Plug-and-Play Anomaly Detection with Expectation Maximization Filtering
This work addresses anomaly detection for crowd surveillance using autonomous smart cameras, but it is incremental as it builds on existing deep learning methods with specific optimizations.
The paper tackles anomaly detection in crowds for early rescue response by proposing a plug-and-play smart camera framework that addresses constraints like no iterative training, no labels, and simultaneous training and classification. It achieves improvements in AUC, such as 4.66% and 4.9% over convolutional autoencoders and LSTM methods, and 24.87% over future frame prediction-based approaches.
Anomaly detection in crowds enables early rescue response. A plug-and-play smart camera for crowd surveillance has numerous constraints different from typical anomaly detection: the training data cannot be used iteratively; there are no training labels; and training and classification needs to be performed simultaneously. We tackle all these constraints with our approach in this paper. We propose a Core Anomaly-Detection (CAD) neural network which learns the motion behavior of objects in the scene with an unsupervised method. On average over standard datasets, CAD with a single epoch of training shows a percentage increase in Area Under the Curve (AUC) of 4.66% and 4.9% compared to the best results with convolutional autoencoders and convolutional LSTM-based methods, respectively. With a single epoch of training, our method improves the AUC by 8.03% compared to the convolutional LSTM-based approach. We also propose an Expectation Maximization filter which chooses samples for training the core anomaly-detection network. The overall framework improves the AUC compared to future frame prediction-based approach by 24.87% when crowd anomaly detection is performed on a video stream. We believe our work is the first step towards using deep learning methods with autonomous plug-and-play smart cameras for crowd anomaly detection.