Supervised latent dirichlet allocation models for efficient activity representation

Local spatio-temporal features with a Bag-of-visual words model is a popular approach used in human action recognition. Bag-of-features methods suffer from several challenges such as extracting appropriate appearance and motion features from videos, converting extracted features appropriate for classification and designing a suitable classification framework. In this paper we address the problem of efficiently representing the extracted features for classification to improve the overall performance. We introduce two generative supervised topic models, maximum entropy discrimination LDA (MedLDA) and class- specific simplex LDA (css-LDA), to encode the raw features suitable for discriminative SVM based classification. Unsupervised LDA models disconnect topic discovery from the classification task, hence yield poor results compared to the baseline Bag-of-words framework. On the other hand supervised LDA techniques learn the topic structure by considering the class labels and improve the recognition accuracy significantly. MedLDA maximizes likelihood and within class margins using max-margin techniques and yields a sparse highly discriminative topic structure; while in css-LDA separate class specific topics are learned instead of common set of topics across the entire dataset. In our representation first topics are learned and then each video is represented as a topic proportion vector, i.e. it can be comparable to a histogram of topics. Finally SVM classification is done on the learned topic proportion vector. We demonstrate the efficiency of the above two representation techniques through the experiments carried out in two popular datasets. Experimental results demonstrate significantly improved performance compared to the baseline Bag-of-features framework which uses kmeans to construct histogram of words from the feature vectors.

A Cause and Effect Analysis of Motion Trajectories for Modeling Actions

An action is typically composed of different parts of the object moving in particular sequences. The presence of different motions (represented as a 1D histogram) has been used in the traditional bag-of-words (BoW) approach for recognizing actions. However the interactions among the motions also form a crucial part of an action. Different object-parts have varying degrees of interactions with the other parts during an action cycle. It is these interactions we want to quantify in order to bring in additional information about the actions. In this paper we propose a causality based approach for quantifying the interactions to aid action classification. Granger causality is used to compute the cause and effect relationships for pairs of motion trajectories of a video. A 2D histogram descriptor for the video is constructed using these pairwise measures. Our proposed method of obtaining pairwise measures for videos is also applicable for large datasets. We have conducted experiments on challenging action recognition databases such as HMDB51 and UCF50 and shown that our causality descriptor helps in encoding additional information regarding the actions and performs on par with the state-of-the art approaches. Due to the complementary nature, a further increase in performance can be observed by combining our approach with state-of-the-art approaches.

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

A coupled discriminative dictionary and transformation learning approach with applications to cross domain matching

Cross domain and cross-modal matching has many applications in the field of computer vision and pattern recognition. A few examples are heterogeneous face recognition, cross view action recognition, etc. This is a very challenging task since the data in two domains can differ significantly. In this work, we propose a coupled dictionary and transformation learning approach that models the relationship between the data in both domains. The approach learns a pair of transformation matrices that map the data in the two domains in such a manner that they share common sparse representations with respect to their own dictionaries in the transformed space. The dictionaries for the two domains are learnt in a coupled manner with an additional discriminative term to ensure improved recognition performance. The dictionaries and the transformation matrices are jointly updated in an iterative manner. The applicability of the proposed approach is illustrated by evaluating its performance on different challenging tasks: face recognition across pose, illumination and resolution, heterogeneous face recognition and cross view action recognition. Extensive experiments on five datasets namely, CMU-PIE, Multi-PIE, ChokePoint, HFB and IXMAS datasets and comparisons with several state-of-the-art approaches show the effectiveness of the proposed approach. (C) 2015 Elsevier B.V. All rights reserved.

