- Ákos Zarándy, doctor of HAS, research advisor
Curriculum vitae
Dr. Ákos Zarándy
Personal Information
Name: Ákos Zarándy
Date of birth: Oct 6th, 1967
Workplace: Computer and Automation Research Institute of the Hungarian Academy of Sciencies (MTA-SZTAKI)
Address: POB: 63, 1518 Budapest, Hungary
Phone: +36 1 279-6131
Fax: +36 1 209-5264
Email: zarandy@sztaki.hu
Citizenship: Hungarian
Professional Experience
2007-present Senior Research Fellow (MTA-SZTAKI, Hungary)
2005-2006 CTO (Eutecus Inc. Berkeley, California, USA)
2000-2005 CEO (AnaLogic Computers Ltd, Budapest, Hungary, Spin-off company of SZTAKI)
1997-2005 Research Fellow (MTA-SZTAKI, Hungary)
1992-1997 PhD student (MTA-SZTAKI, Hungary)
1993, 95, 96, 98 Visiting scholar or post doc at University of California at Berkeley
Education
2010 DSC of the Hungarian Academy of Sciencies
1997 Ph.D. in Computer science, Hungarian Academey of Sciences:
"CNN Universal Machines: spatial logic, colors, and illusions"
1992 MsC, Electrical Engineering, Technical University of Budapest, Hungary
Fields of interest
Focal-plane sensor-processors: architecture, design, and development
Cellular Neural Network research: VLSI implementations, algorithm development
IR imaging: sensor interface development
Human and artificial vision, color vision: modelling
Image processing: algorithms, embedded implementation
System integration: ultra-high speed, low power, embedded image processing devices
Major technical achievements
2006-2007: 8x8 nanoantenna sensor interface including per pixel analogue amplifiers and programmable digital filters (100dB signal to noise ratio total) (Project Leader)
2005-2006: Focal-plane sensor-processor array with 64 fully programmable on-chip processors: XENON (Project Leader)
2004-2005: Locally adaptive image sensor development
2002-2005: Biologically motivated collision warning focal-plane sensor-processor array: LOCUST (Group Leader)
2002-2003 Bi-i: Industrial grade camera capable over 25,000 FPS visual decision making (capturing and real-time evaluation) Product of the year, Vision 2003, Stuttgart (Project Leader)
1996-2000: CNN Chip Prototyping System (chief developer)
Publication Summary
26 peer-reviewed published (or accepted) papers
5 Book chapters
45 conference contributions
300 total number of citations (excluding self citation)
2 patents
Most Important International Collaborations
1994- present: Focal-plane sensor-processor chip development and testing, Microelectronic Institute Seville, Spain, Prof. Angel Rodriguez-Vazquez and his group
2002-present Active contour algorithm implementation on sensor-processor array School of Electrical and Electronic Engineering The University of Manchester, Dr. Piotr Dudek
2000-present: Neuromorph modell implementations on sensor processor arrays Friedrich Miescher Institute, Dr. Botond Roska
1998-present Robot guidance algorithms for sensor-processor array Department of Electronic and Electrical Systems, University of Catania, Dr. Paolo Arena
Teaching
2005-present Peter Pazmany Catholic University, „Electronic components of the computing, communicating and sensing devices”
Grants and Scholarships
2005-2007: Nanoantenna sensor-processor array development: Eutecus Inc, Notre Dame University (two US grants: N00014-05C-0370 and HQ0006-05-C-7268, over $1,5M) role: PI
2002-2003 RobotEyepair (Hungarian grant IKTA4-044) Budget: 420k Euro. Role: PI
2004-2007 SPARK: Spatial-temporal Patterns for Action-oriented perception in Roving robots, (FP6-2003-IST-2) EU FP6, role: participant
2002-2005: LOCUST: Life-Like Object Detection For Collision Avoidance Using Spatio-Temporal Image Processing. (IST-2001-38097) EU FP5-FP6. Role: participant
2000-2003 DICTAM: Dynamic Image Computing Using Tera-Speed Analogic Visual Microprocessors. (IST-1999-19007) EU FP5. role: participant
Honors and Awards
2007 Charles Simonyi Award
2007 Microprocessor Report Innovation Award, San Jose, California: Superfast Sensor-Processors Break New Ground in Digital Imaging
2005 Best paper award, “Per-pixel integration time controlled image sensor” ECCTD Ireland
2003 Product of the year at Stuttgart Vision fair: Bi-i camera
2002 John von Kemeny Award
2000 Denes Gabor Patent Award
1999 General Electrics Scholarship
Spcecial issues, sessions sessions
2004: Special issue: IEEE Transactions on Circuits and Systems—I: Fundamental Theory and Applications (TCAS-I), „CNN Technology and Active Wave Computing: Analog-and-logic cellular machines integrating sensors and/or actuators” guest co-editor
2003: Special session: IEEE International symphosium on Circuits and Systems (ISCAS) „Spatiotemporal cellular vision systems” co-organizer
2002: Journal of Circuits, Systems, and Computers, „CNN Technology and Visual Microprocessors”, guest co-editor
Publications[ order by time]
[ order by categories ]
[ order by authors]
Book- Analog VLSI based Bayesian multi-scale optical flow estimation. (Research report of the Analogical and Neural Computing Laboratory DNS-7-2004)
- Local contrast measures for detection of microalcifications. (Research report of the Analogical and Neural Computing Laborarory, DNS-3-1999)
- Fault tolerant design of analogic CNN templates and algorithms. Part I: The binary output case.(Research report of the Analogical and Neural Computing Laboratory, DNS-3-1998.)
