Results 1 - 10
of
35
V.: What’s going on? Discovering spatiotemporal dependencies in dynamic scenes
- In: Proc. of the IEEE CVPR
, 2010
"... We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the right of way between different lanes or typical traffic light sequences. To extract them, sequences of activities need to be ..."
Abstract
-
Cited by 75 (1 self)
- Add to MetaCart
(Show Context)
We present two novel methods to automatically learn spatio-temporal dependencies of moving agents in complex dynamic scenes. They allow to discover temporal rules, such as the right of way between different lanes or typical traffic light sequences. To extract them, sequences of activities need to be learned. While the first method extracts rules based on a learned topic model, the second model called DDP-HMM jointly learns co-occurring activities and their time dependencies. To this end we employ Dependent Dirichlet Processes to learn an arbitrary number of infinite Hidden Markov Models. In contrast to previous work, we build on state-of-the-art topic models that allow to automatically infer all parameters such as the optimal number of HMMs necessary to explain the rules governing a scene. The models are trained offline by Gibbs Sampling using unlabeled training data. 1.
Anomaly detection in crowded scenes,”
- in IEEE Conference on Computer Vision and Pattern Recognition,
, 2010
"... ..."
(Show Context)
A Markov Clustering Topic Model for Mining Behaviour in Video
"... This paper addresses the problem of fully automated mining of public space video data. A novel Markov Clustering Topic Model (MCTM) is introduced which builds on existing Dynamic Bayesian Network models (e.g. HMMs) and Bayesian topic models (e.g. Latent Dirichlet Allocation), and overcomes their dra ..."
Abstract
-
Cited by 53 (6 self)
- Add to MetaCart
(Show Context)
This paper addresses the problem of fully automated mining of public space video data. A novel Markov Clustering Topic Model (MCTM) is introduced which builds on existing Dynamic Bayesian Network models (e.g. HMMs) and Bayesian topic models (e.g. Latent Dirichlet Allocation), and overcomes their drawbacks on accuracy, robustness and computational efficiency. Specifically, our model profiles complex dynamic scenes by robustly clustering visual events into activities and these activities into global behaviours, and correlates behaviours over time. A collapsed Gibbs sampler is derived for offline learning with unlabeled training data, and significantly, a new approximation to online Bayesian inference is formulated to enable dynamic scene understanding and behaviour mining in new video data online in real-time. The strength of this model is demonstrated by unsupervised learning of dynamic scene models, mining behaviours and detecting salient events in three complex and crowded public scenes. 1.
Observe locally, infer globally: A space-time mrf for detecting abnormal activities with incremental updates
- In CVPR
"... We propose a space-time Markov Random Field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each l ..."
Abstract
-
Cited by 42 (0 self)
- Add to MetaCart
We propose a space-time Markov Random Field (MRF) model to detect abnormal activities in video. The nodes in the MRF graph correspond to a grid of local regions in the video frames, and neighboring nodes in both space and time are associated with links. To learn normal patterns of activity at each local node, we capture the distribution of its typical optical flow with a Mixture of Probabilistic Principal Component Analyzers. For any new optical flow patterns detected in incoming video clips, we use the learned model and MRF graph to compute a maximum a posteriori estimate of the degree of normality at each local node. Further, we show how to incrementally update the current model parameters as new video observations stream in, so that the model can efficiently adapt to visual context changes over a long period of time. Experimental results on surveillance videos show that our space-time MRF model robustly detects abnormal activities both in a local and global sense: not only does it accurately localize the atomic abnormal activities in a crowded video, but at the same time it captures the global-level abnormalities caused by irregular interactions between local activities. 1.
Online Detection of Unusual Events in Videos via Dynamic Sparse Coding
"... Real-time unusual event detection in video stream has been a difficult challenge due to the lack of sufficient training information, volatility of the definitions for both normality and abnormality, time constraints, and statistical limitation of the fitness of any parametric models. We propose a fu ..."
Abstract
-
Cited by 19 (0 self)
- Add to MetaCart
(Show Context)
Real-time unusual event detection in video stream has been a difficult challenge due to the lack of sufficient training information, volatility of the definitions for both normality and abnormality, time constraints, and statistical limitation of the fitness of any parametric models. We propose a fully unsupervised dynamic sparse coding approach for detecting unusual events in videos based on online sparse reconstructibility of query signals from an atomically learned event dictionary, which forms a sparse coding bases. Based on an intuition that usual events in a video are more likely to be reconstructible from an event dictionary, whereas unusual events are not, our algorithm employs a principled convex optimization formulation that allows both a sparse reconstruction code, and an online dictionary to be jointly inferred and updated. Our algorithm is completely unsupervised, making no prior assumptions of what unusual events may look like and the settings of the cameras. The fact that the bases dictionary is updated in an online fashion as the algorithm observes more data, avoids any issues with concept drift. Experimental results on hours of real world surveillance video and several Youtube videos show that the proposed algorithm could reliably locate the unusual events in the video sequence, outperforming the current state-of-the-art methods. 1.
Anomalous behaviour detection using spatiotemporal oriented energies, subset inclusion histogram comparison and event driven processing
- ECCV
, 2010
"... This paper proposes a novel approach to anomalous behaviour detection in video. The approach is comprised of three key components. First, distributions of spatiotemporal oriented energy are used to model behaviour. This representation can capture a wide range of naturally occurring visual spacetime ..."
