Fusion of Hyperspectral and LiDAR Remote Sensing Data Using Multiple Feature Learning

Abstract

Hyperspectral image classification has been an active topic of research. In recent years, it has been found that light detection and ranging (LiDAR) data provide a source of complementary information that can greatly assist in the classification of hyperspectral data, in particular when it is difficult to separate complex classes. This is because, in addition to the spatial and the spectral information provided by hyperspectral data, LiDAR can provide very valuable information about the height of the surveyed area that can help with the discrimination of classes and their separability. In the past, several efforts have been investigated for fusion of hyperspectral and LiDAR data, with some efforts driven by the morphological information that can be derived from both data sources. However, a main challenge for the learning approaches is how to exploit the information coming from multiple features. Specifically, it has been found that simple concatenation or stacking of features such as morphological attribute profiles (APs) may contain redundant information. In addition, a significant increase in the number of features may lead to very high-dimensional input features. This is in contrast with the limited number of training samples often available in remote-sensing applications, which may lead to the Hughes effect. In this work, we develop a new efficient strategy for fusion and classification of hyperspectral and LiDAR data. Our approach has been designed to integrate multiple types of features extracted from these data. An important characteristic of the presented approach is that it does not require any regularization parameters, so that different types of features can be efficiently exploited and integrated in a collaborative and flexible way. Our experimental results, conducted using a hyperspectral image and a LiDAR-derived digital surface model (DSM) collected over the University of Houston campus and the neighboring urban area, indicate that the proposed framework for multiple feature learning provides state-of-the-art classification results.Index Terms-Digital surface model (DSM), hyperspectral, light detection and ranging (LiDAR), multiple feature learning.

High-Resolution Remote Sensing Data Classification over Urban Areas Using Random Forest Ensemble and Fully Connected Conditional Random Field

“…where i S and j S are the 3 most important features selected by RFE model and all other parameters are the same as the parameters defined in Equation (11). To minimize this energy function, we use a mean-field approximate inference algorithm [60] to refine the configuration of the labels.…”

“…To exploit the complementary characteristics of multisource data, data fusion based methods are also popular and have been proven to be more reliable than the single-source data methods used by many researchers [8]. For example, both images and 3D geometry data have been used in several previous studies [9][10][11][12].…”

Optimal Band Configuration for the Roof Surface Characterization Using Hyperspectral and LiDAR Imaging

“…A significant increase in the number of features of the urban area increases the complexity of classification; therefore, it demands the platforms which has diverse sensor technologies [23,24]. Moreover, it is obvious that no single technology is competent for reliable image interpretation [25].…”

Random-Forest-Ensemble-Based Classification of High-Resolution Remote Sensing Images and NDSM Over Urban Areas

“…To exploit the complementary characteristics of multi-source data, data fusion based methods are also popular and have been proved to be more reliable than the single-source data based ones by many researchers (Zhang and Lin, 2016). For example, both images and 3D geometry data were used in (Rau et al, 2015;Gerke and Xiao, 2014;Khodadadzadeh et al, 2015;Zhang et al, 2015). According to the basic element employed in classification process, the existing methods can be categorized into segmentation-based ones and segmentation-free-based ones.…”