Accurate surface description from binocular stereo

“…We can therefore remove the inconsistent disparity values to increase the accuracy. This process is called cross checking [6]. Working with rectified images, it is quite easy to efficiently implement cross-checking.…”

Section: Disparity Selectionmentioning

confidence: 99%

A versatile stereo implementation on commodity graphics hardware

Yang

Pollefeys

2005

Real-Time Imaging

View full text Add to dashboard Cite

“…Image matching is widely considered to be the most difficult to solve and clearly dependent on the choice of features [3], which are application dependent and can differ from simple pointlike ones to very complex structures.…”

Section: Introductionmentioning

confidence: 99%

Feature extraction from aerial images and structural stereo matching

Torkar

Pavešić²

1996

Proceedings of 13th International Conference on Pattern Recognition

View full text Add to dashboard Cite

In this paper, a method of generating structural descriptions of stereo image pairs and their matching t o Tecouer 3-0 f o r m of objects in space, is discussed. T h e method consists of the following steps: firstly, straight line segments are extracted in both images and the relations a m o n g t h e m are investigated. T h e relational subgraphs are constructed then, and the correspondence graph is created. Using the "stable marriage" searching algorithm the features in one image corresponding to features in the other image are found. T h e method was tested o n a set of aerial stereo images of urban .scenes.

show abstract

Accurate surface description from binocular stereo

Cited by 16 publications

References 14 publications

Real-time stereo on GPGPU using progressive multi-resolution adaptive windows

Real-time stereo on GPGPU using progressive multi-resolution adaptive windows

A versatile stereo implementation on commodity graphics hardware

Feature extraction from aerial images and structural stereo matching

Contact Info

Product

Resources

About