References of "Demisse, Girum 50001642"
     in
Bookmark and Share    
Full Text
Peer Reviewed
See detailLocalized Trajectories for 2D and 3D Action Recognition
Papadopoulos, Konstantinos UL; Demisse, Girum UL; Ghorbel, Enjie UL et al

in Sensors (2019)

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion ... [more ▼]

The Dense Trajectories concept is one of the most successful approaches in action recognition, suitable for scenarios involving a significant amount of motion. However, due to noise and background motion, many generated trajectories are irrelevant to the actual human activity and can potentially lead to performance degradation. In this paper, we propose Localized Trajectories as an improved version of Dense Trajectories where motion trajectories are clustered around human body joints provided by RGB-D cameras and then encoded by local Bag-of-Words. As a result, the Localized Trajectories concept provides an advanced discriminative representation of actions. Moreover, we generalize Localized Trajectories to 3D by using the depth modality. One of the main advantages of 3D Localized Trajectories is that they describe radial displacements that are perpendicular to the image plane. Extensive experiments and analysis were carried out on five different datasets. [less ▲]

Detailed reference viewed: 38 (7 UL)
Full Text
Peer Reviewed
See detailDeformation-Based Abnormal Motion Detection using 3D Skeletons
Baptista, Renato UL; Demisse, Girum UL; Aouada, Djamila UL et al

in IEEE International Conference on Image Processing Theory, Tools and Applications (IPTA) (2018, November)

In this paper, we propose a system for abnormal motion detection using 3D skeleton information, where the abnormal motion is not known a priori. To that end, we present a curve-based representation of a ... [more ▼]

In this paper, we propose a system for abnormal motion detection using 3D skeleton information, where the abnormal motion is not known a priori. To that end, we present a curve-based representation of a sequence, based on few joints of a 3D skeleton, and a deformation-based distance function. We further introduce a time-variation model that is specifically designed for assessing the quality of a motion; we refer to a distance function that is based on such a model as~\emph{motion quality distance}. The overall advantages of the proposed approach are 1) lower dimensional yet representative sequence representation and 2) a distance function that emphasizes time variation, the motion quality distance, which is a particularly important property for quality assessment. We validate our approach using a publicly available dataset, SPHERE-StairCase2014 dataset. Qualitative and quantitative results show promising performance. [less ▲]

Detailed reference viewed: 79 (4 UL)
Full Text
Peer Reviewed
See detailPose Encoding for Robust Skeleton-Based Action Recognition
Demisse, Girum UL; Papadopoulos, Konstantinos UL; Aouada, Djamila UL et al

in CVPRW: Visual Understanding of Humans in Crowd Scene, Salt Lake City, Utah, June 18-22, 2018 (2018, June 18)

Some of the main challenges in skeleton-based action recognition systems are redundant and noisy pose transformations. Earlier works in skeleton-based action recognition explored different approaches for ... [more ▼]

Some of the main challenges in skeleton-based action recognition systems are redundant and noisy pose transformations. Earlier works in skeleton-based action recognition explored different approaches for filtering linear noise transformations, but neglect to address potential nonlinear transformations. In this paper, we present an unsupervised learning approach for estimating nonlinear noise transformations in pose estimates. Our approach starts by decoupling linear and nonlinear noise transformations. While the linear transformations are modelled explicitly the nonlinear transformations are learned from data. Subsequently, we use an autoencoder with L2-norm reconstruction error and show that it indeed does capture nonlinear noise transformations, and recover a denoised pose estimate which in turn improves performance significantly. We validate our approach on a publicly available dataset, NW-UCLA. [less ▲]

Detailed reference viewed: 170 (43 UL)
Full Text
Peer Reviewed
See detailDeformation Based 3D Facial Expression Representation
Demisse, Girum UL; Aouada, Djamila UL; Ottersten, Björn UL

in ACM Transactions on Multimedia Computing, Communications, & Applications (2018)

We propose a deformation based representation for analyzing expressions from 3D faces. A point cloud of a 3D face is decomposed into an ordered deformable set of curves that start from a fixed point ... [more ▼]

We propose a deformation based representation for analyzing expressions from 3D faces. A point cloud of a 3D face is decomposed into an ordered deformable set of curves that start from a fixed point. Subsequently, a mapping function is defined to identify the set of curves with an element of a high dimensional matrix Lie group, specifically the direct product of SE(3). Representing 3D faces as an element of a high dimensional Lie group has two main advantages. First, using the group structure, facial expressions can be decoupled from a neutral face. Second, an underlying non-linear facial expression manifold can be captured with the Lie group and mapped to a linear space, Lie algebra of the group. This opens up the possibility of classifying facial expressions with linear models without compromising the underlying manifold. Alternatively, linear combinations of linearised facial expressions can be mapped back from the Lie algebra to the Lie group. The approach is tested on the BU-3DFE and the Bosphorus datasets. The results show that the proposed approach performed comparably, on the BU-3DFE dataset, without using features or extensive landmark points. [less ▲]

