350 rub
Journal Electromagnetic Waves and Electronic Systems №10 for 2016 г.
Article in number:
Features of the context access memory for computer vision systems and image processing
Authors:
E.A. Titenko - Ph.D. (Eng.), Associate Professor, Department of Information Systems and Technology, South-West State University, Kursk
А.P. Tipikin - Ph.D. (Eng.), Associate Professor, Department of Information Systems and Technology, South-West State University, Kursk
D.V. Lapin - Post-graduate, South-West State University, Kursk
Abstract:
The object of study is parallel processing of regular data in context access memory. Regular data are three-dimensional images in the computing vision system of the mobile robot.
The aim is to increase responsiveness of the implementation of complex image processing operations: filtration, contrast, search mask, and others.
Modern computer systems are based on standard functional units (microprocessors) or specialized functional modules (VLSI, FPGA). Analysis of the structural features and functionality of the organization of microprocessors for computer vision systems is identified on the speed limit. Modern specialized LSI / VLSI contain logic elements, finished functional units. Programmable LSI, VLSI used for processing data with regular structure, especially images. The context access memory combines the functions of storing and processing information. It provides multiple access to all the information, and a parallel search of the data amount. As a result, the use of the context access memory allows hardware-level executive quickly control of mobile robot devices.
Research methods were the system analysis and the computer design theory.
Pages: 56-59
References
- Kravec O.JA., Podvalnyjj E.S., Titov V.S., JAstrebov A.S. Arkhitektura vychislitelnykh sistem s ehlementami konvejjernojj obrabotki: Ucheb. posobie. GOU VPO SPbGUT, GOU VPO Voronezh. gos. tekhn. un-t, GOU VPO Kursk. gos. tekhn. un-t. SPb: Politekhnika.2009. 152 s.
- Titenko E.A., Emeljanov S.G., Zerin I.S. Odnorodnye vychislitelnye struktury dlja parallelnykh simvolnykh vychislenijj // Izvestija JUgo-Zapadnogo gosudarstvennogo universiteta. 2011. № 6(39). CH. 2. S. 77-82.
- Kaljaev I.A., Levin I.I. Modulno-narashhivaemye mnogoprocessornye sistemy so strukturno-procedurnojj organizaciejj vychislenijj. M.: JAnus-K. 2003. 380 s.
- Artamonov D.S., Putrja M.G. Metod optimizacii vychislitelnogo processa na rekonfiguriruemykh vychislitelnykh sredakh // Informacionnye tekhnologii vychislitelnye sistemy. 2010. № 3. S. 19-26.
- Titenko E.A. Organizacija rekonfiguriruemogo multiprocessora potoka dannykh // Vestnik kompjuternykh i informacionnykh tekhnologijj. 2012. № 2. S. 24-29.
- Titenko E.A., Atakishhev O.I. Metod associativnojj obrabotki strok i apparatno-orientirovannyjj algoritm dlja ego realizacii // Izvestija JUgo-Zapadnogo gosudarstvennogo universiteta. Kursk. 2011. № 6(39). CH. 2. S.72-77.
- Titov, V.S., Konovalchik A.P., Titenko E.A. Vysokoproizvoditelnye vychislitelnye sistemy na osnove PLIS // Izvestija JUgo-Zapadnogo gosudarstvennogo universiteta. 2012. № 4(43). CH. 2. S. 73-77.