Exploring Pose-Based Anomaly Detection for Retail Security: A Real-World Shoplifting Dataset and Benchmark
It addresses the problem of shoplifting for retailers by providing a novel dataset and benchmark, though it is incremental as it applies existing pose-based methods to a new domain-specific dataset.
This paper tackles shoplifting detection by framing it as an anomaly detection problem and introduces PoseLift, a privacy-preserving dataset of anonymized human pose data from real-world retail scenarios, achieving high detection accuracy while addressing privacy and bias concerns.
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.