Detailed reference viewed: 177 (23 UL)
Full Text
See detailDeformation Based Curved Shape Representation
Demisse, Girum UL

Doctoral thesis (2017)

Representation and modelling of an objects' shape is critical in object recognition, synthesis, tracking and many other applications in computer vision. As a result, there is a wide range of approaches in ... [more ▼]

Representation and modelling of an objects' shape is critical in object recognition, synthesis, tracking and many other applications in computer vision. As a result, there is a wide range of approaches in formulating representation space and quantifying the notion of similarity between shapes. A similarity metric between shapes is a basic building block in modelling shape categories, optimizing shape valued functionals, and designing a classifier. Consequently, any subsequent shape based computation is fundamentally dependent on the computational efficiency, robustness, and invariance to shape preserving transformations of the defined similarity metric. In this thesis, we propose a novel finite dimensional shape representation framework that leads to a computationally efficient, closed form solution, and noise tolerant similarity distance function. Several important characteristics of the proposed curved shape representation approach are discussed in relation to earlier works. Subsequently, two different solutions are proposed for optimal parameter estimation of curved shapes. Hence, providing two possible solutions for the point correspondence estimation problem between two curved shapes. Later in the thesis, we show that several statistical models can readily be adapted to the proposed shape representation framework for object category modelling. The thesis finalizes by exploring potential applications of the proposed curved shape representation in 3D facial surface and facial expression representation and modelling. [less ▲]

Detailed reference viewed: 204 (91 UL)
Full Text
Peer Reviewed
See detailFacial Expression Recognition via Joint Deep Learning of RGB-Depth Map Latent Representations
Oyedotun, Oyebade UL; Demisse, Girum UL; Shabayek, Abd El Rahman UL et al

in 2017 IEEE International Conference on Computer Vision Workshop (ICCVW) (2017, August 21)

Humans use facial expressions successfully for conveying their emotional states. However, replicating such success in the human-computer interaction domain is an active research problem. In this paper, we ... [more ▼]

Humans use facial expressions successfully for conveying their emotional states. However, replicating such success in the human-computer interaction domain is an active research problem. In this paper, we propose deep convolutional neural network (DCNN) for joint learning of robust facial expression features from fused RGB and depth map latent representations. We posit that learning jointly from both modalities result in a more robust classifier for facial expression recognition (FER) as opposed to learning from either of the modalities independently. Particularly, we construct a learning pipeline that allows us to learn several hierarchical levels of feature representations and then perform the fusion of RGB and depth map latent representations for joint learning of facial expressions. Our experimental results on the BU-3DFE dataset validate the proposed fusion approach, as a model learned from the joint modalities outperforms models learned from either of the modalities. [less ▲]

Detailed reference viewed: 314 (51 UL)
Full Text
Peer Reviewed
See detailDeformation Based Curved Shape Representation
Demisse, Girum UL; Aouada, Djamila UL; Ottersten, Björn UL

in IEEE Transactions on Pattern Analysis & Machine Intelligence (2017)

In this paper, we introduce a deformation based representation space for curved shapes in Rn. Given an ordered set of points sampled from a curved shape, the proposed method represents the set as an ... [more ▼]

In this paper, we introduce a deformation based representation space for curved shapes in Rn. Given an ordered set of points sampled from a curved shape, the proposed method represents the set as an element of a finite dimensional matrix Lie group. Variation due to scale and location are filtered in a preprocessing stage, while shapes that vary only in rotation are identified by an equivalence relationship. The use of a finite dimensional matrix Lie group leads to a similarity metric with an explicit geodesic solution. Subsequently, we discuss some of the properties of the metric and its relationship with a deformation by least action. Furthermore, invariance to reparametrization or estimation of point correspondence between shapes is formulated as an estimation of sampling function. Thereafter, two possible approaches are presented to solve the point correspondence estimation problem. Finally, we propose an adaptation of k-means clustering for shape analysis in the proposed representation space. Experimental results show that the proposed representation is robust to uninformative cues, e.g. local shape perturbation and displacement. In comparison to state of the art methods, it achieves a high precision on the Swedish and the Flavia leaf datasets and a comparable result on MPEG-7, Kimia99 and Kimia216 datasets. [less ▲]

Detailed reference viewed: 307 (53 UL)
Full Text
Peer Reviewed
See detailSimilarity Metric For Curved Shapes In Euclidean Space
Demisse, Girum UL; Aouada, Djamila UL; Ottersten, Björn UL

in IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2016 (2016, June 26)

In this paper, we introduce a similarity metric for curved shapes that can be described, distinctively, by ordered points. The proposed method represents a given curve as a point in the deformation space ... [more ▼]

