Dimitris Kastaniotis

Pose-based human action recognition via sparse representation in dissimilarity space

A framework for pose-based human action recognition is proposed, where coordinates of joints are considered as inputs.By comparing corresponding trajectories, actions are represented by vectors of dissimilarities to a set of prototypes.The task of recognition is performed into the dissimilarity space.The newly created UPCV Action dataset is introduced, consisting of skeletal data for 10 actions.Evaluation on three datasets confirms better performance compared to other pose-based and depth-based methods. Human actions can be considered as a sequence of body poses over time, usually represented by coordinates corresponding to human skeleton models. Recently, a variety of low-cost devices have been released, able to produce markerless real time pose estimation. Nevertheless, limitations of the incorporated RGB-D sensors can produce inaccuracies, necessitating the utilization of alternative representation and classification schemes in order to boost performance. In this context, we propose a method for action recognition where skeletal data are initially processed in order to obtain robust and invariant pose representations and then vectors of dissimilarities to a set of prototype actions are computed. The task of recognition is performed in the dissimilarity space using sparse representation. A new publicly available dataset is introduced in this paper, created for evaluation purposes. The proposed method was also evaluated on other public datasets, and the results are compared to those of similar methods.

HEp-2 cells classification via sparse representation of textural features fused into dissimilarity space

Abstract Autoimmune diseases are proven to be connected with the occurrence of autoantibodies in patient serum. Antinuclear autoantibodies (ANAs) identification can be accomplished in a laboratory using indirect immunofluorescence (IIF) imaging. In this paper a system for automatic classification of staining patterns on HEp-2 fluorescence images is proposed. Our method utilizes two descriptors in order to encode gradient and textural characteristics of the depicted patterns. Along with distribution of SIFT features, we propose the new GoC-LBP descriptor based on co-occurrences of uniform Local Binary Patterns along directions dictated by the orientation of local gradient. At a second stage, the descriptors are fused while creating a dissimilarity representation of an image. A powerful classification scheme is incorporated, utilizing a discriminative sparse representation-based scheme for the classification. Experiments were conducted using a publicly available dataset, comparing the obtained performance to recently reported results of a relevant contest, demonstrating the effectives of the proposed method.

A framework for gait-based recognition using Kinect

Dynamic characteristics of gait are utilized for identity and gender recognition.A new publicly available dataset for gait recognition is presented.Our algorithm can operate extremely well with a small sample training size.The proposed framework follows a biologicaly inspired human motion analysis.The hierarchy of feature representations results in a high level description. Gait analysis has gained new impetus over the past few years. This is mostly due to the launch of low cost depth cameras accompanied with real time pose estimation algorithms. In this work we focus on the problem of human gait recognition. In particular, we propose a modification of a framework originally designed for the task of action recognition and apply it to gait recognition. The new scheme allows us to achieve complex representations of gait sequences and thus express efficiently the dynamic characteristics of human walking sequences. The representational power of the suggested model is evaluated on a publicly available dataset where we achieved up to 93.29% identification rate, 3.1% EER on the verification task and 99.11% gender recognition rate.

Gait based recognition via fusing information from Euclidean and Riemannian manifolds

Pose-based gait recognition using Euclidean and Riemannian feature representations.Euclidean representation is based on a residual aggregation method.Riemannian is based on the covariance representation of a sequence.A new publicly available dataset acquired using Kinect 2 is presented.Fusion and Classification is performed via SRC in RKHS. Gait is a particular periodical type of human motion with several unique characteristics for every person. In this work we focus on the problem of pose based gait recognition. The contribution of the proposed work is threefold. First we represent every gait sequence according to both the deviation of the poses from an appropriate global model, as well as the intra-sequence pose variability. Secondly, we propose a method which allows us to fuse information from feature representations from both Euclidean and Riemannian spaces by mapping data in a Reproducing Kernel Hilbert Space (RKHS). Classification is then performed using a kernelized version of the SRC algorithm. Third we present a new publicly available dataset for pose based gait recognition captured with Kinect V2. Experimental evaluation reveals state-of-the-art performance in both recognition and verification tasks and a capacity for real-time operation.

Pose-based gait recognition with local gradient descriptors and hierarchically aggregated residuals

Abstract. We focus on the problem of pose-based gait recognition. Our contribution is two-fold. First, we incorporate a local histogram descriptor that allows us to encode the trajectories of selected limbs via a one-dimensional version of histogram of oriented gradients features. In this way, a gait sequence is encoded into a sequence of local gradient descriptors. Second, we utilize a robust encoding method in which the residuals of local descriptors, with respect to a discriminative model, are aggregated into fixed length vectors. This technique combines the advantages of both residual aggregation and soft-assignment techniques, resulting in a powerful vector representation. For classification purposes, we use a nonlinear kernel to map vectors into a reproducing kernel Hilbert space. Then, we classify an encoded gait sequence according to the sparse representation-based classification method. Experimental evaluation on two publicly available datasets demonstrates the effectiveness of the proposed scheme on both recognition and verification tasks.

Using kinect for assesing the state of Multiple Sclerosis patients

In this work a prototype video-based system for assessing the state of patients with Multiple sclerosis is proposed. In particular we introduce an automated system for capturing and analyzing gait sequences from patients performing the well known 2-minute walking test. The contribution of this work is twofold. First we provide a computerized approach for performing the 2-minute walk test and showing that there is a great correlation between the estimated by the system walking distance and the distance measured by the physicians (Pearsons Rho= 0.7292, p<;0.001). Second we present some preliminary results indicating that extracted gait style information is able to differentiate between healthy controls (HC) and Multiple Sclerosis patients even when the Extended Disability Status Scale (EDSS) is low. In order to exploit style information we first incorporated a view invariant representation of the skeleton. Then we represented a selected set of limbs using the Euler Angles and we mapped the sequences of features into the dissimilarity space achieving fixed length representation. Classification performed using Linear Discriminant Analysis resulted into an 88.2% correct classification rate. For our experiments we used a total of 9 MS and 8 HC matched in gender and age.

HEp-2 Cell Classification Using Descriptors Fused into the Dissimilarity Space into the Dissimilarity Space

Autoimmune diseases are strictly connected with the presence of autoantibodies in patient serum. Detection of Antinucleolar Antibodies (ANAs) in patient serum is performed using a laboratory technique named Indirect Immunofluorescence (IIF) followed by manual evaluation on the acquired slides from specialized personnel. In this procedure, several limitations appear and several automatic techniques have been proposed for the task of ANA detection. In this work we present a method achieving state-of-the-art performance on a publicly available dataset. More precisely, two powerful and rotation invariant descriptors are incorporated into a two stage classification scheme where the feature vectors are represented and fused in the dissimilarity space. Then, in a second level dissimilarity vectors are classified using a linear SVM classifier. Evaluation on the HEp-2 cell contest dataset yields a 70.16% performance on cell-level classification. Furthermore we provide results in Image Level Classification where a 78.57% classification rate was achieved.