Athanasios Voulodimos

A Cloud Environment for Data-intensive Storage Services

The emergence of cloud environments has made feasible the delivery of Internet-scale services by addressing a number of challenges such as live migration, fault tolerance and quality of service. However, current approaches do not tackle key issues related to cloud storage, which are of increasing importance given the enormous amount of data being produced in todays rich digital environment (e.g. by smart phones, social networks, sensors, user generated content). In this paper we present the architecture of a scalable and flexible cloud environment addressing the challenge of providing data-intensive storage cloud services through raising the abstraction level of storage, enabling data mobility across providers, allowing computational and content-centric access to storage and deploying new data-oriented mechanisms for QoS and security guarantees. We also demonstrate the added value and effectiveness of the proposed architecture through two real-life application scenarios from the healthcare and media domains.

Bayesian filter based behavior recognition in workflows allowing for user feedback

In this paper, we propose a novel online framework for behavior understanding, in visual workflows, capable of achieving high recognition rates in real-time. To effect online recognition, we propose a methodology that employs a Bayesian filter supported by hidden Markov models. We also introduce a novel re-adjustment framework of behavior recognition and classification by incorporating the users feedback into the learning process through two proposed schemes: a plain non-linear one and a more sophisticated recursive one. The proposed approach aims at dynamically correcting erroneous classification results to enhance the behavior modeling and therefore the overall classification rates. The performance is thoroughly evaluated under real-life complex visual behavior understanding scenarios in an industrial plant. The obtained results are compared and discussed.

A dataset for workflow recognition in industrial scenes

In this paper we introduce the WR (Workflow Recognition) dataset. Recorded in the production line of a major automobile manufacturer, this dataset consists of sequences that depict workers executing industrial workflows. The heavy occlusions, outliers, the visually complicated background and the human-machinery interaction are among the factors that make this dataset a very challenging testbed for computer vision and image processing algorithms. We provide the original video sequences together with event labeling, as well as feature vectors extracted through our proposed scene representation methodology, and we refer to our results so far in workflow recognition using this dataset.

Security and Privacy in Pervasive Computing

In this issues Works in Progress department, we have six projects. The first two projects address an individuals privacy concerns and preferences. The next entry discusses a project on data protection for electronic passports. The remaining three projects are investigating various types of privacy protection mechanisms for data collected in pervasive computing environments, by attestation services, and by voice recording systems.

A Threefold Dataset for Activity and Workflow Recognition in Complex Industrial Environments

Unlike any previous effort, the Workflow Recognition (WR) large-scale dataset is a collection of video sequences from the real industrial manufacturing environment of a major automobile manufacturer.

IMPROVING MULTI-CAMERA ACTIVITY RECOGNITION BY EMPLOYING NEURAL NETWORK BASED READJUSTMENT

In this paper, we propose a method to enhance activity recognition in complex environments, where problems like occlusions, outliers and illumination changes occur. In order to address the problems induced by the dependency on the cameras viewpoint, multiple cameras are used in an endeavor to exploit redundancies. We initially examine the effectiveness of various information stream fusion approaches based on hidden Markov models, including Students t-endowed models for tolerance to outliers. Following, we introduce a neural network-based readjustment mechanism that fits these fusion schemes and aims at dynamically correcting erroneous classification results for image sequences, thus improving the overall recognition rates. The proposed approaches are evaluated under complex real life activity recognition scenarios, and the acquired results are compared and discussed.

Efficient tracking using a robust motion estimation technique

Camera based supervision is a critical part of event detection and analysis applications. However, visual tracking still remains one of the biggest challenges in the area of computer vision, although it has been extensively discussed during in the previous years. In this paper we propose a robust tracking approach based on object flow, which is a motion model for estimating both the displacement and the direction of an object of interest. In addition, an observation model that utilizes a generative prior is adopted to tackle the pitfalls that derive from the appearance changes of the object under study. The efficiency of our technique is demonstrated using sequences captured in a complex industrial environment. The experimental results show that the proposed algorithm is sound, yielding improved performance in comparison with other tracking approaches.

A System for Multicamera Task Recognition and Summarization for Structured Environments

In this paper, we propose a novel system for visual recognition and summarization of pick and place tasks that may be executed in settings such as an industrial assembly line. Our novel approach is based on the utilization of hidden Markov models for online task recognition as well as on the use of prior knowledge via a Hopfield-based optimization scheme. To facilitate offline analysis, we extract summaries of the captured content based on these features. We extract the motion energy using the norms of the Zernike moments, looking for local minima and maxima that indicate distinctive visual events and thus key-frames. The proposed scheme is not threshold-dependent, and, therefore, the number of extracted key-frames varies according to the complexity of motion energy variation. We validate our system by experimenting on two datasets.

Enhanced human behavior recognition using HMM and evaluative rectification

Human behavior recognition and real world environments monitoring constitute challenging research problems rapidly gaining momentum over the last years. Methods for time series classification like the Hidden Markov Models have been employed in the past for similar tasks, however in many challenging cases they fail, since some behaviors are much more difficult to model than others. This happens particularly in cases that there is scarcity of labelled data. In this paper we introduce a novel re-adjustment framework of behavior recognition and classification by allowing the user incorporation in the learning process. The proposed Evaluative Rectification approach aims at dynamically correcting erroneous classification results to enhance the behavior modeling and therefore the overall classification rates. We evaluate the performance of the examined approach in a challenging real-life industrial environment of an automobile manufacturer. Our experiments indicate a significant outperformance of the proposed Evaluative Rectification scheme compared with traditional classification frameworks, such as Hidden Markov Models.

Using Personalized Mashups for Mobile Location Based Services

In this paper, a framework that allows users to build, deploy and distribute personalized mobile services is described. The framework allows the integration of static and dynamic content that stems from various web sources, system data and from the personal user preferences, and is combined to form mashups for supporting the provision of mobile services in a time dependent, location aware, context driven and, finally, personalized manner. The framework has been implemented based on Pocket PC user devices, and can be deployed over any IP supporting network architecture.