Skeletal Video Anomaly Detection using Deep Learning: Survey, Challenges and Future Directions
This is an incremental survey paper that identifies challenges and future directions for privacy-protecting anomaly detection in videos, relevant for researchers and practitioners in surveillance and healthcare.
The paper surveys skeleton-based deep learning methods for video anomaly detection, addressing privacy concerns and noise sensitivity of appearance-based features, and concludes that skeleton-based approaches are a viable privacy-protecting alternative.
The existing methods for video anomaly detection mostly utilize videos containing identifiable facial and appearance-based features. The use of videos with identifiable faces raises privacy concerns, especially when used in a hospital or community-based setting. Appearance-based features can also be sensitive to pixel-based noise, straining the anomaly detection methods to model the changes in the background and making it difficult to focus on the actions of humans in the foreground. Structural information in the form of skeletons describing the human motion in the videos is privacy-protecting and can overcome some of the problems posed by appearance-based features. In this paper, we present a survey of privacy-protecting deep learning anomaly detection methods using skeletons extracted from videos. We present a novel taxonomy of algorithms based on the various learning approaches. We conclude that skeleton-based approaches for anomaly detection can be a plausible privacy-protecting alternative for video anomaly detection. Lastly, we identify major open research questions and provide guidelines to address them.