1,720,962 research outputs found
Online Nonparametric Bayesian Activity Mining and Analysis from Surveillance Video
No full textA method for online incremental mining of activity patterns from the surveillance video stream is presented in this paper. The framework consists of a learning block in which Dirichlet process mixture model is employed for the incremental clustering of trajectories. Stochastic trajectory pattern models are formed using the Gaussian process regression of the corresponding flow functions. Moreover, a sequential Monte Carlo method based on Rao-Blackwellized particle filter is proposed for tracking and online classification as well as the detection of abnormality during the observation of an object. Experimental results on real surveillance video data are provided to show the performance of the proposed algorithm in different tasks of trajectory clustering, classification, and abnormality detectio
Incremental learning of environment interactive structures from trajectories of individuals
No full textThis work proposes a novel method for estimating the influence that unknown static objects might have over mobile agents. Since the motion of agents can be affected by the presence of fixed objects, it is possible use the information about trajectories deviations to infer the presence of obstacles and estimate the forces involved in a scene. Artificial neural networks are used to estimate a non-parametric function related to the velocity field influencing moving agents. The proposed method is able to incrementally learn the velocity fields due to external static objects within the monitored environment. It determines whether an object has a repulsive or an attractive influence and provides an estimation of its position and size. As stationarity is assumed, i.e., time-invariance of force fields, learned observation models can be used as prior knowledge for estimating hierarchically the properties of new objects in a scene
A particle filter based sequential trajectory classifier for behavior analysis in video surveillance
No full textThe problem of behavior assessment in video surveillance is approached using trajectory classification. Lagrangian state dynamic is used for probabilistic modeling of trajectory patterns and an off-line parameter learning method for the model is proposed. For classification purpose, an on-line sequential maximum a posterior trajectory classifier is introduced based on particle filter. Finally, the performance of this method is evaluated using a traffic video data set
Unsupervised trajectory pattern classification using hierarchical Dirichlet Process Mixture hidden Markov model
No full textIn this paper we present a trajectory clustering method based on nonparametric Bayesian approach proposed for analyzing dynamic systems. Our method uses a modified hierarchical Dirichlet process-hidden Markov model in order to learn trajectory patterns into its parameter variables in an unsupervised way. Due to inherited Bayesian structure, this model resolves some limitations in trajectory clustering problem such as sequential analysis, incremental learning and non-uniform sampling. In this paper we introduce this model and its learning algorithm and finally we evaluate its performance
Online pedestrian group walking event detection using spectral analysis of motion similarity graph
No full textA method for online identification of group of moving objects in the video is proposed in this paper. This method at each frame identifies group of tracked objects with similar local instantaneous motion pattern using spectral clustering on motion similarity graph. Then, the output of the algorithm is used to detect the event of more than two object moving together as required by PETS2015 challenge. The performance of the algorithm is evaluated on the PETS2015 dataset
Abnormal vessel behavior detection in port areas based on Dynamic Bayesian Networks
No full textAutomatic recognition of abnormal situations in harbor environments is approached in this paper with a system based on Dynamic Bayesian Networks. The area under surveillance is partitioned in zones of different sizes and shapes by means of an Instantaneous Topological Map, on which events are detected and inference is carried out. The model is trained with synthetic normal trajectories of ships and vessels mooring in the port, and each time a new trajectory is presented to the system, comparisons with the normal behaviors stored in the network are performed. If no match is found, an abnormal situation is declared and countermeasures can be taken. The algorithm has been tested in a real port with simulated data in order to evaluate the false alarm rate and the abnormal detection capabilities of the proposed approach
Abnormal vessel behavior detection in port areas based on Dynamic Bayesian Networks
No full textAutomatic recognition of abnormal situations in harbor environments is approached in this paper with a system based on Dynamic Bayesian Networks. The area under surveillance is partitioned in zones of different sizes and shapes by means of an Instantaneous Topological Map, on which events are detected and inference is carried out. The model is trained with synthetic normal trajectories of ships and vessels mooring in the port, and each time a new trajectory is presented to the system, comparisons with the normal behaviors stored in the network are performed. If no match is found, an abnormal situation is declared and countermeasures can be taken. The algorithm has been tested in a real port with simulated data in order to evaluate the false alarm rate and the abnormal detection capabilities of the proposed approach
Activity recognition based on inertial sensors for Ambient Assisted Living
No full textAmbient Assisted Living (AAL) aims to create innovative technical solutions and services to support independent living among older adults, improve their quality of life and reduce the costs associated with health and social care. AAL systems provide health monitoring through sensor based technologies to preserve health and functional ability and facilitate social support for the ageing population. Human activity recognition (HAR) is an enabler for the development of robust AAL solutions, especially in safety critical environments. Therefore, HAR models applied within this domain (e.g. for fall detection or for providing contextual information to caregivers) need to be accurate to assist in developing reliable support systems. In this paper, we evaluate three machine learning algorithms, namely Support Vector Machine (SVM), a hybrid of Hidden Markov Models (HMM) and SVM (SVM-HMM) and Artificial Neural Networks (ANNs) applied on a dataset collected between the elderly and their caregiver counterparts. Detected activities will later serve as inputs to a bidirectional activity awareness system for increasing social connectedness. Results show high classification performances for all three algorithms. Specifically, the SVM-HMM hybrid demonstrates the best classification performance. In addition to this, we make our dataset publicly available for use by the machine learning community
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