- Analogic Macro Code (AMC). Extended assembly language for CNN computers. Version 1.1.(Research report of the Analogical and Neural Computing Laboratory, DNS-10-1998.)
- The art of CNN template design.(Research report of the Analogical and Neural Computing Laboratory, DNS-8-1997.)
- Functional measurements of the first analog input/output CNN universal chip. (Research report of the Analogical and Neural Computing Laboratory, DNS-4-1997.)
- Analogic mammogram diagnostic workstation boosted up with cellular neural networks. Version 1.1. (Research report of the Analogical and Neural Computing Laboratory, DNS-3-1997.)
- New results and measurements related to dynamic image coding using CNN universal chips. (Memorandum of the Electronics Research Laboratory, UCB/ERL M96/58)
- Implementation of large-neighborhood nonlinear templates on the CNN universal machine. ( Research report of the Analogical and Neural Computing Laboratory, DNS-7-1996.)
- Implementation of binary and gray-scale mathematical morphology on the CNN universal machine. ( Memorandum of the Electronics Research Laboratory, UCB/ERL M96/19)
- Analogic CNN models of some qualitative pattern recognition tasks in the inferotemporal cortex. (Research report of the Neuromorphic Information Technology, Graduate Center. NIT-1-1995.)
- Spatial logic algorithms using analogic CNN instructions and its use in bank-note recognition. (Research report of the Analogical and Neural Computing Laboratory DNS-5-1995.)
- Novel types of analogic CNN algorithms for recognizing bank-notes. (Memorandum UCB/ERL M94/29.)
- Language, compiler, and operating system for the CNN supercomputer. Memorandum UCB/ERL M93/34
- CNNHAC cellular neural network simulator using hardware accelerator board. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-11-1992.)
- CNNM multi-layer cellular neural network simulator.Version 2.4. 1992. User's guide. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-12-1992.)
- Some novel capabilities of CNN. Game of life and examples of multipath algorithms. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-3-1992.)
- The use of CNN models in the visual parthway. Part II: The amacrine cell in the modified retina model, simple LGN effects and motion related illusions. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-9-1992.)
Authors: Roska, T; Hámori, J; Lábos, E; Lotz, K; Orzó, L; Takács, J; Venetianer, P; Vidnyánszky, Z; Zarándy, ÁDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1992.Published by: The use of CNN models in the visual parthway. Part II: The amacrine cell in the modified retina model, simple LGN effects and motion related illusions. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-9-1992.) (Page: 51)
- The use of CNN models in the subcortical visual pathway. (Reseach report of the Dual and Neural Computing Systems Laboratory DNS-16-1992)
- DUALCOMP dual CNN compiler to CNN-HAC1 board. Version 2.0. 1992. User's guide
Conference issue- Performance analysis of a vision only sense and avoid system for small UAVs.
- Visual detection and implementation aspects of a UAV see and avoid system.
- Wi-FLIP: A wireless smart camera based on a focal-plane low-power image processor.
Authors: Fernández-Berni, Jorge; Carmona-Galán, Ricardo; Linán-Cembrano, Gustavo; Zarándy, Ákos; Rodríguez-Vázquez, AngelDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2011. 08. 22.Published by: ICDSC 2011. 5th ACM/IEEE international conference on distributed smart cameras. Ghent, 2011. (Length: 1-6. page)Download article: [html]
- Demo: Real-time remote reporting of active regions with Wi-FLIP.
Authors: Fernández-Berni, Jorge; Carmona-Galán, Ricardo; Linán-Cembrano, Gustavo; Zarándy, Ákos; Rodríguez-Vázquez, AngelDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2011. 08. 22.Published by: ICDSC 2011. 5th ACM/IEEE international conference on distributed smart cameras. Ghent, 2011. (Length: 1-2. page)Download article: [html]
- Performance analysis of a vision only sense and avoid system for small UAVs.
