Abstract
Hyperspectral (HS) data have found a wide range of applications in recent years. Researchers observed that more spectral information helps land cover classification performance in many cases. However, in some practical applications, HS data may not be available, due to cost, data storage, or bandwidth issues. Instead, users may only have RGB and near infrared (NIR) bands available for land cover classification. Sometimes, light detection and ranging (LiDAR) data may also be available to assist land cover classification. A natural research problem is to investigate how well land cover classification can be achieved under the aforementioned data constraints. In this paper, we investigate the performance of land cover classification while only using four bands (RGB+NIR) or five bands (RGB+NIR+LiDAR). A number of algorithms have been applied to a well-known dataset (2013 IEEE Geoscience and Remote Sensing Society Data Fusion Contest). One key observation is that some algorithms can achieve better land cover classification performance by using only four bands as compared to that of using all 144 bands in the original hyperspectral data with the help of synthetic bands generated by Extended Multi-attribute Profiles (EMAP). Moreover, LiDAR data do improve the land cover classification performance even further.
Highlights
Hyperspectral (HS) images have been used in many applications [1]
We applied nine algorithms, including three hyperspectral classification methods, Matched Signature Detection (MSD), Adaptive Subspace Detection (ASD), Reed-Xiaoli Detection (RXD), and their kernel versions, and Sparse Representation (SR), Joint SR (JSR), and Support Vector Machine (SVM) to the 2013 IEEE Geoscience and Remote Sensing Society (GRSS) Data Fusion Contest dataset [23] for land cover classification
The results clearly demonstrated that our proposed approach achieved land cover classification results that were very close to the state-of-the-art methods in the literature by using only RGB, near infrared (NIR), and light detection and ranging (LiDAR) with Extended Multi-attribute Profiles (EMAP)
Summary
Hyperspectral (HS) images have been used in many applications [1]. Examples of HS sensors include Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) [2] and Adaptive Infrared Imaging Spectroradiometer (AIRIS) [3]. We focus on addressing the above practical problem in land cover classification, where only a few bands, namely RGB and near infrared (NIR) bands, are available. We applied nine algorithms, including three hyperspectral classification methods, Matched Signature Detection (MSD), Adaptive Subspace Detection (ASD), Reed-Xiaoli Detection (RXD), and their kernel versions, and Sparse Representation (SR), Joint SR (JSR), and Support Vector Machine (SVM) to the 2013 IEEE GRSS Data Fusion Contest dataset [23] for land cover classification. The results clearly demonstrated that our proposed approach achieved land cover classification results that were very close to the state-of-the-art methods in the literature by using only RGB, NIR, and LiDAR with EMAP. We will conclude our paper with a few remarks
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
