Holistic features for real-time crowd behaviour anomaly detection
Marsden, Mark, McGuinness, KevinORCID: 0000-0003-1336-6477, Little, SuzanneORCID: 0000-0003-3281-3471 and O'Connor, Noel E.ORCID: 0000-0002-4033-9135
(2016)
Holistic features for real-time crowd behaviour anomaly detection.
In: 2016 IEEE International Conference on Image Processing, 25-28 Sept 2016, Phoenix, AZ, USA.
ISBN Electronic ISSN: 2381-8549
This paper presents a new approach to crowd behaviour anomaly detection that uses a set of efficiently computed, easily interpretable, scene-level holistic features. This low-dimensional descriptor combines two features from the literature: crowd collectiveness [1] and crowd conflict [2], with two newly developed crowd features: mean motion speed and a new formulation of crowd density. Two different anomaly detection approaches are investigated using these features. When only normal training data is available we use a Gaussian Mixture Model (GMM) for outlier detection. When both normal and abnormal training data is available we use a Support Vector Machine (SVM) for binary classification. We evaluate on two crowd behaviour anomaly detection datasets, achieving both state-of-the-art classification performance on the violent-flows dataset [3] as well as better than real-time processing performance (40 frames per second).
2016 IEEE International Conference on Image Processing (ICIP). IEEE International Conference on Image Processing (ICIP)
.
IEEE. ISBN Electronic ISSN: 2381-8549