Formatting code for EMoA
====EMoA: Embedded Mobile Agent Framework for Smart Buildings====
{{image url="http://www.nano-tera.ch/images/uploads/315/315.gif" title="text" alt="text"}}
The current project tackles in-house safety by communicating domestic incidents such as a person falling or an unusual behaviour. The number of in-house deaths and injuries in the case of elderly, disabled and children could be considerably reduced if these incidents are immediately reported to a facultative or an emergency centre. We believe that the use of multiple video sources will provide us with a powerful, flexible and accurate surveillance/detection system. With this purpose, we envision a distributed smart camera system, based on low-power embedded systems-on-chip targeting image processing and network communication. Our starting point is an existing single smart camera fall detection system developed at our labs within the scope of a research project granted by the strategic fund of the University of Applied Sciences Western Switzerland (HES-SO), which is based on the system-on-chip OMAP1. The implemented fall detection algorithm processes the input video stream by performing, first, a background subtraction, followed by an object segmentation, which serves as input for the tracking of the person and its eventual fall detection.
The ultimate goal pursued by this project is thus the enhancement of the existing single smart camera fall detection system to cover a larger field of view and make the system more robust. The accomplishment of this objective mainly depends on a successful implementation of a mobile agent middleware on the target embedded platform (see Figure 1). Such middleware has to be designed for distributed image processing, where two or more cameras can cooperate for a single task such as tracking a person. The main requirements of such a mobile agent system for distributed smart cameras are: Lightweight, abstractions of image processing, collaborative image processing, and synchronizations.
To achieve the above mentioned goal, we require the implementation of a mobile agent framework capable of, on one hand, separating between video-based tracking algorithm and application logic, and, on the other hand, migrating agents among the different video processing units. While this kind of frameworks are well-known and established in general purpose computer networks, the requirements imposed by the embedded world, makes a straight-forward application of mobile agents for such systems rather challenging.
{{image url="http://www.nano-tera.ch/images/uploads/315/315.gif" title="text" alt="text"}}
The current project tackles in-house safety by communicating domestic incidents such as a person falling or an unusual behaviour. The number of in-house deaths and injuries in the case of elderly, disabled and children could be considerably reduced if these incidents are immediately reported to a facultative or an emergency centre. We believe that the use of multiple video sources will provide us with a powerful, flexible and accurate surveillance/detection system. With this purpose, we envision a distributed smart camera system, based on low-power embedded systems-on-chip targeting image processing and network communication. Our starting point is an existing single smart camera fall detection system developed at our labs within the scope of a research project granted by the strategic fund of the University of Applied Sciences Western Switzerland (HES-SO), which is based on the system-on-chip OMAP1. The implemented fall detection algorithm processes the input video stream by performing, first, a background subtraction, followed by an object segmentation, which serves as input for the tracking of the person and its eventual fall detection.
The ultimate goal pursued by this project is thus the enhancement of the existing single smart camera fall detection system to cover a larger field of view and make the system more robust. The accomplishment of this objective mainly depends on a successful implementation of a mobile agent middleware on the target embedded platform (see Figure 1). Such middleware has to be designed for distributed image processing, where two or more cameras can cooperate for a single task such as tracking a person. The main requirements of such a mobile agent system for distributed smart cameras are: Lightweight, abstractions of image processing, collaborative image processing, and synchronizations.
To achieve the above mentioned goal, we require the implementation of a mobile agent framework capable of, on one hand, separating between video-based tracking algorithm and application logic, and, on the other hand, migrating agents among the different video processing units. While this kind of frameworks are well-known and established in general purpose computer networks, the requirements imposed by the embedded world, makes a straight-forward application of mobile agents for such systems rather challenging.
