Results 1 - 10
of
17
Extracting and locating temporal motifs in video scenes using a hierarchical non parametric bayesian model
- in IEEE Conference on Computer Vision and Pattern Recognition
, 2011
"... In this paper, we present an unsupervised method for mining activities in videos. From unlabeled video sequences of a scene, our method can automatically recover what are the recurrent temporal activity patterns (or motifs) and when they occur. Using non parametric Bayesian methods, we are able to a ..."
Abstract
-
Cited by 16 (6 self)
- Add to MetaCart
(Show Context)
In this paper, we present an unsupervised method for mining activities in videos. From unlabeled video sequences of a scene, our method can automatically recover what are the recurrent temporal activity patterns (or motifs) and when they occur. Using non parametric Bayesian methods, we are able to automatically find both the underlying number of motifs and the number of motif occurrences in each document. The model’s robustness is first validated on synthetic data. It is then applied on a large set of video data from state-of-the-art papers. We show that it can effectively recover temporal activities with high semantics for humans and strong temporal information. The model is also used for prediction where it is shown to be as efficient as other approaches. Although illustrated on video sequences, this model can be directly applied to various kinds of time series where multiple activities occur simultaneously. 1.
Earth mover’s prototypes: a convex learning approach for discovering activity patterns in dynamic scenes
- in IEEE Conf. on Computer Vision and Pattern Recognition
, 2011
"... Mining behaviors in complex scenes ..."
Bridging the past, present and future: Modeling scene activities from event relationships and global rules
- In CVPR
, 2012
"... This paper addresses the discovery of activities and learns the underlying processes that govern their occurrences over time in complex surveillance scenes. To this end, we propose a novel topic model that accounts for the two main factors that affect these occurrences: (1) the existence of global s ..."
Abstract
-
Cited by 8 (3 self)
- Add to MetaCart
(Show Context)
This paper addresses the discovery of activities and learns the underlying processes that govern their occurrences over time in complex surveillance scenes. To this end, we propose a novel topic model that accounts for the two main factors that affect these occurrences: (1) the existence of global scene states that regulate which of the activities can spontaneously occur; (2) local rules that link past activity occurrences to current ones with temporal lags. These complementary factors are mixed in the probabilistic generative process, thanks to the use of a binary random variable that selects for each activity occurrence which one of the above two factors is applicable. All model parameters are efficiently inferred using a collapsed Gibbs sampling inference scheme. Experiments on various datasets from the literature show that the model is able to capture temporal processes at multiple scales: the scene-level first order Markovian process, and causal relationships amongst activities that can be used to predict which activity can happen after another one, and after what delay, thus providing a rich interpretation of the scene’s dynamical content. 1.
A prototype learning framework using emd: Application to complex scenes analysis
- IEEE Trans. Pattern Anal. Mach. Intell
"... Abstract—In the last decades, many efforts have been devoted to develop methods for automatic scene understanding in the context of video surveillance applications. This paper presents a novel non-object centric approach for complex scene analysis. Similarly to previous methods, we use low-level cue ..."
Abstract
-
Cited by 7 (3 self)
- Add to MetaCart
(Show Context)
Abstract—In the last decades, many efforts have been devoted to develop methods for automatic scene understanding in the context of video surveillance applications. This paper presents a novel non-object centric approach for complex scene analysis. Similarly to previous methods, we use low-level cues to individuate atomic activities and create clip histograms. Differently from recent works, the task of discovering high-level activity patterns is formulated as a convex prototype learning problem. This problem results into a simple linear program that can be solved efficiently with standard solvers. The main advantage of our approach is that, using as objective function the Earth Mover’s Distance (EMD), the similarity among elementary activities is taken into account in the learning phase. To improve scalability we also consider some variants of EMD adopting L1 as ground distance for one and two dimensional, linear and circular histograms. In these cases only the similarity between neighboring atomic activities, corresponding to adjacent histogram bins, is taken into account. Therefore we also propose an automatic strategy for sorting atomic activities. Experimental results on publicly available datasets show that our method compares favorably with state-of-the-art approaches, often outperforming them.
A Non-parametric Hierarchical Model to Discover Behavior Dynamics from Tracks
"... Abstract. We present a novel non-parametric Bayesian model to jointly discover the dynamics of low-level actions and high-level behaviors of tracked people in open environments. Our model represents behaviors as Markov chains of actions which capture high-level temporal dynamics. Actions may be shar ..."
