Title :
Range sensing by projecting multiple slits with random cuts
Author :
Maruyama, Minoru ; Abe, Shigeru
Author_Institution :
Mitsubishi Electr. Corp., Hyogo, Japan
fDate :
6/1/1993 12:00:00 AM
Abstract :
A method for range sensing that projects a single pattern of multiple slits is described. Random dots are used to identify each slit. The random dots are given as randomly distributed cuts on each slit. Thus, each slit is divided into many small line segments. Segment matching between the image and the pattern is performed to obtain 3-D data. Using adjacency relations among slit segments, the false matches are reduced, and segment pairs whose adjacent segments correspond with each other are extracted and considered to be correct matches. Then, from the resultant matches, the correspondence is propagated by exploiting the adjacency relationships to get an entire range image
Keywords :
image recognition; image segmentation; 3-D data; adjacency relations; image recognition; image segmentation; multiple slits projection; random cuts; random dots; range sensing; segment matching; Data acquisition; Data mining; Image segmentation; Machine intelligence; Pattern matching; Pattern recognition; Shape;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
