The unmanned aerial vehicle (UAV) plays an increasingly important role in monitoring and managing islands recently for their high feasibility and the miniaturization of sensors, which provide new possibilities for accurate island green cover mapping. We developed a framework that integrates UAV-acquired high-spatial resolution multispectral image and LiDAR data for effective object-based green cover mapping of Donkey Island in the Yellow Sea, China. LiDAR-derived structural and intensity information were combined with multispectral-derived spectral information for obtaining green cover objects. Five kinds of feature types [i.e., spectral, texture, height, intensity, and geometry features (GFs)] were calculated based on each object for green cover classification. Meanwhile, a multiple classifier system was adopted to improve the classification accuracy. The results indicate that the accuracy of green cover mapping could be significantly improved by the combination of multiple feature types. The inclusion of height and intensity features (IFs) can increase the overall classification accuracy by 7% and 5%, respectively, but the statistical significant differences are not found between these two feature types. The best green cover map is generated via a feature group obtained by the sequential backward selection with random forest method, reaching an overall accuracy of 88.5% and overall disagreement of 18.5%. Among the three major green cover classes, the accuracy of shrub class mapping improves the most when compared to classification using individual data, followed by tree and grass. Analysis of feature importance implies that spectral, height, and IFs are more beneficial to green cover mapping compared to texture and GFs. Furthermore, integrating multispectral and LiDAR data can provide more reliable green cover distribution maps and reduce the classification uncertainties.
KEYWORDS: RGB color model, Data modeling, Unmanned aerial vehicles, LIDAR, Image classification, Sensors, Roads, Image segmentation, Data acquisition, Classification systems
The unmanned aerial vehicle (UAV) is an emerging technology applied recently in land cover classification, owing to its ability to acquire very high-resolution spatial data, that has provided an effective means for detailed land cover mapping, especially for a small island area. Selecting suitable UAV-acquired data and exploring the combined use of UAV multitype data are of significance for island mapping. Nine classification models were established through a fusion method of visible, multispectral, and light detection and ranging (LIDAR) data acquired by UAVs. A two-level hierarchical land cover classification (level 1 and level 2) of the Donkey Island in China was performed using geographic object-based image analysis with random forest classifier. We investigated the performance of land cover classification models containing different sets of features (spectral, height, intensity, and shape features extracted from UAV data) and evaluated the importance of various features. The results demonstrate that the overall accuracy (OA) of the models generally increase with decreasing detail and the amount of information entering the classification process. The OA achieved range from 82.08% to 92.54% and 74.12% to 85.08% across the nine models for level 1 and level 2, respectively. The best result was achieved with a model combining all features based on multispectral and LIDAR data. Height and intensity information input significantly affect the quality of classification models positively, with height apparently more significant than LIDAR information. When comparing different features, spectral features prominently assist in discriminating land cover classes. The importance of height and intensity features to classification accuracy varies for the classification models, showing greater importance in models based on visible data.
Compare with the reflectance of land surface, ocean water is much less. And, the contribution of atmospheric molecules and aerosols plays an vital importance on the water-leaving reflectance inversion. In order to simplify the inversion process, we generate a look-up-table(LUT) that contains the observation geometry information, the aerosol optical depth(AOD), the exponent of Junge power law(V) and the other factors used to calculate the water-leaving reflectance. The AOD and V are determined using our previous iterative algorithm from dual near-infrared(NIR) and dual shortwave infrared( SWIR) channels, respectively. We compare the retrieved AOD and V with Aerosol Robotic Network(AERONET) measurement data to ensure the precision of aerosol information. The AERONET AOD at 550nm is 0.0876, and the inversed AOD from dual-NIR and dual-SWIR is 0.05-0.325 and 0.0373-0.98, respectively. For dual- NIR, there are 31.97% and 57.18% pixels with the AOD absolute relative error less than 10% and 20%, respectively. For dual-SWIR, there are 31.01% and 59.79%. Then, we use the retrieved aerosol information together with the observation geometry information to get the factors used to calculate the water-leaving reflectance through interpolation. Finally, we use the MODIS ocean color product to verify the water leaving reflectance calculated based on aerosol retrieved from NIR and SWIR, and the two calculated water-leaving reflectance are marked as ρNIR and ρSWIR. In the visible and near-infrared region, both of them are smaller than the product values. Despite the ρSWIR is larger than ρNIR, the overcorrection is much more serious in ρNIR.
Due to the geographical peculiarities of the sea islands, we often encounter the difficulty that some coastlines are hard to
reach or to identify. Thus a specific measurement method cannot be implemented effectively, which affects the
integrity and precision of island coastline surveying. In this paper, we use the digital elevation Model (DEM) by LIDAR
date. However, The elevations acquired by an Airborne LIDAR system are ellipsoid heights, which is different from the
National Vertical Datum 1985 in existing island coastline. For this reason, a regional quasi-geoid model is constructed
with the geometric method, using the EGM2008 gravity field model and GPS/Leveling data. We manage to transform
ellipsoid heights to normal heights from observations, and construct the DEM which is based on National Vertical
Datum 1985. Finally island coastlines are extracted from the reference DEM and the associated tidal model and
compared with that from GPS-RTK measurements.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.