Feature extraction and tracking for large-scale geospatial data

Lina Yu, Feiyu Zhu, Hongfeng Yu, Jun Wang, Kwo Sen Kuo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Feature extraction and tracking is a fundamental operation used in many geoscience applications. In this paper, we present a scalable method for computing and tracking features on distributed memory machines for large-scale geospatial data. We carefully apply new communication schemes to minimize the data exchanged among the computing nodes in building and updating the global connectivity information of features. We present a theoretical complexity analysis, and show that our method can significantly reduce the communication cost compared to the traditional method.

Original languageEnglish (US)
Title of host publication2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1504-1507
Number of pages4
ISBN (Electronic)9781509033324
DOIs
StatePublished - Nov 1 2016
Event36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Beijing, China
Duration: Jul 10 2016Jul 15 2016

Publication series

NameInternational Geoscience and Remote Sensing Symposium (IGARSS)
Volume2016-November

Other

Other36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016
CountryChina
CityBeijing
Period7/10/167/15/16

Fingerprint

Feature extraction
Communication
communication
Data storage equipment
connectivity
Costs
cost
method
analysis

Keywords

  • Feature extraction and tracking
  • geospatial data
  • large-scale data
  • parallel and distributed computing

ASJC Scopus subject areas

  • Computer Science Applications
  • Earth and Planetary Sciences(all)

Cite this

Yu, L., Zhu, F., Yu, H., Wang, J., & Kuo, K. S. (2016). Feature extraction and tracking for large-scale geospatial data. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings (pp. 1504-1507). [7729384] (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2016.7729384

Feature extraction and tracking for large-scale geospatial data. / Yu, Lina; Zhu, Feiyu; Yu, Hongfeng; Wang, Jun; Kuo, Kwo Sen.

2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1504-1507 7729384 (International Geoscience and Remote Sensing Symposium (IGARSS); Vol. 2016-November).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Yu, L, Zhu, F, Yu, H, Wang, J & Kuo, KS 2016, Feature extraction and tracking for large-scale geospatial data. in 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings., 7729384, International Geoscience and Remote Sensing Symposium (IGARSS), vol. 2016-November, Institute of Electrical and Electronics Engineers Inc., pp. 1504-1507, 36th IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016, Beijing, China, 7/10/16. https://doi.org/10.1109/IGARSS.2016.7729384
Yu L, Zhu F, Yu H, Wang J, Kuo KS. Feature extraction and tracking for large-scale geospatial data. In 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1504-1507. 7729384. (International Geoscience and Remote Sensing Symposium (IGARSS)). https://doi.org/10.1109/IGARSS.2016.7729384
Yu, Lina ; Zhu, Feiyu ; Yu, Hongfeng ; Wang, Jun ; Kuo, Kwo Sen. / Feature extraction and tracking for large-scale geospatial data. 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1504-1507 (International Geoscience and Remote Sensing Symposium (IGARSS)).
@inproceedings{62ba016720ad43c595fa0e5ede4f9587,
title = "Feature extraction and tracking for large-scale geospatial data",
abstract = "Feature extraction and tracking is a fundamental operation used in many geoscience applications. In this paper, we present a scalable method for computing and tracking features on distributed memory machines for large-scale geospatial data. We carefully apply new communication schemes to minimize the data exchanged among the computing nodes in building and updating the global connectivity information of features. We present a theoretical complexity analysis, and show that our method can significantly reduce the communication cost compared to the traditional method.",
keywords = "Feature extraction and tracking, geospatial data, large-scale data, parallel and distributed computing",
author = "Lina Yu and Feiyu Zhu and Hongfeng Yu and Jun Wang and Kuo, {Kwo Sen}",
year = "2016",
month = "11",
day = "1",
doi = "10.1109/IGARSS.2016.7729384",
language = "English (US)",
series = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1504--1507",
booktitle = "2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings",

}

TY - GEN

T1 - Feature extraction and tracking for large-scale geospatial data

AU - Yu, Lina

AU - Zhu, Feiyu

AU - Yu, Hongfeng

AU - Wang, Jun

AU - Kuo, Kwo Sen

PY - 2016/11/1

Y1 - 2016/11/1

N2 - Feature extraction and tracking is a fundamental operation used in many geoscience applications. In this paper, we present a scalable method for computing and tracking features on distributed memory machines for large-scale geospatial data. We carefully apply new communication schemes to minimize the data exchanged among the computing nodes in building and updating the global connectivity information of features. We present a theoretical complexity analysis, and show that our method can significantly reduce the communication cost compared to the traditional method.

AB - Feature extraction and tracking is a fundamental operation used in many geoscience applications. In this paper, we present a scalable method for computing and tracking features on distributed memory machines for large-scale geospatial data. We carefully apply new communication schemes to minimize the data exchanged among the computing nodes in building and updating the global connectivity information of features. We present a theoretical complexity analysis, and show that our method can significantly reduce the communication cost compared to the traditional method.

KW - Feature extraction and tracking

KW - geospatial data

KW - large-scale data

KW - parallel and distributed computing

UR - http://www.scopus.com/inward/record.url?scp=85007482993&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85007482993&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2016.7729384

DO - 10.1109/IGARSS.2016.7729384

M3 - Conference contribution

AN - SCOPUS:85007482993

T3 - International Geoscience and Remote Sensing Symposium (IGARSS)

SP - 1504

EP - 1507

BT - 2016 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2016 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -