Smart camera architecture

Editorial Special issue Smart Camera Architecture Fran¸cois BERRY Institut Pascal - UMR 6602 UBP/CNRS - Campus des C´ ezeaux 24, Avenue des Landais 63170 AUBIERE - FRANCE

Ricardo CARMONA Instituto de Microelectr´ onica de Sevilla(CSIC-Universidad de Sevilla) Avda. Am´ erico Vespucio s/n 41092 Sevilla - SPAIN

Richard KLEIHORST Xetal NV Boeimeerstraat 1A Bonheiden 2820 - BELGIUM

Smart cameras are not a simple vision device which provides images but rather an embedded system which understand them. So, smart cameras combine video sensing, processing, and communication on a single embedded platform. Thus, a smart camera integrates some processing capability. This can take the form of a dedicated field-programmable gate array (FPGA), a digital signal processor (DSP), a fully-fledged CPU or CPU/GPU combination from a processor vendor such as Intel or AMD, or a CPU supported by an FPGA.This approach has emerged thanks to a confluence of simultaneous advances in three key disciplines: computer vision, image sensors and embedded computing. One of the major advantages of this kind of embedded system is that they are able to deal with a wide range of problems, presenting several advantages which can be categorized as: • Communication bottlenecks: embedded processing allows reducing the data communication between sensors and the host system, avoiding the bottlenecks that frequently occur in real-time image processing. • Autonomous or Mobile devices: avoiding the use of a mainframe computer system, compact sizes (for unmanned aerial vehicles for example) and low power consumption can be obtained. • Active perception: for these applications, a high-speed feedback link between sensing and processing is fundamental

Preprint submitted to Journal of System Architecture

September 18, 2013

• Camera networks: distributed processing using smart cameras have major advantages over centralized processing systems, since it avoids the transmission of large amounts of information. Smart cameras are now finding their way into a number of niche applications once dominated by camera/PC software-based combinations. However, the choice of smart camera and development environment is dependent on the nature of the vision application, the cost and volume of the system in which the camera will be deployed, and the ease with which it is to be programmed. In this special issue, we propose to collect the best contributions of the workshop WASC (Workshop on Architecture of Smart Camera). Thus, this issue focuses on novel advances in architecture for image understanding, signal and image processing, configurable and FPGA-based architecture, VLSI systems, but also on Languages, software environments and programming tools and applications of smart cameras.

2

View publication stats