Decision Fusion Based on Hyperspectral and Multispectral Satellite Imagery for Accurate Forest Species Mapping

Abstract

This study investigates the effectiveness of combining multispectral very high resolution (VHR) and hyperspectral satellite imagery through a decision fusion approach, for accurate forest species mapping. Initially, two fuzzy classifications are conducted, one for each satellite image, using a fuzzy output support vector machine (SVM). The classification result from the hyperspectral image is then resampled to the multispectral's spatial resolution and the two sources are combined using a simple yet efficient fusion operator. Thus, the complementary information provided from the two sources is effectively exploited, without having to resort to computationally demanding and time-consuming typical data fusion or vector stacking approaches. The effectiveness of the proposed methodology is validated in a complex Mediterranean forest landscape, comprising spectrally similar and spatially intermingled species. The decision fusion scheme resulted in an accuracy increase of 8% compared to the classification using only the multispectral imagery, whereas the increase was even higher compared to the classification using only the hyperspectral satellite image. Perhaps most importantly, its accuracy was significantly higher than alternative multisource fusion approaches, although the latter are characterized by much higher computation, storage, and time requirements.

Determining Subcanopy Psidium cattleianum Invasion in Hawaiian Forests Using Imaging Spectroscopy

“…BSVM and other variants of the support vector machine are flexible and distribution-free modeling approaches, which are based on the principles of structural risk minimization theory, i.e., a machine learning procedure that balances model complexity and efficiency based on the success of fitting the training data [54]. BSVM is a partially supervised and non-parametric classification method that researchers have recently increased its use in for remote sensing applications [31,33,55]. Our results suggest BSVM as a promising method to disentangle spectrally-mixed classifications, as this approach generates decision values from a similarity function (kernel), which optimize complex comparisons between classes in a dynamic machine learning process.…”

“…2016, 8,33 11 of 17 range. However, classifier outputs from both methods displayed a gradual increase in spectral similarity with the P. cattleianum endmembers as the threshold increased, which indicate that both methods are similar, but not identical, in measuring the level of spectral correspondence between target pixels and endmembers.…”

“…Although the BSVM algorithms create binary Boolean classes (i.e., a given pixel may belong or not to the focal class), they compute decision values from support vectors, indicating the degree of similarity between classes [32]. These decision values have rarely been explored for their potential use in focal species mapping with remote sensing (however, see [33]). The ability of BSVM to perform complex comparisons between classes in a dynamic machine learning process may be useful in quantifying the spectral separability of classes.…”

Remote Sensing and Reflectance Profiling in Entomology

“…one object), and that will likely compromise classification accuracies. Imaging software engineers have developed numerous approaches to fragment pixels (1,55) and to artificially increase the spatial resolution of one imaging source through the use of a second type of imagery as part of a process called image fusion (35,128). Despite these classification solutions, it is generally recommended that the spatial resolution be high enough to avoid mixed pixels and then averaged as part of spatial binning (reducing the spatial and spectral resolutions of hyperspectral imaging data) of input data (42,65,158).…”

Incorporating Diversity into Self-Learning for Synergetic Classification of Hyperspectral and Panchromatic Images

“…Unlike conventional multisource classification techniques based on the feature level or decision level [24], SL can be considered as a new framework of synergetic processing for HS and high-resolution PAN images. It consists of two prevalent techniques, namely high-resolution image segmentation and active learning.…”