Plug-and-Play Anomaly Detection with Expectation Maximization Filtering

06/16/2020
by   Muhammad Umar Karim Khan, et al.
0

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 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 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 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.

READ FULL TEXT

page 3

page 9

page 10

page 13

research
09/11/2019

Anomaly Detection with Inexact Labels

We propose a supervised anomaly detection method for data with inexact a...
research
01/28/2023

Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore

In the area of fewshot anomaly detection (FSAD), efficient visual featur...
research
10/25/2022

Deep Crowd Anomaly Detection: State-of-the-Art, Challenges, and Future Research Directions

Crowd anomaly detection is one of the most popular topics in computer vi...
research
05/08/2023

Is AUC the best measure for practical comparison of anomaly detectors?

The area under receiver operating characteristics (AUC) is the standard ...
research
06/03/2019

An Adaptive Training-less System for Anomaly Detection in Crowd Scenes

Anomaly detection in crowd videos has become a popular area of research ...
research
11/10/2020

Decoupled Appearance and Motion Learning for Efficient Anomaly Detection in Surveillance Video

Automating the analysis of surveillance video footage is of great intere...
research
12/02/2020

Video Anomaly Detection by Estimating Likelihood of Representations

Video anomaly detection is a challenging task not only because it involv...

Please sign up or login with your details

Forgot password? Click here to reset