In this paper, we introduce a similarity metric for curved shapes that can be described, distinctively, by ordered points. The proposed method represents a given curve as a point in the deformation space, the direct product of rigid transformation matrices, such that the successive action of the matrices on a fixed starting point reconstructs the full curve. In general, both open and closed curves are represented in the deformation space modulo shape orientation and orientation preserving diffeomorphisms. The use of direct product Lie groups to represent curved shapes led to an explicit formula for geodesic curves and the formulation of a similarity metric between shapes by the $L^{2}$-norm on the Lie algebra. Additionally, invariance to reparametrization or estimation of point correspondence between shapes is performed as an intermediate step for computing geodesics. Furthermore, since there is no computation of differential quantities on the curves, our representation is more robust to local perturbations and needs no pre-smoothing. We compare our method with the elastic shape metric defined through the square root velocity (SRV) mapping, and other shape matching approaches [less ▲]

Detailed reference viewed: 351 (54 UL)
Full Text
Peer Reviewed
See detailVisual and human-interpretable feedback for assisting physical activity
Goncalves Almeida Antunes, Michel UL; Baptista, Renato UL; Demisse, Girum UL et al

in European Conference on Computer Vision (ECCV) Workshop on Assistive Computer Vision and Robotics Amsterdam, (2016)

Physical activity is essential for stroke survivors for recovering some autonomy in daily life activities. Post-stroke patients are initially subject to physical therapy under the supervision of a health ... [more ▼]

Physical activity is essential for stroke survivors for recovering some autonomy in daily life activities. Post-stroke patients are initially subject to physical therapy under the supervision of a health professional, but due to economical aspects, home based rehabilitation is eventually suggested. In order to support the physical activity of stroke patients at home, this paper presents a system for guiding the user in how to properly perform certain actions and movements. This is achieved by presenting feedback in form of visual information and human-interpretable messages. The core of the proposed approach is the analysis of the motion required for aligning body-parts with respect to a template skeleton pose, and how this information can be presented to the user in form of simple recommendations. Experimental results in three datasets show the potential of the proposed framework. [less ▲]

Detailed reference viewed: 272 (45 UL)
Full Text
Peer Reviewed
See detailTemplate-Based Statistical Shape Modelling on Deformation Space
Demisse, Girum UL; Aouada, Djamila UL; Ottersten, Björn UL

in 22nd IEEE International Conference on Image Processing (2015)

A statistical model for shapes in $\mathbb{R}^2$ or $\mathbb{R}^3$ is proposed. Shape modelling is a difficult problem mainly due to the non-linear nature of its space. Our approach considers curves as ... [more ▼]

A statistical model for shapes in $\mathbb{R}^2$ or $\mathbb{R}^3$ is proposed. Shape modelling is a difficult problem mainly due to the non-linear nature of its space. Our approach considers curves as shape contours, and models their deformations with respect to a deformable template shape. Contours are uniformly sampled into a discrete sequence of points. Hence, the deformation of a shape is formulated as an action of transformation matrices on each of these points. A parametrized stochastic model based on Markov process is proposed to model shape variability in the deformation space. The model's parameters are estimated from a labeled training dataset. Moreover, a similarity metric based on the Mahalanobis distance is proposed. Subsequently, the model has been successfully tested for shape recognition, synthesis, and retrieval. [less ▲]

Detailed reference viewed: 218 (52 UL)
Full Text
Peer Reviewed
See detailInterpreting Thermal 3D Models of Indoor Environments for Energy Efficiency
Demisse, Girum UL; Borrman, Dorit; Nuchter, Andreas

in In Journal of Intelligent and Robotic Systems, Springer (2014)

In recent years 3D models of buildings are used in maintenance and inspection, preservation, and other building related applications. However, the usage of these models is limited because most models are ... [more ▼]

In recent years 3D models of buildings are used in maintenance and inspection, preservation, and other building related applications. However, the usage of these models is limited because most models are pure representations with no or little associated semantics. In this paper we present a pipeline of techniques used for interior interpretation, object detection, and adding energy related semantics to windows of a 3D thermal model. A sequence of algorithms is presented for building the fundamental semantics of a 3D model. Among other things, these algorithms enable the system to differentiate between objects in a room and objects that are part of the room, e.g. floor, windows. Subsequently, the thermal information is used to construct a stochastic mathematical model - namely Markov Random Field - of the temperature distribution of the detected windows. As a result, the MAP (Maximum a posteriori) framework is used to further label the windows as either open, closed or damaged based upon their temperature distribution. The experimental results showed the robustness of the techniques. Furthermore, a strategy to optimize the free parameters is described, in cases where there is ample training dataset. [less ▲]

Detailed reference viewed: 113 (21 UL)