State estimation schemes for independent component coupled hidden Markov models

Conventional Hidden Markov models generally consist of a Markov chain observed through a linear map corrupted by additive noise. This general class of model has enjoyed a huge and diverse range of applications, for example, speech processing, biomedical signal processing and more recently quantitative finance. However, a lesser known extension of this general class of model is the so-called Factorial Hidden Markov Model (FHMM). FHMMs also have diverse applications, notably in machine learning, artificial intelligence and speech recognition [13, 17]. FHMMs extend the usual class of HMMs, by supposing the partially observed state process is a finite collection of distinct Markov chains, either statistically independent or dependent. There is also considerable current activity in applying collections of partially observed Markov chains to complex action recognition problems, see, for example, [6]. In this article we consider the Maximum Likelihood (ML) parameter estimation problem for FHMMs. Much of the extant literature concerning this problem presents parameter estimation schemes based on full data log-likelihood EM algorithms. This approach can be slow to converge and often imposes heavy demands on computer memory. The latter point is particularly relevant for the class of FHMMs where state space dimensions are relatively large. The contribution in this article is to develop new recursive formulae for a filter-based EM algorithm that can be implemented online. Our new formulae are equivalent ML estimators, however, these formulae are purely recursive and so, significantly reduce numerical complexity and memory requirements. A computer simulation is included to demonstrate the performance of our results. © Taylor & Francis Group, LLC.

Vidéosurveillance intelligente pour la détection de chutes chez les personnes âgées

Les pays industrialisés comme le Canada doivent faire face au vieillissement de leur population. En particulier, la majorité des personnes âgées, vivant à domicile et souvent seules, font face à des situations à risques telles que des chutes. Dans ce contexte, la vidéosurveillance est une solution innovante qui peut leur permettre de vivre normalement dans un environnement sécurisé. L’idée serait de placer un réseau de caméras dans l’appartement de la personne pour détecter automatiquement une chute. En cas de problème, un message pourrait être envoyé suivant l’urgence aux secours ou à la famille via une connexion internet sécurisée. Pour un système bas coût, nous avons limité le nombre de caméras à une seule par pièce ce qui nous a poussé à explorer les méthodes monoculaires de détection de chutes. Nous avons d’abord exploré le problème d’un point de vue 2D (image) en nous intéressant aux changements importants de la silhouette de la personne lors d’une chute. Les données d’activités normales d’une personne âgée ont été modélisées par un mélange de gaussiennes nous permettant de détecter tout événement anormal. Notre méthode a été validée à l’aide d’une vidéothèque de chutes simulées et d’activités normales réalistes. Cependant, une information 3D telle que la localisation de la personne par rapport à son environnement peut être très intéressante pour un système d’analyse de comportement. Bien qu’il soit préférable d’utiliser un système multi-caméras pour obtenir une information 3D, nous avons prouvé qu’avec une seule caméra calibrée, il était possible de localiser une personne dans son environnement grâce à sa tête. Concrêtement, la tête de la personne, modélisée par une ellipsoide, est suivie dans la séquence d’images à l’aide d’un filtre à particules. La précision de la localisation 3D de la tête a été évaluée avec une bibliothèque de séquence vidéos contenant les vraies localisations 3D obtenues par un système de capture de mouvement (Motion Capture). Un exemple d’application utilisant la trajectoire 3D de la tête est proposée dans le cadre de la détection de chutes. En conclusion, un système de vidéosurveillance pour la détection de chutes avec une seule caméra par pièce est parfaitement envisageable. Pour réduire au maximum les risques de fausses alarmes, une méthode hybride combinant des informations 2D et 3D pourrait être envisagée.

Reconnaissance des actions humaines : méthode basée sur la réduction de dimensionnalité par MDS spatio-temporelle

L’action humaine dans une séquence vidéo peut être considérée comme un volume spatio- temporel induit par la concaténation de silhouettes dans le temps. Nous présentons une approche spatio-temporelle pour la reconnaissance d’actions humaines qui exploite des caractéristiques globales générées par la technique de réduction de dimensionnalité MDS et un découpage en sous-blocs afin de modéliser la dynamique des actions. L’objectif est de fournir une méthode à la fois simple, peu dispendieuse et robuste permettant la reconnaissance d’actions simples. Le procédé est rapide, ne nécessite aucun alignement de vidéo, et est applicable à de nombreux scénarios. En outre, nous démontrons la robustesse de notre méthode face aux occultations partielles, aux déformations de formes, aux changements d’échelle et d’angles de vue, aux irrégularités dans l’exécution d’une action, et à une faible résolution.

