Abstract
We have developed a prototype for a miniaturized, active vision system with a sensor architecture based on a logarithmically structured, space-variant, pixel geometry. The central part of the image has a high resolution, and the periphery has a a smoothly falling resolution. The human visual system uses a similar image architecture. Our system integrates a miniature CCD-based camera, a novel pantilt actuator/controller, general purpose processors, a video-telephone modem and a display. Due to the ability of space-variant sensors to cover large work spaces, yet provide high acuity with an extremely small number of pixels, architectures with space-variant, active vision systems provide a potential for reductions in system size and cost of several orders of magnitude. Cortex-I takes up less than a third of a cubic foot, including camera, actuators, control, computers, and power supply, and was built for a (one-off) parts cost of roughly US $2000. In this paper, we describe several applications that we have developed for Cortex-I such as tracking moving objects, visual attention, pattern recognition (license plate reading), and video-telephone communcications (teleoperation). We report here on the design of the camera and optics (8 × 8 × 8 mm), a method to convert the uniform image to a space-variant image, and a new miniature pan-tilt actuator, the spherical pointing motor (SPM), (4 × 5 × 6 cm). Finally, we discuss applications for motion tracking and license plate reading. Potential application domains for systems of this type include vision systems for mobile robots and robot manipulators, traffic monitoring systems, security and surveillance, telerobotics, and consumer video communications. The long-range goal of this project is to demonstrate that major new applications of robotics will become feasible when small, low-cost, machine-vision systems can be mass produced. We use the term “commodity robotics” to express the expected impact of the possibilities for opening up new application niches in robotics and machine vision, for what has until now been an expensive, and therefore limited, technology.
Similar content being viewed by others
References
Abbott AL, Ahuja N (1990) Active surface reconstruction by integrating focus, vergence, stereo, and camera calibration. International Conference on Computer Vision. IEEE Computer Society Press, Los Alamitos, CA
Abbott AL, Ahuja N (1991) The University of Illinois active vision system. Technical Report CV-91-8-2, University of Illinois, Beckman Institute
Allen PK, Yoshimi B, Timcenko A (1991) Real-time visual servoing. Proceedings of the 1991 IEEE International Conference on Robots and Automation, IEEE Computer Society Press, Los Alamitos, CA
Bajcsy R (1988) Active perception. IEEE Proceedings, 76:996–1005
Ballard DH (1989) Animate vision. Technical Report, Computer Science Department, University of Rochester, Rochester, NY
Baloch AA, Waxman AM (1991) Behavioral control of the mobile robot mavin. In: Antognetti, Milutinov (eds) Neural networks: concepts, applications, and implementations, Volume IV. Prentice Hall, Englewood Cliffs, NJ
Bederson BB (1992) A miniature space-variant active vision system: Cortex-I. PhD Thesis, Computer Science Department, Graduate School of Arts and Science, New York University, New York
Bederson BB, Wallace RS, Schwartz EL (1992) A miniature pantilt actuator: the spherical pointing motor. Technical Report 264, New York University, Computer Science Department, Robotics Research, New York, NY
Bederson BB, Wallace RS, Schwartz EL (1992) Two miniature pantilt devices. IEEE International Conference on Robotics and Automation. IEEE Computer Society Press, Los Alamitos, CA, pp 658–663
Bederson BB, Wallace RS, Schwartz EL (1994) A miniature pan-tilt actuator: the spherical pointing motor. IEEE Trans Robotics Automation
Brown C (ed) The Rochester robot. Technical Report 257, University of Rochester, Rochester, NY
Chaikin GM, Weiman CFR (1981) Image processing system. US Patent No. 4 267 573
Clark JJ, Ferrier NJ, (1988) Modal control of an attentive vision system. Second International Conference on Computer Vision, p 514
Dickmanns ED, Graefe V (1988) Applications of dynamic monocular machine vision. Machine Vision Appl 1:241–261
Kawarabayashi H, Watanabe M, Shirai Y, Asade M, Miura J (1991) Tracking of a moving object using an active vision system. Japan Mechanical Society, Robotics Mechatronics Conference Proceedings, pp 207–212
Krotkov E, Fuma F, Summers J (1988) An agile stereo camera system for flexible image aqisition. IEEE J Robotics Automation 4:108–113
Ong P-W (1992) Image Processing, pattern recognition and attentional algorithms in a space-variant active vision system. PhD Thesis, Computer Science Department, Graduate School of Arts and Science, New York University, NY
Ong P-W, Wallace RS, Schwartz EL (1992) Space-variant optical character recognition, 11th International Conference on Pattern Recognition. IEEE Computer Society Press, Los Alamitos, CA
Rizzi AA, Whitcomb LL, Koditschek DE (1991) Distributed real-time control of a spatial robot juggler. IEEE Computer Magazine
Rojer AS, Schwartz EL (1990) Design considerations for a spacevariant visual sensor with complex-logarithmic geometry. 10th International Conference on Pattern Recognition Atlantic City, NJ, IEEE Computer Society Press, 2:278–285
Rojer AS (1989) Space-variant computer vision with a complete-logarithmic sensor geometry. PhD thesis, Computer Science Department, Graduate School of Arts and Science, New York University, New York
Sandini G, Bosero F, Bottino F, Ceccherini A (1989) The use of an anthropomorphic visual sensor for motion estimation and object tracking. Image Understanding and Machine Vision Workshop. Optical Society of America, pp 1–5
Reference deleted
Sandini G, Dario P, Debusschere I (1989) Active vision based on space-variant sensing. 5th International Symposium on Robotics Research, MIT Press, MA
Schwartz EL (1977) Spatial mapping in primate sensory projection: analytical structure and relevance to perception. Biological Cybernetics 25:181–194
Schwartz EL, Merker B, Wolfson E, Shaw A (1988) Computational neuroscience: applications of computer graphics and image processing to two and three dimensional modeling of the functional architecture of visual cortex. IEEE Comput Graph Appl 8:13–28
Spiegel J van der, Kreider F, Claeys C, Debusschere I, Sandini G, Dario P, Fantini F, Belluti P, Soncini G (1989) A foveated retinalike sensor using ccd technology. In: Mead C, Ismail M (eds) Analog VLSI Implementations of Neural Networks. Kluwer, Boston
Wallace RS, Howard MD (1984) HBA vision architecture: built and benchmarked. IEEE Trans Patt Anal Machine Intell
Wallace RS, Ong P-W, Bederson BB, Schwartz EL (1991) Space-variant image processing. Technical Report 256, New York University, Computer Science Department, Robotics Research, New York, NY
Wallace RS, Ong P-W, Bederson BB, Schwartz EL (1994) Space-variant image processing. Int Comp Vision 13: 71–94
Wallace RS, Webb JA, Wu IC (1989) Architecture independent image processing: performance of apply on diverse architectures. Comp Vision Graph Information Processing, 48:265–276
Wallace RS (1994) Miniature direct drive rotary actuators II; Eye, finger and leg. Robotics and autonomous systems 13:97–105
Wallace RS (1993) Miniature direct drive rotary actuators. Robotics and autonomous systems II: 129–133
Weiman CF, Chaikin G (1979) Logarithmich spiral grids for image-processing and display. Comp Graph Image Processing 11:197–226
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Bederson, B.B., Wallace, R.S. & Schwartz, E. A miniaturized space-variant active vision system: Cortex-I. Machine Vis. Apps. 8, 101–109 (1995). https://doi.org/10.1007/BF01213475
Issue Date:
DOI: https://doi.org/10.1007/BF01213475