Contracting Skeletal Kinematics for Human-Related Video Anomaly Detection

TL;DR

This paper introduces COSKAD, a novel skeletal motion encoding model using graph convolutional networks and hyperspherical embeddings, achieving state-of-the-art results in human-related video anomaly detection.

Contribution

It proposes a new hyperspherical embedding space for skeletal motion, improving anomaly detection performance over existing methods.

Findings

Outperforms state-of-the-art on UBnormal dataset

Sets new benchmarks on ShanghaiTech Campus and CUHK Avenue datasets

Achieves performance comparable to video-based methods

Abstract

Detecting the anomaly of human behavior is paramount to timely recognizing endangering situations, such as street fights or elderly falls. However, anomaly detection is complex since anomalous events are rare and because it is an open set recognition task, i.e., what is anomalous at inference has not been observed at training. We propose COSKAD, a novel model that encodes skeletal human motion by a graph convolutional network and learns to COntract SKeletal kinematic embeddings onto a latent hypersphere of minimum volume for Video Anomaly Detection. We propose three latent spaces: the commonly-adopted Euclidean and the novel spherical and hyperbolic. All variants outperform the state-of-the-art on the most recent UBnormal dataset, for which we contribute a human-related version with annotated skeletons. COSKAD sets a new state-of-the-art on the human-related versions of ShanghaiTech Campus and CUHK Avenue, with performance comparable to video-based methods. Source code and dataset will be released upon acceptance.