Light-weight salient foreground detection for embedded smart cameras

An embedded smart camera is a stand-alone unit that not only captures images, but also includes a processor, memory and communication interface. Battery-powered, embedded smart cameras introduce many additional challenges since they have very limited resources, such as energy, processing power and memory. Computer vision algorithms running on these camera boards should be light-weight and efficient. Considering the memory requirements of an algorithm and its portability to an embedded processor should be an integral part of the algorithm design in addition to the accuracy requirements. This paper presents a light-weight and efficient background modeling and foreground detection algorithm that is highly robust against lighting variations and non-static backgrounds including scenes with swaying trees, water fountains and rain. Compared to many traditional methods, the memory requirement for the data saved for each pixel is very small in the proposed algorithm. Moreover, the number of memory accesses and instructions are adaptive, and are decreased depending on the amount of activity in the scene. Each pixel is treated differently based on its history, and instead of requiring the same number of memory accesses and instructions for every pixel, we require less instructions for stable background pixels. The plot of the number of unstable pixels at each frame also serves as a tool to find the video portions with high activity. The proposed method selectively updates the background model with an automatically adaptive rate, thus can adapt to rapid changes. As opposed to traditional methods, pixels are not always treated individually, and information about neighbors is incorporated into decision making. The results obtained with nine challenging outdoor and indoor sequences are presented, and compared with the results of different state-of-the-art background subtraction methods. The ROC curves and memory comparison of different background subtraction methods are also provided. The experimental results demonstrate the success of the proposed light-weight salient foreground detection method.     

A UML/OCL framework for the analysis of graph transformation rules

In this paper we present an approach for the analysis of graph transformation rules based on an intermediate OCL representation. We translate different rule semantics into OCL, together with the properties of interest (like rule applicability, conflicts or independence). The intermediate representation serves three purposes: (1) it allows the seamless integration of graph transformation rules with the MOF and OCL standards, and enables taking the meta-model and its OCL constraints (i.e. well-formedness rules) into account when verifying the correctness of the rules; (2) it permits the interoperability of graph transformation concepts with a number of standards-based model-driven development tools; and (3) it makes available a plethora of OCL tools to actually perform the rule analysis. This approach is especially useful to analyse the operational semantics of Domain Specific Visual Languages. We have automated these ideas by providing designers with tools for the graphical specification and analysis of graph transformation rules, including a back-annotation mechanism that presents the analysis results in terms of the original language notation.     

Time-extended multi-robot coordination for domains with intra-path constraints

Many applications require teams of robots to cooperatively execute tasks. Among these domains are those in which successful coordination must respect intra-path constraints, which are constraints that occur on the paths of agents and affect route planning. This work focuses on multi-agent coordination for disaster response with intra-path precedence constraints, a compelling application that is not well addressed by current coordination methods. In this domain a group of fire truck agents attempt to address fires spread throughout a city in the wake of a large-scale disaster. The disaster has also caused many city roads to be blocked by impassable debris, which can be cleared by bulldozer robots. A high-quality coordination solution must determine not only a task allocation but also what routes the fire trucks should take given the intra-path precedence constraints and which bulldozers should be assigned to clear debris along those routes.     

Shape-sensitive MLS deformation

This work presents methods for deforming meshes in a shape-sensitive way using Moving Least Squares (MLS) optimization. It extends an approach for deforming space (Cuno et al. in Proceedings of the 27th Computer Graphics International Conference, pp. 115–122, 2007) by showing how custom distance metrics may be used to achieve deformations which preserve the overall mesh shape. Several variant formulations are discussed and demonstrated, including the use of geodesic distances, distances constrained to paths contained in the mesh, the use of skeletons, and a reformulation of the MLS scheme which makes it possible to affect the bending behavior of the deformation. Finally, aspects of the implementation of these techniques in parallel architectures such as GPUs (graphics processing units) are described and compared with CPU-only implementations.     

Performance analysis of allocation policies for interGrid resource provisioning

Several Grids have been established and used for varying science applications during the last years. Most of these Grids, however, work in isolation and with different utilisation levels. Previous work has introduced an architecture and a mechanism to enable resource sharing amongst Grids. It has demonstrated that there can be benefits for a Grid to offload requests or provide spare resources to another Grid. In this work, we address the problem of resource provisioning to Grid applications in multiple-Grid environments. The provisioning is carried out based on availability information obtained from queueing-based resource management systems deployed at the provider sites which are the participants of the Grids. We evaluate the performance of different allocation policies. In contrast to existing work on load sharing across Grids, the policies described here take into account the local load of resource providers, imprecise availability information and the compensation of providers for the resources offered to the Grid. In addition, we evaluate these policies along with a mechanism that allows resource sharing amongst Grids. Experimental results obtained through simulation show that the mechanism and policies are effective in redirecting requests thus improving the applications’ average weighted response time.     

