Dynamic action recognition based on dynemes and Extreme Learning Machine

In this paper, we propose a novel method that performs dynamic action classification by exploiting the effectiveness of the Extreme Learning Machine (ELM) algorithm for single hidden layer feedforward neural networks training. It involves data grouping and ELM based data projection in multiple levels. Given a test action instance, a neural network is trained by using labeled action instances forming the groups that reside to the test sample’s neighborhood. The action instances involved in this procedure are, subsequently, mapped to a new feature space, determined by the trained network outputs. This procedure is performed multiple times, which are determined by the test action instance at hand, until only a single class is retained. Experimental results denote the effectiveness of the dynamic classification approach, compared to the static one, as well as the effectiveness of the ELM in the proposed dynamic classification setting.     

Motion-based segmentation of objects using overlapping temporal windows

Motion segmentation refers to the problem of separating the objects in a video sequence according to their motion. It is a fundamental problem of computer vision, since various systems focusing on the analysis of dynamic scenes include motion segmentation algorithms. In this paper we present a novel approach, where a video shot is temporally divided in successive and overlapping windows and motion segmentation is performed on each window respectively. This attribute renders the algorithm suitable even for long video sequences. In the last stage of the algorithm the segmentation results for every window are aggregated into a final segmentation. The presented algorithm can handle effectively asynchronous trajectories on each window even when they have no temporal intersection. The evaluation of the proposed algorithm on the Berkeley motion segmentation benchmark demonstrates its scalability and accuracy compared to the state of the art.     

Subclass discriminant Nonnegative Matrix Factorization for facial image analysis

Nonnegative Matrix Factorization (NMF) is among the most popular subspace methods, widely used in a variety of image processing problems. Recently, a discriminant NMF method that incorporates Linear Discriminant Analysis inspired criteria has been proposed, which achieves an efficient decomposition of the provided data to its discriminant parts, thus enhancing classification performance. However, this approach possesses certain limitations, since it assumes that the underlying data distribution is unimodal, which is often unrealistic. To remedy this limitation, we regard that data inside each class have a multimodal distribution, thus forming clusters and use criteria inspired by Clustering based Discriminant Analysis. The proposed method incorporates appropriate discriminant constraints in the NMF decomposition cost function in order to address the problem of finding discriminant projections that enhance class separability in the reduced dimensional projection space, while taking into account subclass information. The developed algorithm has been applied for both facial expression and face recognition on three popular databases. Experimental results verified that it successfully identified discriminant facial parts, thus enhancing recognition performance.     

Multi-view human movement recognition based on fuzzy distances and linear discriminant analysis

In this paper, a novel multi-view human movement recognition method is presented. A novel representation of multi-view human movement videos is proposed that is based on learning basic multi-view human movement primitives, called multi-view dynemes. The movement video is represented in a new feature space (called dyneme space) using these multi-view dynemes, thus producing a time invariant multi-view movement representation. Fuzzy distances from the multi-view dynemes are used to represent the human body postures in the dyneme space. Three variants of Linear Discriminant Analysis (LDA) are evaluated to achieve a discriminant movement representation in a low dimensionality space. The view identification problem is solved either by using a circular block shift procedure followed by the evaluation of the minimum Euclidean distance from any dyneme, or by exploiting the circular shift invariance property of the Discrete Fourier Transform (DFT). The discriminant movement representation combined with camera viewpoint identification and a nearest centroid classification step leads to a high human movement classification accuracy.     

