Embedded Vision System
- PDF / 115,352 Bytes
- 2 Pages / 600.032 x 792 pts Page_size
- 88 Downloads / 193 Views
Editorial Embedded Vision System Dietmar Dietrich1 and Heinrich Garn2 1 Institute
of Computer Technology, Faculty of Electrical Engineering and Information Technology, Vienna University of Technology, 1040 Vienna, Austria 2 Smart Systems Division, Austrian Research Centers GmbH (ARC), 1220 Vienna, Austria Received 23 January 2007; Accepted 23 January 2007 Copyright © 2007 D. Dietrich and H. Garn. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Video surveillance and machine vision systems are attracting growing academic and industrial interests. The market for digital CCTV systems is constantly growing because of terror attacks, crime, vandalism, and violence in public and also in business domains. The turnover for CCTV products for video surveillance is estimated to grow by 10% per year in Europe and by 13% per year worldwide, reaching 3.8 billion US$ in Europe and 10.6 billion US$ by 2008. In the machine vision market, the annual growth in turnover in vision systems has been 7%–15% over the last few years. In the smart-vision segment, an annual growth of as much as 20% is predicted within the next 4 years. Innovation and technological lead of an enterprise were identified as the key impulses for this growth. Vision systems are still skeptically perceived by potential users. More than 50% view vision systems are too expensive or complex in setup and use. All this shows that embedded vision systems have a high potential for innovative product development and represent the major future growth factor in the imaging industry. There are numerous technical challenges that researchers and engineers are working on all around the world. We are proud to present a selection of excellent scientific papers about recent innovations in this special issue of the EURASIP Journal on Embedded Systems. About 60% of the submitted papers have been accepted. The emphasis is on tools, architectures, and methodologies for implementing computer vision in field-programmable logic arrays (FPGAs) and digital signal processors (DSP): (i) a tool for automatic generation of the memory management implementation for spatial and temporal real-time video processing systems targeting fieldprogrammable logic arrays;
(ii) a software library for image processing algorithms for an embedded system; (iii) a high-level optimization methodology for implementing the convolutional face finder algorithm for real-time applications on mobile phones; (iv) an adaptive and predictive FPGA embedded architecture for vision systems dedicated to image analysis; (v) a design methodology for mapping computer-vision algorithms onto an FPGA through the use of coarsegrain reconfigurable dataflow graphs; (vi) a novel FPGA-based architecture dedicated to active vision; (vii) design considerations for a scalable high-performance vision system, like partitioning of image processing algorithms between hardware an
Data Loading...
