Tags

Type your tag names separated by a space and hit enter

Sampling the disparity space image.
IEEE Trans Pattern Anal Mach Intell. 2004 Mar; 26(3):419-25.IT

Abstract

A central issue in stereo algorithm design is the choice of matching cost. Many algorithms simply use squared or absolute intensity differences based on integer disparity steps. In this paper, we address potential problems with such approaches. We begin with a careful analysis of the properties of the continuous disparity space image (DSI) and propose several new matching cost variants based on symmetrically matching interpolated image signals. Using stereo images with ground truth, we empirically evaluate the performance of the different cost variants and show that proper sampling can yield improved matching performance.

Authors+Show Affiliations

Szeliski R
Microsoft Research, One Microsoft Way, Redmond, WA 98052, USA. szeliski@microsoft.com
Scharstein D
No affiliation info available

MeSH

AlgorithmsArtificial IntelligenceComputer GraphicsImage EnhancementImage Interpretation, Computer-AssistedImaging, Three-DimensionalInformation Storage and RetrievalNumerical Analysis, Computer-AssistedPattern Recognition, AutomatedPhotogrammetryReproducibility of ResultsSample SizeSensitivity and SpecificitySignal Processing, Computer-AssistedSubtraction Technique

Pub Type(s)

Comparative Study
Evaluation Study
Journal Article
Validation Study

Language

eng

PubMed ID

15376889

Clinical Trial Links

Stereo Photogrammetry Imaging in Normal Volunteers and Patients With Head and Facial Malformations

Citation

Szeliski, Richard, and Daniel Scharstein. "Sampling the Disparity Space Image." IEEE Transactions On Pattern Analysis and Machine Intelligence, vol. 26, no. 3, 2004, pp. 419-25.
Szeliski R, Scharstein D. Sampling the disparity space image. IEEE Trans Pattern Anal Mach Intell. 2004;26(3):419-25.
Szeliski, R., & Scharstein, D. (2004). Sampling the disparity space image. IEEE Transactions On Pattern Analysis and Machine Intelligence, 26(3), 419-25.
Szeliski R, Scharstein D. Sampling the Disparity Space Image. IEEE Trans Pattern Anal Mach Intell. 2004;26(3):419-25. PubMed PMID: 15376889.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Sampling the disparity space image. AU - Szeliski,Richard, AU - Scharstein,Daniel, PY - 2004/9/21/pubmed PY - 2004/10/13/medline PY - 2004/9/21/entrez SP - 419 EP - 25 JF - IEEE transactions on pattern analysis and machine intelligence JO - IEEE Trans Pattern Anal Mach Intell VL - 26 IS - 3 N2 - A central issue in stereo algorithm design is the choice of matching cost. Many algorithms simply use squared or absolute intensity differences based on integer disparity steps. In this paper, we address potential problems with such approaches. We begin with a careful analysis of the properties of the continuous disparity space image (DSI) and propose several new matching cost variants based on symmetrically matching interpolated image signals. Using stereo images with ground truth, we empirically evaluate the performance of the different cost variants and show that proper sampling can yield improved matching performance. SN - 0162-8828 UR - https://www.unboundmedicine.com/medline/citation/15376889/Sampling_the_disparity_space_image_ DB - PRIME DP - Unbound Medicine ER -