Abstract
Mobile Laser Scanning data were collected simultaneously with hyperspectral data using the Finnish Geodetic Institute Sensei system. The data were tested for tree species classification. The test area was an urban garden in the City of Espoo, Finland. Point clouds representing 168 individual tree specimens of 23 tree species were determined manually. The classification of the trees was done using first only the spatial data from point clouds, then with only the spectral data obtained with a spectrometer, and finally with the combined spatial and hyperspectral data from both sensors. Two classification tests were performed: the separation of coniferous and deciduous trees, and the identification of individual tree species. All determined tree specimens were used in distinguishing coniferous and deciduous trees. A subset of 133 trees and 10 tree species was used in the tree species classification. The best classification results for the fused data were 95.8% for the separation of the coniferous and deciduous classes. The best overall tree species classification succeeded with 83.5% accuracy for the best tested fused data feature combination. The respective results for paired structural features derived from the laser point cloud were 90.5% for the separation of the coniferous and deciduous classes and 65.4% for the species classification. Classification accuracies with paired hyperspectral reflectance value data were 90.5% for the separation of coniferous and deciduous classes and 62.4% for different species. The results are among the first of their kind and they show that mobile collected fused data outperformed single-sensor data in both classification tests and by a significant margin.
Highlights
We propose the use of mobile hyperspectral data together with mobile laser-scanning (MLS) data in tree species classification
LiDAR-derived features; (ii) The overall results of both single and paired hyperspectral features; (iii) The comparison of the results obtained from the LiDAR-derived and the hyperspectral features; (iv) The detailed classification results of combined feature quadruples consisting of two hyperspectral features at different wavelengths and of two LiDAR-derived features; (v) Different classification feature selection methods are compared in order to validate the presented results
The best paired classification result was 90.5% and it was obtained with LiDAR-derived features that were the relative number of points over 10% of the normalized tree height (PR, hN > 0.5) and the kurtosis of the point cloud height distribution
Summary
We propose the use of mobile hyperspectral data together with mobile laser-scanning (MLS) data in tree species classification. A MLS system is, similar to airborne laser scanning (ALS) systems, but typically applied MLS platforms include a van or a car. Compared to airborne laser systems, which typically collect point clouds with a resolution of 0.5–40 pts/m2 from an altitude of 100–3000 m, MLS provides point clouds with a resolution of hundreds or even thousands of points/m2 from a distance of some dozens of meters. ALS data provides mainly horizontal structures in urban environments, such as the roofs of buildings, while MLS is at its best in detecting vertical objects, e.g., walls of buildings, trees, and lampposts [15,25,26]. MLS is used in road line and pavement mapping studies to provide very high resolution spatial surface data [14,17]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
