervised anomaly detection paradigm based on human pose estimation. Our contributions are threefold: (1) We introduce PoseLift—the first real-world, privacy-preserving shoplifting pose dataset—where anonymized keypoint sequences ensure behavioral fidelity while eliminating identifiable attributes; (2) We design a lightweight pose representation coupled with a scene-aware anomaly scoring mechanism, enabling both unsupervised and semi-supervised learning; (3) We establish a comprehensive benchmarking framework tailored to retail behavior analysis. Extensive experiments demonstrate that our method achieves state-of-the-art shoplifting detection accuracy on PoseLift, significantly outperforming conventional vision-based approaches. Crucially, it safeguards customer privacy and mitigates algorithmic bias, offering a trustworthy foundation for ethical retail security systems.

Technology Category

• Computer Vision: Bias, Fairness & Privacy
• Machine Learning: Privacy
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Shoplifting poses a significant challenge for retailers, resulting in billions of dollars in annual losses. Traditional security measures often fall short, highlighting the need for intelligent solutions capable of detecting shoplifting behaviors in real time. This paper frames shoplifting detection as an anomaly detection problem, focusing on the identification of deviations from typical shopping patterns. We introduce PoseLift, a privacy-preserving dataset specifically designed for shoplifting detection, addressing challenges such as data scarcity, privacy concerns, and model biases. PoseLift is built in collaboration with a retail store and contains anonymized human pose data from real-world scenarios. By preserving essential behavioral information while anonymizing identities, PoseLift balances privacy and utility. We benchmark state-of-the-art pose-based anomaly detection models on this dataset, evaluating performance using a comprehensive set of metrics. Our results demonstrate that pose-based approaches achieve high detection accuracy while effectively addressing privacy and bias concerns inherent in traditional methods. As one of the first datasets capturing real-world shoplifting behaviors, PoseLift offers researchers a valuable tool to advance computer vision ethically and will be publicly available to foster innovation and collaboration. The dataset is available at https://github.com/TeCSAR-UNCC/PoseLift.

Problem

• Abnormal Behavior Detection
• Real-time Monitoring
• Privacy Protection

Innovation

• PoseLift Dataset
• Anomaly Detection
• Privacy Protection