Visual understanding industrial workflows under uncertainty on distributed service oriented architectures

Service Oriented Architecture (SOA) is an evolution of distributed computing based on the request/reply design paradigm for synchronous and asynchronous applications. In such architectures, application developers or system integrators can build scenarios by composing one or more services without knowing the services’ underlying implementations. In this paper, we adopt a SOA framework for on-line scheduling complex industrial workflows. The proposed SOA consists of three main layers; the input layer, the benchmarking layer, the prediction layer and the scheduler. The main innovation of our SOA architecture is the prediction layer that supports computer vision tools able to visually observe how an industrial workflow is actually executed. This way, we can automatically estimate the actual execution time for a process. In particular a new self-initialized visual tracker algorithm is proposed in this paper to robustly trace workers’ trajectory in a plant via visual observations. Then, part-to-whole curve matching is presented so as to find correspondences among the traced curve and the ideal one and thus improving scheduler efficiency. The input layer interoperably describes industrial operations using the XPDL (an XML-based) format. The benchmarker evaluates much faster than real-time and in an off-line mode how long it takes for an industrial workflow to be executed on a given resource guaranteeing an almost real-time implementation of the video processing algorithms on the plant. The last component of the proposed SOA is the scheduler with the goal to assign the workflows to the available resources. In this paper, a Maximum Benefit First (MBF) scheduler is presented which maximizes the total gain received by the industry when completing execution of all the beneficial operations with minimum violations of their delivery deadlines (that is with the minimum compensations). Experiments have been conducted on a real-world industrial plant of Nissan Iberica automobile construction indicating the efficiency of the proposed system.     

Blind robust watermarking schemes for copyright protection of 3D mesh objects

In this paper, two novel methods suitable for blind 3D mesh object watermarking applications are proposed. The first method is robust against 3D rotation, translation, and uniform scaling. The second one is robust against both geometric and mesh simplification attacks. A pseudorandom watermarking signal is cast in the 3D mesh object by deforming its vertices geometrically, without altering the vertex topology. Prior to watermark embedding and detection, the object is rotated and translated so that its center of mass and its principal component coincide with the origin and the z-axis of the Cartesian coordinate system. This geometrical transformation ensures watermark robustness to translation and rotation. Robustness to uniform scaling is achieved by restricting the vertex deformations to occur only along the r coordinate of the corresponding (r, /spl theta/, /spl phi/) spherical coordinate system. In the first method, a set of vertices that correspond to specific angles /spl theta/ is used for watermark embedding. In the second method, the samples of the watermark sequence are embedded in a set of vertices that correspond to a range of angles in the /spl theta/ domain in order to achieve robustness against mesh simplifications. Experimental results indicate the ability of the proposed method to deal with the aforementioned attacks.     

Optimal Robot Speed Trajectory by Minimization of the Actuator Motor Electromechanical Losses

This paper considers the control problem of a robotic manipulator with separately excited dc motor drives as actuators. An innovative method is proposed which achieves robot speed-control requirements, with simultaneous minimization of total electromechanical losses, while the drives follow the desired speed profiles of the robot joints under various loads and random load disturbances. If there is no demand for a specific speed profile, the optimal speed trajectory is determined by minimizing an electromechanical losses criterion. Controllable energy losses, such as armature copper losses, armature iron losses, field copper losses, stray load losses, brush load losses, friction and windage losses, can be expressed proportionally to the squares of the armature and the field (exciting) currents, the angular velocity and the magnetic field flux. The controllable energy loss term is also included in the optimal control integral quadratic performance index, defined for the whole operation period. Thus the appropriate control signals required for following the desired trajectory by simultaneous energy loss minimization for the whole operation interval are achieved. Two case studies of optimal robot control with and without minimization of actuator energy losses are presented and compared, showing the energy savings that can be achieved by the proposed methodology.     

Caricature generation utilizing the notion of anti-face

The production of caricatures is a particularly interesting field of art, because it aims to highlight the very essence of a given face. Caricature generation systems traditionally rely on two approaches: they either follow extracted rules through learning algorithms, or follow rules that were directly programmed by experts. This paper attempts to reduce the reliance on heuristic methods, by proposing a novel method that provides a set of well-defined rules, which can be put to use for the purpose of caricature generation. The method is based on the notion of anti-face in conjunction with unbiased distortions. In addition, we indicate the usefulness of the anti-face as a means to perceive, for our own sake, the degree to which our face seems peculiar to others. Finally, we deploy a reverse variant of the method in order to attain beautification.