Stereoscopic depth perception for robot vision: algorithms and architectures

Conference · Sat Jan 01 00:00:00 EST 1983

OSTI ID:5139744

Safranek, R J; Kak, A C

The implementation of depth perception algorithms for computer vision is considered. In automated manufacturing, depth information is vital for tasks such as path planning and 3-d scene analysis. The presentation begins with a survey of computer algorithms for stereoscopic depth perception. The emphasis is on the Marr-Poggio paradigm of human stereo vision and its computer implementation. In addition, a stereo matching algorithm based on the relaxation labelling technique is examined. A computer architecture designed to efficiently implement stereo matching algorithms, an MIMD array interfaced to a global memory, is presented. 9 references.

• OSTI ID: 5139744
• Resource Relation: Conference: Sponsored by IEEE, Port Chester, NY, USA, 31 Oct 1983
• Country of Publication: United States
• Language: English

Related Subjects

99 GENERAL AND MISCELLANEOUS//MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE
ROBOTS
VISION
ALGORITHMS
ARCHITECTURE
COMPUTERS
IMAGE PROCESSING
PATTERN RECOGNITION
MATHEMATICAL LOGIC
PROCESSING
990200* - Mathematics & Computers