- Collision avoidance for UAV using visual detection.
- Applications of the virtual cellular machine to many-core processors.
- Retinal approaching object detector model implementation and validation.
- Bio-inspired looming object detector algorithm on the Eye-RIS focal plane-processor system.
- Digital processor array implementation aspects of a 3D multi-layer vision architecture.
Authors: Földesy, Péter; Carmona-Galan, R.; Zarándy, Ákos; Rekeczky, Cs.; Rodríguez-Vázquez, A.; Roska, TamásEditor: Roska, Tamás; Gilli, Marco; Zarándy, ÁkosDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2010. 02. 03.Published by: 12th international workshop on cellular nanoscale networks and their applications. CNNA 2010. Berkeley, 2010. (Page: 329-332.)Download article: [html]
- Displacement calculation algorithm on a heterogeneous multi-layer cellular sensor processor array.
- A 3-D chip architecture for optical sensing and concurrent processing.
Authors: Rodríguez-Vázquez, A.; Carmona, R.; Domínguez Matas, C.; Suárez-Cambre, M.; Brea, V.; Pozas, F.; Linán, G.; Földesy, Péter; Zarándy, Ákos; Rekeczky, CsabaEditor: Berghmans, F.; Mignani, A. G.; van Hof, C. A.Department: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2010.Published by: Optical sensing and detection. Brussels, 2010. (Proceedings of SPIE 7726.) (Page: 772613-1-772613-12.)Download article: [html]
- 3D multi-layer vision architecture for surveillance and reconnaissance applications.
- Real-time moving object segmentation algorithm implemented on the Eye-RIS focal plane sensor-processor system.
- Implementing the non-linear wave metric on the Q-Eye cellular array processor chip.
- Clusterable cellular visual microprocessor.
- Analysis of 2D operators on topographic and non-topographic processor architectures.
- High performance processor array for image processing.
- 3D integrated scalable focal-plane processor array.
- High-speed label inspection system for textile industry
- Per-pixel integration time controlled image sensor
- Various implementations of topographic, sensory, cellular wave computers
- Topographic and non-topographic neural network based computational platform for UAV applications
- Bayesian incorporation of multiple scales in optical flow estimation
- Bi-i: a standalone cellular vision system. Part II: Topographic and non-topographic algorithms and related applications
- Bi-i: a standalone cellular vision system. Part I. Architecture and ultra high frame rate processing examples
- Adaptive perception with locally-adaptable sensor array
- High dynamic range perception with spatially variant exposure
- Proactive, adaptive, cellular sensory-computer architecture via extending the CNN univesal machine
- Vision systems based on the 128x128 focal plane cellular visual microprocessor chips
- Moving object traking on panoramic images.
- Image processing library for the ALADDIN visual computer.
- CNN based color constancy algorithm.
- Dennis Gabor as the initiator of optical computing. Importance and prospects of optical computing and an optical implementation of the CCN-UM computer.
- ACE box: high-performance visual computer based on the ACE4k analogic array processor chip.
- An optical CNN implementation with stored programmability.
- Dennis Gabor as the initiator of optical computing: Importance and prospects of optical computing and an optical implementation of the CNN-UM computer.
- An analogic CNN engine board with the 64x64 analog I/O CNN-UM chip.
- CNN technology in action.
Authors: Zarándy, Á; Espejo, S; Földesy, P; Kék, L; Linán, G; Rekeczky, C; Rodriguez-Vázquez, A; Roska, T; Szatmári, I; Szirányi, T; Szolgay, PDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2000.Published by: Proceedings of the 6th IEEE international workshop on cellular neural networks and their applications. (CNNA 2000). Catania, 2000. (Page: 79-81)
- 20 msec focal plane image processing.
- Futási eredmények az analogikai CNN-UM vizuális mikroprocesszorokon.
- A new type of analogic CNN agorithmfor printed circuit board layout error detection.
- The CADETWin application software design system - a tutorial.
Authors: Szolgay, P; László, K; Kék, L; Kozek, T; Nemes, L; Petrás, I; Rekeczky, CS; Szatmári, I; Zarándy, Á; Zöld, S; Roska, TDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1999.Published by: Design automation day on cellular visual microprocessor. Stresa, 1999. (Page: 58-68)
- The computational infrastructure for cellular visual microprocessors.
Authors: Szolgay, P; Zarándy, Á; Zöld, S; Roska, T; Földesy, P; Kék, L; Kozek, T; László, K; Petrás, I; Rekeczky, CS; Szatmári, I; Bálya, DDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1999.Published by: MicroNeuro '99. Proceedings of the seventh international conference on microelectronics for neural, fuzzy, and bio-inspired systems. Granada, 1999. (Page: 54-60)
- CNN chip prototyping and development systems.
