Publication result detail

The Estimation of a Depth Map Using Spatial Continuity and Edges

BOLEČEK, L.; ŘÍČNÝ, V.

Original Title

The Estimation of a Depth Map Using Spatial Continuity and Edges

English Title

The Estimation of a Depth Map Using Spatial Continuity and Edges

Type

Paper in proceedings (conference paper)

Original Abstract

This paper deals with creating depth maps from two images. The initial map is created using the sum of the absolute differences of the each image points neighborhood. Many discontinuities are in this map. Therefore, we have to use some approach for its improvement. The proposed method utilizes a combination of a few approaches. The first approach is based on the assumption of continuity of the depth map in rows and utilizing information about edges in images. We designed rules for filling zero areas in the initial depth map. The second step uses disparity of significant points found in zero areas. The significant points are found by the algorithm Speeded Up Robust Features (SURF). The applicability of the proposed method is demonstrated on a few images from Middlebury Stereo Datasets. In the future, we will execute subjective tests for examining the influence of the depth map to the evaluation of the spatial effect. The proposed methods will be used as tool for depth maps generation with various quality.

English abstract

This paper deals with creating depth maps from two images. The initial map is created using the sum of the absolute differences of the each image points neighborhood. Many discontinuities are in this map. Therefore, we have to use some approach for its improvement. The proposed method utilizes a combination of a few approaches. The first approach is based on the assumption of continuity of the depth map in rows and utilizing information about edges in images. We designed rules for filling zero areas in the initial depth map. The second step uses disparity of significant points found in zero areas. The significant points are found by the algorithm Speeded Up Robust Features (SURF). The applicability of the proposed method is demonstrated on a few images from Middlebury Stereo Datasets. In the future, we will execute subjective tests for examining the influence of the depth map to the evaluation of the spatial effect. The proposed methods will be used as tool for depth maps generation with various quality.

Keywords

3D reconstruction, features points, image correspondence

Key words in English

3D reconstruction, features points, image correspondence

Authors

BOLEČEK, L.; ŘÍČNÝ, V.

RIV year

2014

Released

03.07.2013

ISBN

978-1-4799-0403-7

Book

37th International Conference on Telecommunications and Signal Processing (TSP)

Edition

první

Pages from

51

Pages to

54

Pages count

4

BibTex

@inproceedings{BUT101179,
  author="Libor {Boleček} and Václav {Říčný}",
  title="The Estimation of a Depth Map Using Spatial Continuity and Edges",
  booktitle="37th International Conference on Telecommunications and Signal Processing (TSP)",
  year="2013",
  series="první",
  number="1",
  pages="51--54",
  isbn="978-1-4799-0403-7"
}