caa a22 4500 445295414 CHVBK 20180317142540.0 cr unu---uuuuu 170323e20101201xx s 000 0 eng 10.1007/s11554-009-0148-7 doi (NATIONALLICENCE)springer-10.1007/s11554-009-0148-7 Integrated video motion estimator with Retinex-like pre-processing for robust motion analysis in automotive scenarios: algorithmic and real-time architecture design [Elektronische Daten] [Stefano Marsi, Sergio Saponara] The paper presents a novel technique for robust motion analysis in real automotive scenarios based on integrated Retinex-like pre-processing algorithm with block matching video motion estimator. Both algorithmic and real-time hardware design issues are discussed. The benefits of the proposed technique are manifold: the entire system is more robust; the estimated motion vectors are more reliable and less dependent on critical ambient conditions like shadows or flashes; the proposed algorithm may allow to perform motion estimation using very few bits and running as a 2- or 1-bit transform, still maintaining good performances. Real-time hardware implementation is achieved by design and synthesis in 65nm CMOS standard-cells technology of an Application Specific Instruction-set Processor. Design optimizations for both the processing core and the memory organization are presented. With respect to the state of the art the proposed hardware implementation ensures bounded circuit complexity, low power consumption and reprogrammability of the technique. Springer-Verlag, 2010 Robust motion analysis nationallicence Video processing for automotive applications nationallicence Motion estimation nationallicence Retinex filters nationallicence Application Specific Instruction-set Processor (ASIP) nationallicence Hardware for real-time processing nationallicence Marsi Stefano DEEI, University of Trieste, via Valerio 10, 34127, Trieste, Italy aut Saponara Sergio Department of Information Engineering, University of Pisa, via G. Caruso 16, 56122, Pisa, Italy aut Journal of Real-Time Image Processing Springer-Verlag 5/4(2010-12-01), 275-289 1861-8200 5:4<275 2010 5 11554 https://doi.org/10.1007/s11554-009-0148-7 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s11554-009-0148-7 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Marsi Stefano DEEI, University of Trieste, via Valerio 10, 34127, Trieste, Italy aut NATIONALLICENCE 700 1- Saponara Sergio Department of Information Engineering, University of Pisa, via G. Caruso 16, 56122, Pisa, Italy aut NATIONALLICENCE 773 0- Journal of Real-Time Image Processing Springer-Verlag 5/4(2010-12-01), 275-289 1861-8200 5:4<275 2010 5 11554 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer