Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

Yang Cao; Hong Wei; Huijie Zhao

doi:10.1109/PRRS.2008.4783166

Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

Yang Cao^*
, Hong Wei
, Huijie Zhao

^*Corresponding author for this work

School of Artificial Intelligence(Institute of Artificial Intelligence)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

4 Scopus citations

Abstract

In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and coregistered bands.

Original language	English
Title of host publication	2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008
DOIs	https://doi.org/10.1109/PRRS.2008.4783166
State	Published - 2008
Event	2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008 - Tampa, FL, United States Duration: 7 Dec 2008 → 7 Dec 2008

Publication series

Name	2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008

Conference

Conference	2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008
Country/Territory	United States
City	Tampa, FL
Period	7/12/08 → 7/12/08

Access to Document

10.1109/PRRS.2008.4783166

Cite this

@inproceedings{aac0e62902564e5482877988a516e55f,

title = "Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands",

abstract = "In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and coregistered bands.",

author = "Yang Cao and Hong Wei and Huijie Zhao",

year = "2008",

doi = "10.1109/PRRS.2008.4783166",

language = "英语",

isbn = "9781424426539",

series = "2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008",

booktitle = "2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008",

note = "2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008 ; Conference date: 07-12-2008 Through 07-12-2008",

}

Cao, Y, Wei, H & Zhao, H 2008, Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands. in 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008., 4783166, 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008, 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008, Tampa, FL, United States, 7/12/08. https://doi.org/10.1109/PRRS.2008.4783166

Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands. / Cao, Yang; Wei, Hong; Zhao, Huijie.
2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008. 2008. 4783166 (2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

AU - Cao, Yang

AU - Wei, Hong

AU - Zhao, Huijie

PY - 2008

Y1 - 2008

N2 - In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and coregistered bands.

AB - In this paper, a fuzzy Markov random field (FMRF) model is used to segment land-objects into tree, grass, building, and road regions by fusing remotely sensed LIDAR data and co-registered color bands, i.e. scanned aerial color (RGB) photo and near infra-red (NIR) photo. An FMRF model is defined as a Markov random field (MRF) model in a fuzzy domain. Three optimization algorithms in the FMRF model, i.e. Lagrange multiplier (LM), iterated conditional mode (ICM), and simulated annealing (SA), are compared with respect to the computational cost and segmentation accuracy. The results have shown that the FMRF model-based ICM algorithm balances the computational cost and segmentation accuracy in land-cover segmentation from LIDAR data and coregistered bands.

UR - https://www.scopus.com/pages/publications/63849158664

U2 - 10.1109/PRRS.2008.4783166

DO - 10.1109/PRRS.2008.4783166

M3 - 会议稿件

AN - SCOPUS:63849158664

SN - 9781424426539

T3 - 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008

BT - 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008

T2 - 2008 IAPR Workshop on Pattern Recognition in Remote Sensing, PRRS 2008

Y2 - 7 December 2008 through 7 December 2008

ER -

Optimization algorithms in FMRF model-based segmentation for LIDAR data and co-registered bands

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this