Parallel algorithms for computer vision. Final report, 31 August 1988-31 January 1990

Technical Report · Sun Apr 01 04:00:00 EDT 1990

OSTI ID:6637970

Poggio, T

The main effort in this project has been directed towards the development of an integrated vision system, - the Vision Machine - based on a parallel supercomputer. The core of the Vision Machine is in fact a set of parallel algorithms for visual recognition and navigation in an unstructured environment. The present version of the Vision Machine has been demonstrated to process images in close to real time by (1) computing first several low-level cues, such as edges, stereo disparity, optical flow, color and texture, (2) integrating them to extract a cartoon-like description of the scene in terms of the physical discontinuities of surfaces, and (3) using this cartoon in a recognition stage, based on parallel model matching. In addition to the development of the parallel algorithms, their implementation and testing, we have also done substantial work in several areas that are very closely related. These include (1) design and fabrication of VLSI circuits to transfer to potentially cheap and fast hardware some of the software algorithms, (2) initial development of techniques to synthesize by learning vision algorithms, and (3) several projects involving autonomous navigation of small robots.

• Research Organization: Massachusetts Inst. of Tech., Cambridge, MA (USA). Artificial Intelligence Lab.
• OSTI ID: 6637970
• Report Number(s): AD-A-221871/7/XAB
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS
990200* -- Mathematics & Computers
ALGORITHMS
COMPUTER CODES
COMPUTER GRAPHICS
COMPUTERS
DIGITAL COMPUTERS
DOCUMENT TYPES
ENVIRONMENT
IMAGE PROCESSING
LEARNING
MATHEMATICAL LOGIC
OPTICAL PROPERTIES
PARALLEL PROCESSING
PATTERN RECOGNITION
PHYSICAL PROPERTIES
PROCESSING
PROGRAMMING
PROGRESS REPORT
REAL TIME SYSTEMS
ROBOTS
SUPERCOMPUTERS
SURFACES
VISION