Current Issue : July - September Volume : 2014 Issue Number : 3 Articles : 6 Articles
Automatic video annotation has become an important issue in visual sensor networks, due to the existence of a semantic gap.\nAlthough it has been studied extensively, semantic representation of visual information is not well understood. To address the\nproblem of pattern classification in video annotation, this paper proposes a discriminative constraint to find a solution to approach\nthe sparse representative coefficients with discrimination.We study a general method of discriminative dictionary learning which\nis independent of the specific dictionary and classifier learning algorithms. Furthermore, a tightly coupled discriminative sparse\ncoding model is introduced. Ultimately, the experimental results show that the provided method offers a better video annotation\nmethod that cannot be achieved with existing schemes....
With the increasing growth of media cloud technologies, web service technologies, and smartphones equipped sensors, a number\nof collaborative media services are being built for ubiquitous user access. Currently, collaborative services are being used in several\nareas like healthcare, defense, education, and so forth. However, due to the challenge of providing such service to users in terms of\ncomputations, communications, processing, and storage, there is a growing need for an infrastructure to have on-demand access to\na shared pool of configurable computing resources (e.g., networks, storages, servers, applications, and services). Cloud computing is\nsuch a paradigm or infrastructure to provide configurable platformto support the collaborative service. In this paper, we present the\ncorresponding framework of collaborative media service for efficient collaboration between caregivers and healthcare professionals.\nThe experimental results not only showed our solution is more efficient than the similar system but also proved that our solution\ncan work well for web service-based collaborative environment....
Smart cameras were conceived to provide scalable solutions to automatic video analysis applications, such as surveillance and\nmonitoring. Since then, many algorithms and system architectures have been proposed, which use smart cameras to distribute\nfunctionality and save bandwidth. Still, smart cameras are rarely used in commercial systems and real installations. In this paper,\nwe investigate the reason behind the scarce commercial usage of smart cameras. We found that, in order to achieve scalability,\nsmart cameras put additional constraints on the quality of input data to the vision algorithms, making it an unfavourable choice\nfor future multicamera systems. We recognized that these constraints can be relaxed by following a cloud based hub architecture\nand propose a cloud entity, SmartHub, which provides a scalable solution with reduced constraints on the quality. A framework is\nproposed for designing SmartHub system for a given camera placement. Experiments show the efficacy of SmartHub based systems\nin multicamera scenarios....
Software-as-a-service (SaaS) has emerged as a new computing paradigm to provide reliable software on demand. With such an\ninspiring motivation, sensor cloud system can benefit from this infrastructure. Generally, sharing database and schema is the most\ncommonly used data storage model in the cloud. However, the data storage of tenants in the cloud is approaching schema null\nand evolution issues. To address these limitations, this paper proposes multitenant multiple wide tables with vertical scalability by\nanalyzing the features of multitenant data. To solve schema null issue, extended vertical part is used to trim down the amount of\nschema null values. To reduce probability of schema evolution, wide table is divided into multiple clusters that we called multiple\nwide tables. This design reaches the balance between tenant customizing and its performance. Besides, the partition and correctness\nof multiple wide tables with vertical scalability are discussed in detail. The experimental results indicate that the solution of our\nmultiple wide tables with vertical scalability is superior to single wide table, and single wide table with vertical scalability in the\naspects of spatial intensity and read performance....
This paper addresses the problem of estimation fusion in a distributed wireless sensor network (WSN) under the following\nconditions: (i) sensor noises are contaminated by outliers or gross errors; (ii) process noise and sensor noises are correlated; (iii)\ncross-correlation among local estimates is unknown. First, to attack the correlation and outliers, a correlated robustKalman filtering\n(coR2KF) scheme with weighted matrices on innovation sequences is introduced as local estimator. It is shown that the proposed\ncoR2KF takes both conventional Kalman filter and robust Kalman filter as a special case. Then, a novel version of our internal\nellipsoid approximation fusion (IEAF) is used in the fusion center to handle the unknown cross-correlation of local estimates. The\nexplicit solution to both fusion estimate and corresponding covariance is given. Finally, to demonstrate robustness of the proposed\ncoR2KF and the effectiveness of IEAF strategy, a simulation example of tracking a target moving on noisy circular trajectories is\nincluded....
Geosensor networks and sensor webs are two technologies widely used for determining our exposure to pollution levels and\nensuring that this information is publicly available. However, most of these networks are independent from each other and often\ndesigned for specific domains, hindering the integration of sensor data from different sources. We contributed to the integration\nof several environmental sensor networks in the context of the IDEA project. The objective of this project was to measure noise\nand air quality pollution levels in urban areas in Belgium using low-cost sensors. This paper presents the IDEA Environmental\nMeasurement Cloud as a proof-of-conceptData-as-a-Service (DaaS) cloud platformthat integrates environmental sensor networks\nwith a sensor web. Our DaaS platform implements a federated two-layer architecture to loosely couple together sensor networks\ndeployed over a wide geographical area with web services. It offers several data access, discovery, and visualization services to the\npublic while serving as a scientific tool for noise pollution research. After one year of operation, it hosts approximately 6.5 TB of\nenvironmental data and offers to the public near real-time noise pollution measurements from over 40 locations in Belgium....
Loading....