Towards human motion capture from a camera mounted on a mobile robot

This article describes a multiple feature data fusion applied to a particle filter for marker-less human motion capture (HMC) by using a single camera devoted to an assistant mobile robot. Particle filters have proved to be well suited to this robotic context. Like numerous approaches, the principle relies on the projection of the model's silhouette of the tracked human limbs and appearance features located on the model surface, to validate the particles (associated configurations) which correspond to the best model-to-image fits. Our particle filter based HMC system is improved and extended in two ways. First, our estimation process is based on the so-called AUXILIARY scheme which has been surprisingly seldom exploited for tracking purpose. This scheme is shown to outperform conventional particle filters as it limits drastically the well-known burst in term of particles when considering high dimensional state-space. The second line of investigation concerns data fusion. Data fusion is considered both in the importance and measurement functions with some degree of adaptability depending on the current human posture and the environmental context encountered by the robot. Implementation and experiments on indoor sequences acquired by an assistant mobile robot highlight the relevance and versatility of our HMC system. Extensions are finally discussed.     

Fault detection and isolation in robotic manipulators via neural networks: A comparison among three architectures for residual analysis

In this article we discuss artificial neural networks‐based fault detection and isolation (FDI) applications for robotic manipulators. The artificial neural networks (ANNs) are used for both residual generation and residual analysis. A multilayer perceptron (MLP) is employed to reproduce the dynamics of the robotic manipulator. Its outputs are compared with actual position and velocity measurements, generating the so‐called residual vector. The residuals, when properly analyzed, provides an indication of the status of the robot (normal or faulty operation). Three ANNs architectures are employed in the residual analysis. The first is a radial basis function network (RBFN) which uses the residuals of position and velocity to perform fault identification. The second is again an RBFN, except that it uses only the velocity residuals. The third is an MLP which also performs fault identification utilizing only the velocity residuals. The MLP is trained with the classical back‐propagation algorithm and the RBFN is trained with a Kohonen self‐organizing map (KSOM). We validate the concepts discussed in a thorough simulation study of a Puma 560 and with experimental results with a 3‐joint planar manipulator. © 2001 John Wiley & Sons, Inc.     

Visual specification of measurements and redesigns for domain specific visual languages

Ensuring model quality is a key success factor in many computer science areas, and becomes crucial in recent software engineering paradigms like the one proposed by model-driven software development. Tool support for measurements and redesigns becomes essential to help developers improve the quality of their models. However, developing such helper tools for the wide variety of (frequently domain specific) visual notations used by software engineers is a hard and repetitive task that does not take advantage from previous developments, thus being frequently forgotten.In this paper we present our approach for the visual specification of measurements and redesigns for Domain Specific Visual Languages (DSVLs). With this purpose, we introduce a novel DSVL called SLAMMER that contains generalisations of some of the more used types of internal product measurements and redesigns. The goal is to facilitate the task of defining measurements and redesigns for any DSVL, as well as the generation of tools from such specification reducing or eliminating the necessity of coding. We rely on the use of visual patterns for the specification of the relevant elements for each measurement and redesign type. In addition, SLAMMER allows the specification of redesigns either procedurally or by means of graph transformation rules. These redesigns can be triggered when the measurements reach a certain threshold.These concepts have been implemented in the meta-modelling tool AToM³. In this way, when a DSVL is designed, it is possible to specify measurements and redesigns that will become available in the final modelling environment generated for the language. As an example, we show a case study in the web modelling domain.     

Urinary proteomic analysis of chronic allograft nephropathy

The pathogenesis of progressive renal allograft injury, which is termed chronic allograft nephropathy (CAN), remains obscure and is currently defined by histology. Prospective protocol-biopsy trials have demonstrated that clinical and standard laboratory tests are insufficiently sensitive indicators of the development and progression of CAN. The study aim was to determine if CAN could be characterized by urinary proteomic data and identify the proteins associated with disease. The urinary proteome of 75 renal transplant recipients and 20 healthy volunteers was analyzed using surface enhanced laser desorption and ionization MS. Patients could be classified into subgroups with normal histology and Banff CAN grades 2-3 with a sensitivity of 86% and a specificity of 92% by applying the classification algorithm Adaboost to urinary proteomic data. Several urinary proteins associated with advanced CAN were identified including α1-microglobulin, β2-microglobulin, prealbumin, and endorepellin, the antiangiogenic C-terminal fragment of perlecan. Increased urinary endorepellin was confirmed by ELISA and increased tissue expression of the endorepellin/perlecan ratio by immunofluoresence analysis of renal biopsies. In conclusion, analysis of urinary proteomic data has further characterized the more severe CAN grades and identified urinary endorepellin, as a potential biomarker of advanced CAN.     

Medical Positron Imaging with a Dense Drift Space MultiWire Proportional Chamber

A multiplanar positron camera is proposed, made of six MWPC modules, arranged to form the lateral surface of a hexagonal prism. Each 50 x 50 cm(2) module has a single MWPC sandwiched by two 2-cm thick lead glass tube converters. The experimental results for a 15 x 15 cm(2) test module are reported. For 511 keV gamma-rays incident almost perpendicular onto a 1.0-cm thick converter, a detection efficiency of 4.3%, a time resolution of 130 ns (FWHM) and a spatial resolution of 2.8 mm (FWHM) have been measured with a standard Argon-Methane (70-30) mixture at 1.2 atm. The chamber may also be operated in high resolution mode: 1.2-mm (FWHM) spatial resolution has been measured at a 50% lower efficiency. The use of fast delay lines (specific delay 8 ns/cm) for the position read-out ensures a high rate capability. The expected performance of the six-module MWPC camera is discussed and compared with that of a BGO crystal ring camera. The MWPC solution seems very attractive not only for its low cost and simplicity of construction, but also for its fully three-dimensional imaging capability.