Object Recognition Using Three-Dimensional Information

Oshima, Masaki; Shirai, Yoshiaki

doi:10.1109/tpami.1983.4767405

Cited by 223 publications

(56 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Now note that we have succeeded in linking these operators together, so that we can combine the information gotten from their feature values. If we use the first operator application to look up the 4-interpretations of Pl, P2, P3 and p 4 for some model, and the second to look up the 4-interpretations of P2, P4, P 3 and ps, we can retain the 5-interpretations consistent with both. This linking procedure can be repeated indefinitely.…”

Section: Linkable Tripod Operators; the Four-point Casementioning

confidence: 99%

See 1 more Smart Citation

Tripod Operators for the Interpretation of Range Images

Pipitone¹

1991

View full text Add to dashboard Cite

MARO 1991j' DApproved for public release; distribution unlimited. 304 034 ABSTRACT (Maximum 200 words)A new kind of feature extraction operator for range images is introduced that facilitates object recognition in several ways. It consists of three points in 3-space fixed at the vertices of an equilateral triangle and one or more curves, called test curves, fixed in the reference frame of the triangle. This mathematical structure is then moved as a rigid body until the vertices all lie on the surface of some range image or modeled object. The point(s) of intersection of the test curve(s) and the surface are used to define local shape features which are invariant under rigid motions. These features can be used to automatically find distinctive regions at which the begin recognition, to rapidly screen candidate modeled objects for a match, and to speed pruning in the generation of interpretation trees. Tripod operators are applicable to all 3-D shapes, and reduce the need for specialized feature detectors. SUBJECT TERMS 15. NUMBER OF PAGES

show abstract

Section: Linkable Tripod Operators; the Four-point Casementioning

confidence: 99%

“…This general approach was introduced by several authors [2,3,4,10] within a short time. Our work differs from these efforts in that we provide mechanisms for efficiently prestoring model information so that the costly early stages of interpretation tree generation can be avoided at recognition time.…”

Section: Introductionmentioning

confidence: 99%

Tripod Operators for the Interpretation of Range Images

Pipitone¹

1991

View full text Add to dashboard Cite

show abstract

“…One well known technique traces the scene with parallel light stripes ( [147,5,133,150,127,36]). The three dimensional coordinates of individual points on the stripes can be found by triangulation along the baseline between the stripe source and sensor.…”

Section: From What Sources Can We Expect To Get Surface Information?mentioning

confidence: 99%

“…This method of data collection has again become popular (e.g. [127,36]). A particularly significant result was obtained by Faugeras and Hebert [63], who recognized an irregular part using locally planar patches, by matching to an empirically derived model (although the matcher only found a few correspondences).…”

Section: Relation To Other Researchmentioning

confidence: 99%

From surfaces to objects: computer vision and three dimensional scene analysis

Fisher

1990

Choice Reviews Online

View full text Add to dashboard Cite

“…The former approach has the advantage of having many existing algorithms for patch extraction, even from many years ago [23,3,14,9,17]. A recent comparison in [15] concluded that in many ways, our single image planar patch segmentation algorithm has the best performance among current algorithms.…”

Section: Introductionmentioning

confidence: 99%