Abstract
-
Cited by 7 (1 self)
- Add to MetaCart
(Show Context)
Abstract. We present a novel non-parametric Bayesian model to jointly discover the dynamics of low-level actions and high-level behaviors of tracked people in open environments. Our model represents behaviors as Markov chains of actions which capture high-level temporal dynamics. Actions may be shared by various behaviors and represent spatially localized occurrences of a person’s low-level motion dynamics using Switching Linear Dynamics Systems. Since the model handles real-valued features directly, we do not lose information by quantizing measurements to ‘visual words ’ and can thus discover variations in standing, walking and running without discrete thresholds. We describe inference using Gibbs sampling and validate our approach on several artificial and real-world tracking datasets. We show that our model can distinguish relevant behavior patterns that an existing state-of-the-art method for hierarchical clustering cannot. 1
Multi-camera open space human activity discovery for anomaly detection
- In AVSS
, 2011
"... We address the discovery of typical activities in video stream contents and its exploitation for estimating the abnormality levels of these streams. Such estimates can be used to select the most interesting cameras to show to a human operator. Our contributions come from the following facets: i) the ..."
Abstract
-
Cited by 7 (5 self)
- Add to MetaCart
(Show Context)
We address the discovery of typical activities in video stream contents and its exploitation for estimating the abnormality levels of these streams. Such estimates can be used to select the most interesting cameras to show to a human operator. Our contributions come from the following facets: i) the method is fully unsupervised and learns the activities from long term data; ii) the method is scalable and can efficiently handle the information provided by multiple un-calibrated cameras, jointly learning activities shared by them if it happens to be the case (e.g. when they have overlapping fields of view); iii) unlike previous methods which were mainly applied to structured urban traffic scenes, we show that ours performs well on videos from a metro environment where human activities are only loosely constrained.
A sparsity constraint for topic models application to temporal activity mining,” NIPS
, 2010
"... We address the mining of sequential activity patterns from document logs given as word-time occurrences. We achieve this using topics that model both the cooccurrence and the temporal order in which words occur within a temporal window. Discovering such topics, which is particularly hard when multip ..."
Abstract
-
Cited by 4 (1 self)
- Add to MetaCart
(Show Context)
We address the mining of sequential activity patterns from document logs given as word-time occurrences. We achieve this using topics that model both the cooccurrence and the temporal order in which words occur within a temporal window. Discovering such topics, which is particularly hard when multiple activities can occur simultaneously, is conducted through the joint inference of the temporal topics and of their starting times, allowing the implicit alignment of the same activity occurrences in the document. A current issue is that while we would like topic starting times to be represented by sparse distributions, this is not achieved in practice. Thus, in this paper, we propose a method that encourages sparsity, by adding regularization constraints on the searched distributions. The constraints can be used with most topic models (e.g. PLSA, LDA) and lead to a simple modified version of the EM standard optimization procedure. The effect of the sparsity constraint on our activity model and the robustness improvement in the presence of difference noises have been validated on synthetic data. Its effectiveness is also illustrated in video activity analysis, where the discovered topics capture frequent patterns that implicitly represent typical trajectories of scene objects. 1
Dimensionality reduction and topic modelling: from latent semantic indexing to latent dirichlet allocation and beyond
- in Mining Text Data, C. Aggarwal and
, 2012
"... ..."
(Show Context)
C.: Mono versus multi-view tracking-based model for automatic scene activity modeling and anomaly detection
- In: EEE Int. Conf. on Advanced Video and Signal-Based
, 2011
"... In this paper, we present a novel method able to automatically discover recurrent activities occurring in a video scene, and to identify the temporal relations between these activities, which can be used either in mono-view or in multi-view context (for example, to discover the different flows of pa ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
In this paper, we present a novel method able to automatically discover recurrent activities occurring in a video scene, and to identify the temporal relations between these activities, which can be used either in mono-view or in multi-view context (for example, to discover the different flows of passengers inside a subway station and identify the rules that govern these flows). The proposed method is based on particle-based trajectories, analyzed through a cascade of HMM and HDP-HMM models. We experiment our model for scene activity recognition task on a subway dataset using both mono-view and multi-view analysis. We last show that our model is also able to perform on the fly and in real-time abnormal events detection (by identifying activities or relations that do not fit in the usual/learnt ones). 1.
Discovering reoccurring motifs to predict opponent behavior
"... Abstract — In contrast to human soccer players, autonomous robot soccer players often move according to a limited set of predefined behavioral rules. This knowledge can be used advantageously: If the opponent’s behavioral rules are learned, it will be possible to detect these during a match and reac ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
Abstract — In contrast to human soccer players, autonomous robot soccer players often move according to a limited set of predefined behavioral rules. This knowledge can be used advantageously: If the opponent’s behavioral rules are learned, it will be possible to detect these during a match and react accordingly. A method for autonomous activity mining in videos, called Probabilistic Latent Sequential Motifs, is used to discover optical flow patterns in videos of a robot soccer player during a penalty shootout. The discovered patterns are used by a humanoid goalkeeper to predict and anticipate opponent behavior. Effectiveness of the method is tested by comparing the performance of this goalkeeper with predictive behavior to that of an existing goalkeeper that only reacts when the ball approaches at sufficient speed. The performance is measured based on the ratio of number of goals to number of goals prevented. Results show that the goalkeeper with predictive behavior could prevent a fair amount of goals, but that it loses in performance to the existing goalkeeper. Methods that may improve performance are discussed. I.
