Abstract
The Bayesian approach to vision provides a fruitful theoretical framework for integrating different depth modules. In this formulation depth can be represented by one or more surfaces. Prior probabilities, corresponding to natural constraints, can be defined on these surfaces to avoid the ill-posedness of vision. We advocate strong coupling between different depth cues, so that the different modules can interact during computation. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration, by the use of binary decision units. These units can be interpreted in terms of robust statistics. A number of existing psychophysical experiments can be understood within this framework.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of SPIE - The International Society for Optical Engineering |
| Editors | Paul S. Schenker |
| Publisher | Publ by Int Soc for Optical Engineering |
| Pages | 235-246 |
| Number of pages | 12 |
| Volume | 1383 |
| Publication status | Published - 1991 |
| Externally published | Yes |
| Event | Sensor Fusion III: 3-D Perception and Recognition - Boston, MA, USA Duration: 1990 Nov 5 → 1990 Nov 8 |
Other
| Other | Sensor Fusion III: 3-D Perception and Recognition |
|---|---|
| City | Boston, MA, USA |
| Period | 90/11/5 → 90/11/8 |
Fingerprint
ASJC Scopus subject areas
- Electrical and Electronic Engineering
- Condensed Matter Physics
Cite this
Shape-from-X. Psychophysics and computation. / Bulthoff, Heinrich; Yuille, Alan L.
Proceedings of SPIE - The International Society for Optical Engineering. ed. / Paul S. Schenker. Vol. 1383 Publ by Int Soc for Optical Engineering, 1991. p. 235-246.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Shape-from-X. Psychophysics and computation
AU - Bulthoff, Heinrich
AU - Yuille, Alan L.
PY - 1991
Y1 - 1991
N2 - The Bayesian approach to vision provides a fruitful theoretical framework for integrating different depth modules. In this formulation depth can be represented by one or more surfaces. Prior probabilities, corresponding to natural constraints, can be defined on these surfaces to avoid the ill-posedness of vision. We advocate strong coupling between different depth cues, so that the different modules can interact during computation. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration, by the use of binary decision units. These units can be interpreted in terms of robust statistics. A number of existing psychophysical experiments can be understood within this framework.
AB - The Bayesian approach to vision provides a fruitful theoretical framework for integrating different depth modules. In this formulation depth can be represented by one or more surfaces. Prior probabilities, corresponding to natural constraints, can be defined on these surfaces to avoid the ill-posedness of vision. We advocate strong coupling between different depth cues, so that the different modules can interact during computation. This framework is rich enough to accommodate straightforwardly both consonant and contradictory cue integration, by the use of binary decision units. These units can be interpreted in terms of robust statistics. A number of existing psychophysical experiments can be understood within this framework.
UR - http://www.scopus.com/inward/record.url?scp=0025793020&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0025793020&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:0025793020
VL - 1383
SP - 235
EP - 246
BT - Proceedings of SPIE - The International Society for Optical Engineering
A2 - Schenker, Paul S.
PB - Publ by Int Soc for Optical Engineering
ER -