EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RESOLUTION FROM DENSE AERIAL IMAGE MATCHING

Research output: Contribution to conferencePaperResearchpeer review

Authors

  • Mohammad Omidalizarandi
  • Mohammad Saadatseresht

Research Organisations

External Research Organisations

  • University of Tehran
View graph of relations

Details

Original languageEnglish
Pages125-134
Number of pages10
Publication statusPublished - 2013

Abstract

In the recent years, 3D city reconstruction is one of the active researches in the field of photogrammetry. The goal of this work is to improve and extend region growing based segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral information of RGB and grayscale image to extract building roofs, streets and vegetation. In order to process 3D point clouds, hybrid segmentation is carried out in both object space and image space. Our experiments on two case studies verify that updating plane parameters and
robust least squares plane fitting improves the results of building extraction especially in case of low accurate point clouds. In addition, region growing in image space has been derived to the fact that grayscale image is more flexible than RGB image and results in more realistic building roofs.

Keywords

    Object surface segmentation, Image segmentation, Region growing, X-Y-Z image, Intensity

Cite this

EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RESOLUTION FROM DENSE AERIAL IMAGE MATCHING. / Omidalizarandi, Mohammad; Saadatseresht, Mohammad .
2013. 125-134.

Research output: Contribution to conferencePaperResearchpeer review

Download
@conference{8d7d1ac7250f4613aadb6b8f8a75ba9c,
title = "EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RESOLUTION FROM DENSE AERIAL IMAGE MATCHING",
abstract = "In the recent years, 3D city reconstruction is one of the active researches in the field of photogrammetry. The goal of this work is to improve and extend region growing based segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral information of RGB and grayscale image to extract building roofs, streets and vegetation. In order to process 3D point clouds, hybrid segmentation is carried out in both object space and image space. Our experiments on two case studies verify that updating plane parameters and robust least squares plane fitting improves the results of building extraction especially in case of low accurate point clouds. In addition, region growing in image space has been derived to the fact that grayscale image is more flexible than RGB image and results in more realistic building roofs. ",
keywords = "Object surface segmentation, Image segmentation, Region growing, X-Y-Z image, Intensity",
author = "Mohammad Omidalizarandi and Mohammad Saadatseresht",
year = "2013",
doi = "10.5121/csit.2013.3513",
language = "English",
pages = "125--134",

}

Download

TY - CONF

T1 - EXTENDED HYBRID REGION GROWING SEGMENTATION OF POINT CLOUDS WITH DIFFERENT RESOLUTION FROM DENSE AERIAL IMAGE MATCHING

AU - Omidalizarandi, Mohammad

AU - Saadatseresht, Mohammad

PY - 2013

Y1 - 2013

N2 - In the recent years, 3D city reconstruction is one of the active researches in the field of photogrammetry. The goal of this work is to improve and extend region growing based segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral information of RGB and grayscale image to extract building roofs, streets and vegetation. In order to process 3D point clouds, hybrid segmentation is carried out in both object space and image space. Our experiments on two case studies verify that updating plane parameters and robust least squares plane fitting improves the results of building extraction especially in case of low accurate point clouds. In addition, region growing in image space has been derived to the fact that grayscale image is more flexible than RGB image and results in more realistic building roofs.

AB - In the recent years, 3D city reconstruction is one of the active researches in the field of photogrammetry. The goal of this work is to improve and extend region growing based segmentation in the X-Y-Z image in the form of 3D structured data with combination of spectral information of RGB and grayscale image to extract building roofs, streets and vegetation. In order to process 3D point clouds, hybrid segmentation is carried out in both object space and image space. Our experiments on two case studies verify that updating plane parameters and robust least squares plane fitting improves the results of building extraction especially in case of low accurate point clouds. In addition, region growing in image space has been derived to the fact that grayscale image is more flexible than RGB image and results in more realistic building roofs.

KW - Object surface segmentation, Image segmentation, Region growing, X-Y-Z image, Intensity

U2 - 10.5121/csit.2013.3513

DO - 10.5121/csit.2013.3513

M3 - Paper

SP - 125

EP - 134

ER -