Heterogeneous Multi-Robot Cooperation

This report addresses the problem of achieving cooperation within small- to medium- sized teams of heterogeneous mobile robots. I describe a software architecture I have developed, called ALLIANCE, that facilitates robust, fault tolerant, reliable, and adaptive cooperative control. In addition, an extended version of ALLIANCE, called L-ALLIANCE, is described, which incorporates a dynamic parameter update mechanism that allows teams of mobile robots to improve the efficiency of their mission performance through learning. A number of experimental results of implementing these architectures on both physical and simulated mobile robot teams are described. In addition, this report presents the results of studies of a number of issues in mobile robot cooperation, including fault tolerant cooperative control, adaptive action selection, distributed control, robot awareness of team member actions, improving efficiency through learning, inter-robot communication, action recognition, and local versus global control.

Reduced cortico-motor facilitation in a normal sample with high traits of autism

Recent research in social neuroscience proposes a link between mirror neuron system (MNS) and social cognition. The MNS has been proposed to be the neural mechanism underlying action recognition and intention understanding and more broadly social cognition. Pre-motor MNS has been suggested to modulate the motor cortex during action observation. This modulation results in an enhanced cortico-motor excitability reflected in increased motor evoked potentials (MEPs) at the muscle of interest during action observation. Anomalous MNS activity has been reported in the autistic population whose social skills are notably impaired. It is still an open question whether traits of autism in the normal population are linked to the MNS functioning. We measured TMS-induced MEPs in normal individuals with high and low traits of autism as measured by the autistic quotient (AQ), while observing videos of hand or mouth actions, static images of a hand or mouth or a blank screen. No differences were observed between the two while they observed a blank screen. However participants with low traits of autism showed significantly greater MEP amplitudes during observation of hand/mouth actions relative to static hand/mouth stimuli. In contrast, participants with high traits of autism did not show such a MEP amplitude difference between observation of actions and static stimuli. These results are discussed with reference to MNS functioning.

Modelling human behaviour and event detection from videos

Automatic analysis of human behaviour in large collections of videos is gaining interest, even more so with the advent of file sharing sites such as YouTube. However, challenges still exist owing to several factors such as inter- and intra-class variations, cluttered backgrounds, occlusion, camera motion, scale, view and illumination changes. This research focuses on modelling human behaviour for action recognition in videos. The developed techniques are validated on large scale benchmark datasets and applied on real-world scenarios such as soccer videos. Three major contributions are made. The first contribution is in the area of proper choice of a feature representation for videos. This involved a study of state-of-the-art techniques for action recognition, feature extraction processing and dimensional reduction techniques so as to yield the best performance with optimal computational requirements. Secondly, temporal modelling of human behaviour is performed. This involved frequency analysis and temporal integration of local information in the video frames to yield a temporal feature vector. Current practices mostly average the frame information over an entire video and neglect the temporal order. Lastly, the proposed framework is applied and further adapted to real-world scenario such as soccer videos. A dataset consisting of video sequences depicting events of players falling is created from actual match data to this end and used to experimentally evaluate the proposed framework.

Recognition of Human Action Using Moment-Based Feature

The performance of different classification approaches is evaluated using a view-based approach for motion representation. The view-based approach uses computer vision and image processing techniques to register and process the video sequence. Two motion representations called Motion Energy Images and Motion History Image are then constructed. These representations collapse the temporal component in a way that no explicit temporal analysis or sequence matching is needed. Statistical descriptions are then computed using moment-based features and dimensionality reduction techniques. For these tests, we used 7 Hu moments, which are invariant to scale and translation. Principal Components Analysis is used to reduce the dimensionality of this representation. The system is trained using different subjects performing a set of examples of every action to be recognized. Given these samples, K-nearest neighbor, Gaussian, and Gaussian mixture classifiers are used to recognize new actions. Experiments are conducted using instances of eight human actions (i.e., eight classes) performed by seven different subjects. Comparisons in the performance among these classifiers under different conditions are analyzed and reported. Our main goals are to test this dimensionality-reduced representation of actions, and more importantly to use this representation to compare the advantages of different classification approaches in this recognition task.