Results 1 - 10
of
10
Dense spatio-temporal features for nonparametric anomaly detection and localization
- in: Proc. of ACM Workshop on Analysis and Retrieval of Tracked Events and Motion in Imagery Streams (ARTEMIS
"... In this paper we propose dense spatio-temporal features to capture scene dynamic statistics together with appearance, in video surveillance applications. These features are ex-ploited in a real-time anomaly detection system. Anomaly detection is performed using a non-parametric modelling, evaluating ..."
Abstract
-
Cited by 5 (1 self)
- Add to MetaCart
(Show Context)
In this paper we propose dense spatio-temporal features to capture scene dynamic statistics together with appearance, in video surveillance applications. These features are ex-ploited in a real-time anomaly detection system. Anomaly detection is performed using a non-parametric modelling, evaluating directly local descriptor statistics, and an unsu-pervised or semi-supervised approach. A method to update scene statistics, to cope with scene changes that typically happen in real world settings, is also provided. The pro-posed method is tested on publicly available datasets and compared to other state-of-the-art approaches.
M.: Non-parametric anomaly detection exploiting space-time features
- In: Proc. of ACM Multimedia (MM) (2010
"... In this paper a real-time anomaly detection system for video streams is proposed. Spatio-temporal features are exploited to capture scene dynamic statistics together with appear-ance. Anomaly detection is performed in a non-parametric fashion, evaluating directly local descriptor statistics. A metho ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
In this paper a real-time anomaly detection system for video streams is proposed. Spatio-temporal features are exploited to capture scene dynamic statistics together with appear-ance. Anomaly detection is performed in a non-parametric fashion, evaluating directly local descriptor statistics. A method to update scene statistics, to cope with scene changes that typically happen in real world settings, is also pro-vided. The proposed method is tested on publicly available datasets.
Computer Vision and Image Understanding xxx (2011) xxx–xxx Contents lists available at SciVerse ScienceDirect Computer Vision and Image Understanding
"... journal homepage: www.elsevier.com/locate/cviu Multi-scale and real-time non-parametric approach for anomaly detection ..."
Abstract
- Add to MetaCart
journal homepage: www.elsevier.com/locate/cviu Multi-scale and real-time non-parametric approach for anomaly detection
Recognising High-Level Agent Behaviour through Observations in Data Scarce Domains
, 2012
"... This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that the copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without the prior This thesis presents a novel method for p ..."
Abstract
- Add to MetaCart
(Show Context)
This copy of the thesis has been supplied on condition that anyone who consults it is understood to recognise that the copyright rests with its author and that no quotation from the thesis and no information derived from it may be published without the prior This thesis presents a novel method for performing multi-agent behaviour recognition without requiring large training corpora. The reduced need for data means that robust probabilistic recognition can be performed within domains where annotated datasets are traditionally unavailable (e.g. surveillance, defence). Human behaviours are composed from sequences of underlying activities that can be used as salient features. We do not assume that the exact temporal ordering of such features is necessary, so can represent behaviours using an unordered “bag-of-features”. A weak temporal ordering is imposed during inference to match behaviours to observations and replaces the learnt model parameters used by competing methods. Our three-tier architecture comprises low-level video tracking, event analysis and high-level inference. High-level inference is performed using a new, cascading extension of the Rao-Blackwellised Particle Filter. Behaviours are
Neural Networks ( ) – Contents lists available at ScienceDirect Neural Networks
"... journal homepage: www.elsevier.com/locate/neunet ..."
(Show Context)
Extraction of Semantic Information from Events
"... Abstract. Behavior understanding from events can be considered as a typical classification problem using predefined classes. In our research presented in this thesis, the main idea is to deal with this classification problem using motion analysis for behavior recognition. We describe our research wo ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. Behavior understanding from events can be considered as a typical classification problem using predefined classes. In our research presented in this thesis, the main idea is to deal with this classification problem using motion analysis for behavior recognition. We describe our research work from its first steps to the final accomplishments. Novel methods are introduced including a methodology whereby frame infor-mation is coded in graphs (called Optical Flow Proximity Graphs- OF-PGs), using only optical flow to form the feature vector. A symbolic method including two levels of graph representation is also proposed dealing with the same recognition problem. OFPGs are also proposed for video indexing. Furthermore, a bottom-up approach for anomaly de-tection using a multi camera system is proposed. In the framework of this system, we present the use of one class continuous Hidden Markov Models (cHMMs) for the task of human behavior recognition. An approximation algorithm, called Observation Log Probability Approximation (OLPA), is proposed to overcome numerical stability problems in the calculation of probability of emission for very long observations.
UNCLASSIFIED
"... Abstract — Visual Human Intent Analysis (VHIA) is a growing field of research devoted to algorithms that categorize human behavior through input of visual image sequences. In VHIA, it is difficult to make an implementation framework that is robust enough to handle the many non-deterministic ways of ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract — Visual Human Intent Analysis (VHIA) is a growing field of research devoted to algorithms that categorize human behavior through input of visual image sequences. In VHIA, it is difficult to make an implementation framework that is robust enough to handle the many non-deterministic ways of human physical actions. This paper will survey several techniques currently used in VHIA including non-traditional artificial intelligence techniques, visual languages, statistical algorithms, and others. It will give the reader the background and understanding of how open this domain is to new algorithms; improving on the overall research in VHIA or similarly related problems.
