Cognition Guided Video Anomaly Detection Framework for Surveillance Services
Menghao Zhang, Jingyu Wang, Qi Qi, Zirui Zhuang, Haifeng Sun, Jianxin Liao
Abstract
The aim of surveillance services is to detect anomalous events that occur in given surveillance videos. Most existing video anomaly detection methods rely on minimizing reconstruction or prediction errors due to the lack of abnormal data, which results in poor generalization and overfitting. In fact, cognitions for anomalies in surveillance videos mainly relies on crucial relationships, including ones between objects and ones between objects and scenes. Focusing on this property of anomaly detection, a <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">C</b> ognition <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">G</b> uided <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">V</b> ideo <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</b> nomaly <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">D</b> etection framework based on prior knowledge is proposed, called <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CG-VAD</b> . CG-VAD introduces both explicit and implicit prior knowledge into the frame prediction network to let the model exploit crucial relationships. Explicit knowledge containing crucial relationships related to anomaly is introduced into the anomaly detection model through a proposed embedding network based on multi-layer Graph Convolutional Networks. Implicit knowledge in the form of learnable parameters enhances the ability of the model to learn crucial relationships through prompt tuning. By integrating prior knowledge to focus the model on the relationships associated with the anomaly, we find that CG-VAD is not only quick to adapt to new real-world scenarios, but it is also able to recognize the type of anomaly. We have conducted extensive experiments on four benchmark datasets and the results indicate that the proposed method outperforms previous methods. Specifically, CG-VAD achieves an AUROC score of 87.2 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> on the ShanghaiTech dataset. Code is available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/zmh0124/CG-VAD</uri> .