- Fault tolerant CNN template design and optimatization based on chip measurements.
- An emulated digital architecture implementing the CNN universal machine.
- CASTLE: an emulated digital architecture; design issues, new results.
- Implementation of large-neighborhood nonlinear templates on the CNN universal machine.
- Ultra fast image processing via CNN technology.
- CNN template design strategies and fault tolerant CNN template design - a survey.
- Celluláris és neurális áramkörök alkalmazása mammogramok kiértékelésében.
- Real-life application case studies using CMOS 0.8 mm CNN universal chip: analogic algorithm for motion detection and texture segmentation.
- CNN model for identifying colors under different illumination condition via Land's experiments.
- Morphological operators on the CNN universal machine.
- Mammogram analysis using CNN algorithms
- Cellular neural networks. Part 2. Application examples - a tutorial
- An analogic phenomenological CNN algorithm to model the mouth detection task of the inferotemporal cortex discovered by I. Fujita
- Translating neuromorphic CNN visual models to the analogic visual microprocessors
- Intelligent image resolution enhancement by the CNN universal machine and its relevance to TV picture enhancement
- On a CNN chip-prototyping system
- Design of analogic CNN algorithms for mammogram analysis
- Novel types of analogic CNN algorithms for recognizing bank-notes
- Color image processing by CNN
- Some novel capabilities of CNN: Game of life and examples of multipath algorithms
Journal article- Insect-vision inspired collision warning vision processor for automobiles.
- Bi-i: a standalone ultra high speed cellular vision system
- Cellular multiadaptive analogic achitecture: a computational framework for UAV applications
- Receptive field atlas and related CNN models
Authors: Gál, V; Hámori, J; Roska, T; Bálya, D; Borostyánkői, ZS; Brendel, M; Lotz, K; Négyessy, L; Orzó, L; Petrás, I; Rekeczky, CS; Takács, J; Venetiáner, P; Vidnyánszky, Z; Zarándy, ÁDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 2004.Published by: INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS (Volume no.: 14, Issue no.: 2, Page: 551-584)
- Adaptive perception with locally adaptable sensor array
- The new framework of applications: the Aladdin system
- Cellular Neural Networks: A paradigm for nonlinear spatio-temporal processing
- Analogikai celluláris számítógépek. Egy új számítógépelv.
- The computational infrastructure of analogic CNN computing - Part I: The CNN-UM chip prototyping system.
- Fault-tolerant design of analogic CNN templates and algorithms - Part I: The binary output case.
- An emulated digital CNN Implementation.
Authors: Keresztes, P; Zarándy, Á; Roska, T; Szolgay, P; Bezák, T; Hídvégi, T; Jónás, P; Katona, ADepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1999.Published by: JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY (Volume no.: 23, Issue no.: 2-3, Page: 291-303)
- CNN-based models for color vision and visual illusions.
- The art of CNN template design.
- Mammographiás szűrőállomásokhoz telepített analogikai munkahely adatkezelése.
- Implementation of Binary and gray-scale mathematical morphology on the CNN universal machine.
- Implementation of large-neighbourhood non-linear templates on the CNN universal machine.
- 0.8-?m CMOS two-dimensional programmable mixed-signal focal-plane array processor with on-chip binary imaging and instructions storage.
Authors: Domínguez-Castro, R; Espejo, S; Rodríguez-Vázquez, A; Carmona, RA; Földesy, P; Zarándy, Á; Szolgay, P; Szirányi, T; Roska, TDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1997.Published by: IEEE JOURNAL OF SOLID-STATE CIRCUITS (Volume no.: 32, Issue no.: 7, Page: 1013-1026)
- Mammogram and echocardiogram analysis by using cellular neural network technology.
- New results and measurements related to some tasks in object-oriented dynamic image coding using CNN universal chips.
- CNN universal chips crank up the computing power
- Spatial logic algorithm using basic morphological analogic CNN operators.
- The use of CNN models in the subcortical visual pathway
Authors: Roska, T; Hámori, J; Lábos, E; Lotz, K; Orzó, L; Takács, J; Venetianer, PL; Vidnyánszky, Z; Zarándy, ÁDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1993.Published by: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-FUNDAMENTAL THEORY AND APPLICATIONS (Volume no.: 40, Issue no.: 3, Page: 182-195)
- A digital multiprocessor hardware accelerator board for cellular neural networks: CNN-HAC
Authors: Roska, T; Bártfay, G; Szolgay, P; Szirányi, T; Radványi, A; Kozek, T; Ugray, ZS; Zarándy, ÁDepartment: Cellular Sensory and Optical Wave Computing LaboratoryDate: 1992.Published by: INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS (Volume no.: 20, Issue no.: 5, Page: 589-599)
New search
|
Search 
Magyar
