Conference Paper

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

DOI: 10.1117/12.849882 Conference: , Laser Radar Technology and Applications XV


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.

7 Reads
  • Source
    • "However, little research has been performed on species-level classification using both HSI and wLiDAR. Sarrazin et al. (2010) performed exploratory species-level classification using wLiDAR and HSI. They deconvolved the wLiDAR data, corrected data for topographic variation, and extracted structural and spectral features from each modality. "
    [Show abstract] [Hide abstract]
    ABSTRACT: The mapping of tree species, in general and specifically in diverse savanna environments, is of great interest to ecologists and natural resource managers. This study focused on the fusion of imaging spectroscopy and small-footprint waveform light detection and ranging (wLiDAR) data to improve per species structural parameter estimation towards classification and herbaceous biomass modeling. The species classification approach was based on stepwise discriminant analysis (SDA) and used feature metrics from hyperspectral imagery (HSI) combined with wLiDAR data. It was found that fusing data with the SDA did not improve classification significantly, especially compared with the HSI classification results. As for herbaceous biomass modeling, the statistical approach used for the fusion of wLiDAR and HSI was forward selection regression modeling, which selects significant independent metrics and models those to measured biomass. The results indicated that fine scale wLiDAR may not be able to provide accurate measurement of herbaceous biomass, although other factors could have contributed to the relatively poor results, such as the senescent state of grass, the narrow biomass range that was measured, and the low biomass values, i.e., the limited laser-target interactions. We concluded that although fusion did not result in significant improvements over single modality approaches in these two use cases, there is a need for further investigation during the peak growing season.
    Canadian Journal of Remote Sensing 12/2011; 37(06):653-665. DOI:10.5589/m12-007 · 1.73 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: Full-waveform small-footprint Light Detection and Ranging (LiDAR) is still in the early stages of development for forest structure assessment, in part due to the complex interaction between a laser pulse and the forest structure, which is not yet fully understood. In recent years, simulation studies (which claim absolute ground truth) have sought to tackle this problem. The challenge remains to determine the limit of structural fidelity, in terms of tree structural components, that is required for waveform-based simulation studies. Understanding of such interactions could lead to improved biophysical modeling from LiDAR waveform signals. We present a simulation study that evaluates the impact of tree structural components on received waveform signals across different outgoing pulse widths and scanning angles. The simulation was performed on a small red maple (Acer rubrum) and red oak (Quercus rubra) stand. It was concluded the back-scattered waveform is dominated by the leaves, while the trunks, twigs, and leaf stems had a minimal impact on the signal. Scan angle (0°, 10°, and 20°) and outgoing pulse width (4 ns, 8 ns, and 16 ns) do not have as statistically significant (95% confidence) impact on mean waveform comparison statistics. This result has implications on the level of complexity required for future simulations and for waveform LiDAR based structural algorithm development.
    Canadian journal of remote sensing 07/2013; DOI:10.5589/m13-015 · 1.73 Impact Factor