Abstract
-
Cited by 14 (6 self)
- Add to MetaCart
(Show Context)
This paper proposes a novel approach to anomalous behaviour detection in video. The approach is comprised of three key components. First, distributions of spatiotemporal oriented energy are used to model behaviour. This representation can capture a wide range of naturally occurring visual spacetime patterns and has not previously been applied to anomaly detection. Second, a novel method is proposed for comparing an automatically acquired model of normal behaviour with new observations. The method accounts for situations when only a subset of the model is present in the new observation, as when multiple activities are acceptable in a region yet only one is likely to be encountered at any given instant. Third, event driven processing is employed to automatically mark portions of the video stream that are most likely to contain deviations from the expected and thereby focus computational efforts. The approach has been implemented with real-time performance. Quantitative and qualitative empirical evaluation on a challenging set of natural image videos demonstrates the approach’s superior performance relative to various alternatives.
Community Trend Outlier Detection using Soft Temporal Pattern Mining
"... Abstract. Numerous applications, such as bank transactions, road traffic, and news feeds, generate temporal datasets, in which data evolves continuously. To understand the temporal behavior and characteristics of the dataset and its elements, we need effective tools that can capture evolution of the ..."
Abstract
-
Cited by 11 (8 self)
- Add to MetaCart
(Show Context)
Abstract. Numerous applications, such as bank transactions, road traffic, and news feeds, generate temporal datasets, in which data evolves continuously. To understand the temporal behavior and characteristics of the dataset and its elements, we need effective tools that can capture evolution of the objects. In this paper, we propose a novel and important problem in evolution behavior discovery. Given a series of snapshots of a temporal dataset, each of which consists of evolving communities, our goal is to find objects which evolve in a dramatically different way compared with the other community members. We define such objects as community trend outliers. It is a challenging problem as evolutionary patterns are hidden deeply in noisy evolving datasets and thus it is difficult to distinguish anomalous objects from normal ones. We propose an effective two-step procedure to detect community trend outliers. We first model the normal evolutionary behavior of communities across time using soft patterns discovered from the dataset. In the second step, we propose effective measures to evaluate chances of an object deviating from the normal evolutionary patterns. Experimental results on both synthetic and real datasets show that the proposed approach is highly effective in discovering interesting community trend outliers. 1
Improved anomaly detection in crowded scenes via cell-based analysis of foreground speed, size and texture
- In Computer Vision and Pattern Recognition Workshops (CVPRW
, 2011
"... A robust and efficient anomaly detection technique is proposed, capable of dealing with crowded scenes where traditional tracking based approaches tend to fail. Initial foreground segmentation of the input frames confines the analysis to foreground objects and effectively ignores irrelevant backgrou ..."
Abstract
-
Cited by 10 (2 self)
- Add to MetaCart
(Show Context)
A robust and efficient anomaly detection technique is proposed, capable of dealing with crowded scenes where traditional tracking based approaches tend to fail. Initial foreground segmentation of the input frames confines the analysis to foreground objects and effectively ignores irrelevant background dynamics. Input frames are split into nonoverlapping cells, followed by extracting features based on motion, size and texture from each cell. Each feature type is independently analysed for the presence of an anomaly. Unlike most methods, a refined estimate of object motion is achieved by computing the optical flow of only the foreground pixels. The motion and size features are modelled by an approximated version of kernel density estimation, which is computationally efficient even for large training datasets. Texture features are modelled by an adaptively grown codebook, with the number of entries in the codebook selected in an online fashion. Experiments on the recently published UCSD Anomaly Detection dataset show that the proposed method obtains considerably better results than three recent approaches: MPPCA, social force, and mixture of dynamic textures (MDT). The proposed method is also several orders of magnitude faster than MDT, the next best performing method. 1.
Video parsing for abnormality detection
- In ICCV
, 2011
"... Detecting abnormalities in video is a challenging prob-lem since the class of all irregular objects and behaviors is infinite and thus no (or by far not enough) abnormal train-ing samples are available. Consequently, a standard set-ting is to find abnormalities without actually knowing what they are ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
(Show Context)
Detecting abnormalities in video is a challenging prob-lem since the class of all irregular objects and behaviors is infinite and thus no (or by far not enough) abnormal train-ing samples are available. Consequently, a standard set-ting is to find abnormalities without actually knowing what they are because we have not been shown abnormal exam-ples during training. However, although the training data does not define what an abnormality looks like, the main paradigm in this field is to directly search for individual ab-normal local patches or image regions independent of an-other. To address this problem we parse video frames by estab-lishing a set of hypotheses that jointly explain all the fore-ground while, at same time, trying to find normal training samples that explain the hypotheses. Consequently, we can avoid a direct detection of abnormalities. They are discov-ered indirectly as those hypotheses which are needed for covering the foreground without finding an explanation by normal samples for themselves. We present a probabilistic model that localizes abnormalities using statistical infer-ence. On the challenging dataset of [15] it outperforms the state-of-the-art by 7 % to achieve a frame-based abnormal-ity classification performance of 91 % and the localization performance improves by 32 % to 76%. 1.
Group Context Learning for Event Recognition
- In Proceedings of the IEEE Workshop on Application of Computer Vision
, 2012
"... We address the problem of group-level event recognition from videos. The events of interest are defined based on the motion and interaction of members in a group over time. Example events include group formation, dispersion, fol-lowing, chasing, flanking, and fighting. To recognize these complex gro ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
We address the problem of group-level event recognition from videos. The events of interest are defined based on the motion and interaction of members in a group over time. Example events include group formation, dispersion, fol-lowing, chasing, flanking, and fighting. To recognize these complex group events, we propose a novel approach that learns the group-level scenario context from automatically extracted individual trajectories. We first perform a group structure analysis to produce a weighted graph that repre-sents the probabilistic group membership of the individuals. We then extract features from this graph to capture the mo-tion and action contexts among the groups. The features are represented using the “bag-of-words ” scheme. Finally, our method uses the learned Support Vector Machine (SVM) to classify a video segment into the six event categories. Our implementation builds upon a mature multi-camera multi-target tracking system that recognizes the group-level events involving up to 20 individuals in real-time. 1.
