Synonyms
Definition
An aspect is defined as a set of topologically equivalent views of a three-dimensional object. An aspect graph of an object is a graph that contains all aspects of the object as nodes with edges connecting to adjacent aspects. It describes transitions, referred to as visual events, between aspects of the object in a three-dimensional viewer’s space.
Theory
An aspect graph denotes segmentation of the possible view space into regions based on the topology of views of the object. Koenderink and van Doorn originally proposed the concept of aspects [11, 12]. A similar idea can be found in the work of J. J. Gibson [5] and M. Minsky [14]. The work of Chakravarty and Freeman employs a similar concept, referred to as characteristic views [3].
For the sake of a simple explanation, let’s consider the two-dimensional case of view-space...
This is a preview of subscription content, log in via an institution.
References
Bowyer KW, Dyer CR (1990) Aspect graphs: an introduction and survey of recent results. Int J Imaging Syst Technol 2(4):315–328
Callahan J (1985) A model for describing surface shape. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp 240–245
Chakravarty I, Freeman H (1982) Characteristic views as a basis for three-dimensional object recognition. In: Robot vision, vol 336. International Society for Optics and Photonics, pp 37–46
Faugeras O, Mundy J, Ahuja N, Dyer C, Pentland A, Jain R, Ikeuchi K, Bowyer K (1992) Why aspect graphs are not (yet) practical for computer vision. CVGIP: Image Underst 55(2):212–218
Gibson JJ (1966) The senses considered as perceptual systems
Gigus Z, Malik J (1990) Computing the aspect graph for line drawings of polyhedral objects. IEEE Trans Pattern Anal Mach Intell 12(2):113–122
Goad C (1987) Special purpose automatic programming for 3D model-based vision. In: Readings in computer vision. Elsevier, pp 371–381
Ikeuchi K (1987) Generating an interpretation tree from a cad model for 3D-object recognition in bin-picking tasks. Int J Comput Vis 1(2):145–165
Ikeuchi K, Hong KS (1991) Determining linear shape change: toward automatic generation of object recognition programs. CVGIP: Image Underst 53(2):154–170
Ikeuchi K, Kanade T (1989) Modelling sensors: toward automatic generation of object recognition program. Comput Vis Graph Image Process 48(1):50–79
Koenderink JJ, Van Doorn AJ (1976) The singularities of the visual mapping. Biol Cybern 24(1):51–59
Koenderink JJ, van Doorn AJ (1979) The internal representation of solid shape with respect to vision. Biol Cybern 32(4):211–216
Kriegman DJ, Ponce J (1990) Computing exact aspect graphs of curved objects: solids of revolution. Int J Comput Vis 5(2):119–135
Minsky M (1974) A framework for representing knowledge
Norman J (2002) Two visual systems and two theories of perception: an attempt to reconcile the constructivist and ecological approaches. Behav Brain Sci 25(1):73–96
PetitJean S, Ponce J, Kriegman DJ (1992) Computing exact aspect graphs of curved objects: algebraic surfaces. Int J Comput Vis 9(3):231–255
Plantinga H, Dyer CR (1990) Visibility, occlusion, and the aspect graph. Int J Comput Vis 5(2):137–160
Rieger JH (1987) On the classification of views of piecewise smooth objects. Image Vis Comput 5(2):91–97
Sripradisvarakul T, Jain R (1989) Generating aspect graphs for curved objects. In: Proceedings of the Workshop on Interpretation of 3D Scenes. IEEE, pp 109–115
Stewman J, Bowyer KW (1987) Aspect graphs for planar-face convex objects. In: Proceedings of the IEEE Workshop on Computer Vision, pp 123–130
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this entry
Cite this entry
Ikeuchi, K. (2021). Aspect Graph. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_868-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03243-2_868-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03243-2
Online ISBN: 978-3-030-03243-2
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering