Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems

Diane Sarrazin, Jan Van Aardt, Gregory P. Asner, Joe McGlinchy, David W. Messinger, Jiaying Wu

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

2 Citations (Scopus)

Abstract

Research groups at Rochester Institute of Technology and Carnegie Institution for Science are studying savanna ecosystems and are using data from the Carnegie Airborne Observatory (CAO), which integrates advanced imaging spectroscopy and waveform light detection and ranging (wLIDAR) data. This component of the larger ecosystem project has as a goal the fusion of imaging spectroscopy and wLIDAR data in order to improve per-species structural parameter estimation. Waveform LIDAR has proven useful for extracting high vertical resolution structural parameters, while imaging spectroscopy is a well-established tool for species classification. We evaluated data fusion at the feature level, using a stepwise discrimination analysis (SDA) approach with feature metrics from both hyperspectral imagery (HSI) and wLIDAR data. It was found that fusing data with the SDA improved classification, although not significantly. The principal component analysis (PCA) provided many useful bands for the SDA selection, both from HSI and wLIDAR. The overall classification accuracy was 68% for wLIDAR, 59% for HSI, and 72% for the fused data set. The kappa accuracy achieved with wLIDAR was 0.49, 0.36 for HSI, and 0.56 for both modalities.

Original languageEnglish (US)
Title of host publicationLaser Radar Technology and Applications XV
DOIs
StatePublished - Jun 25 2010
Externally publishedYes
EventLaser Radar Technology and Applications XV - Orlando, FL, United States
Duration: Apr 6 2010Apr 9 2010

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume7684
ISSN (Print)0277-786X

Conference

ConferenceLaser Radar Technology and Applications XV
CountryUnited States
CityOrlando, FL
Period4/6/104/9/10

Fingerprint

Hyperspectral Data
ecosystems
Ecosystem
Waveform
Ecosystems
waveforms
Hyperspectral Imagery
Imaging Spectroscopy
imagery
Discrimination
discrimination
Spectroscopy
Imaging techniques
Structural Parameters
spectroscopy
Data fusion
Observatories
multisensor fusion
Data Fusion
Parameter estimation

Keywords

  • Discriminant analysis
  • LIDAR
  • Principal component analysis
  • Species classification
  • Waveform

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Sarrazin, D., Van Aardt, J., Asner, G. P., McGlinchy, J., Messinger, D. W., & Wu, J. (2010). Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems. In Laser Radar Technology and Applications XV [76841H] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7684). https://doi.org/10.1117/12.849882

Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems. / Sarrazin, Diane; Van Aardt, Jan; Asner, Gregory P.; McGlinchy, Joe; Messinger, David W.; Wu, Jiaying.

Laser Radar Technology and Applications XV. 2010. 76841H (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 7684).

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

Sarrazin, D, Van Aardt, J, Asner, GP, McGlinchy, J, Messinger, DW & Wu, J 2010, Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems. in Laser Radar Technology and Applications XV., 76841H, Proceedings of SPIE - The International Society for Optical Engineering, vol. 7684, Laser Radar Technology and Applications XV, Orlando, FL, United States, 4/6/10. https://doi.org/10.1117/12.849882
Sarrazin D, Van Aardt J, Asner GP, McGlinchy J, Messinger DW, Wu J. Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems. In Laser Radar Technology and Applications XV. 2010. 76841H. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.849882
Sarrazin, Diane ; Van Aardt, Jan ; Asner, Gregory P. ; McGlinchy, Joe ; Messinger, David W. ; Wu, Jiaying. / Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems. Laser Radar Technology and Applications XV. 2010. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{6c99ab6b5d944fbd8d4446d32d7012bc,
title = "Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems",
abstract = "Research groups at Rochester Institute of Technology and Carnegie Institution for Science are studying savanna ecosystems and are using data from the Carnegie Airborne Observatory (CAO), which integrates advanced imaging spectroscopy and waveform light detection and ranging (wLIDAR) data. This component of the larger ecosystem project has as a goal the fusion of imaging spectroscopy and wLIDAR data in order to improve per-species structural parameter estimation. Waveform LIDAR has proven useful for extracting high vertical resolution structural parameters, while imaging spectroscopy is a well-established tool for species classification. We evaluated data fusion at the feature level, using a stepwise discrimination analysis (SDA) approach with feature metrics from both hyperspectral imagery (HSI) and wLIDAR data. It was found that fusing data with the SDA improved classification, although not significantly. The principal component analysis (PCA) provided many useful bands for the SDA selection, both from HSI and wLIDAR. The overall classification accuracy was 68{\%} for wLIDAR, 59{\%} for HSI, and 72{\%} for the fused data set. The kappa accuracy achieved with wLIDAR was 0.49, 0.36 for HSI, and 0.56 for both modalities.",
keywords = "Discriminant analysis, LIDAR, Principal component analysis, Species classification, Waveform",
author = "Diane Sarrazin and {Van Aardt}, Jan and Asner, {Gregory P.} and Joe McGlinchy and Messinger, {David W.} and Jiaying Wu",
year = "2010",
month = "6",
day = "25",
doi = "10.1117/12.849882",
language = "English (US)",
isbn = "9780819481481",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Laser Radar Technology and Applications XV",

}

TY - GEN

T1 - Fusing waveform LIDAR and hyperspectral data for species-level structural assessment in savanna ecosystems

AU - Sarrazin, Diane

AU - Van Aardt, Jan

AU - Asner, Gregory P.

AU - McGlinchy, Joe

AU - Messinger, David W.

AU - Wu, Jiaying

PY - 2010/6/25

Y1 - 2010/6/25

N2 - Research groups at Rochester Institute of Technology and Carnegie Institution for Science are studying savanna ecosystems and are using data from the Carnegie Airborne Observatory (CAO), which integrates advanced imaging spectroscopy and waveform light detection and ranging (wLIDAR) data. This component of the larger ecosystem project has as a goal the fusion of imaging spectroscopy and wLIDAR data in order to improve per-species structural parameter estimation. Waveform LIDAR has proven useful for extracting high vertical resolution structural parameters, while imaging spectroscopy is a well-established tool for species classification. We evaluated data fusion at the feature level, using a stepwise discrimination analysis (SDA) approach with feature metrics from both hyperspectral imagery (HSI) and wLIDAR data. It was found that fusing data with the SDA improved classification, although not significantly. The principal component analysis (PCA) provided many useful bands for the SDA selection, both from HSI and wLIDAR. The overall classification accuracy was 68% for wLIDAR, 59% for HSI, and 72% for the fused data set. The kappa accuracy achieved with wLIDAR was 0.49, 0.36 for HSI, and 0.56 for both modalities.

AB - Research groups at Rochester Institute of Technology and Carnegie Institution for Science are studying savanna ecosystems and are using data from the Carnegie Airborne Observatory (CAO), which integrates advanced imaging spectroscopy and waveform light detection and ranging (wLIDAR) data. This component of the larger ecosystem project has as a goal the fusion of imaging spectroscopy and wLIDAR data in order to improve per-species structural parameter estimation. Waveform LIDAR has proven useful for extracting high vertical resolution structural parameters, while imaging spectroscopy is a well-established tool for species classification. We evaluated data fusion at the feature level, using a stepwise discrimination analysis (SDA) approach with feature metrics from both hyperspectral imagery (HSI) and wLIDAR data. It was found that fusing data with the SDA improved classification, although not significantly. The principal component analysis (PCA) provided many useful bands for the SDA selection, both from HSI and wLIDAR. The overall classification accuracy was 68% for wLIDAR, 59% for HSI, and 72% for the fused data set. The kappa accuracy achieved with wLIDAR was 0.49, 0.36 for HSI, and 0.56 for both modalities.

KW - Discriminant analysis

KW - LIDAR

KW - Principal component analysis

KW - Species classification

KW - Waveform

UR - http://www.scopus.com/inward/record.url?scp=77953741986&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77953741986&partnerID=8YFLogxK

U2 - 10.1117/12.849882

DO - 10.1117/12.849882

M3 - Conference contribution

AN - SCOPUS:77953741986

SN - 9780819481481

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Laser Radar Technology and Applications XV

ER -