Abstract
Land-cover classification on very high resolution data (decimetre-level) is a well-studied yet challenging problem in remote sensing data processing. Most of the existing works focus on using images with orthographic view or orthophotos with the associated digital surface models (DSMs). However, the use of the nowadays widely-available oblique images to support such a task is not sufficiently investigated. In the effort of identifying different land-cover classes, it is intuitive that information of side-views obtained from the oblique can be of great help, yet how this can be technically achieved is challenging due to the complex geometric association between the side and top views. We aim to address these challenges in this paper by proposing a framework with enhanced classification results, leveraging the use of orthophoto, digital surface models and oblique images. The proposed method contains a classic two-step of (1) feature extraction and (2) a classification approach, in which the key contribution is a feature extraction algorithm that performs simplified geometric association between top-view segments (from orthophoto) and side-view planes (from projected oblique images), and joint statistical feature extraction. Our experiment on five test sites showed that the side-view information could steadily improve the classification accuracy with both kinds of training samples (1.1% and 5.6% for evenly distributed and non-evenly distributed samples, separately). Additionally, by testing the classifier at a large and untrained site, adding side-view information showed a total of 26.2% accuracy improvement of the above-ground objects, which demonstrates the strong generalization ability of the side-view features.
Highlights
Land-cover classification of high resolution data is an intensively investigated area of research in remote sensing [1,2,3]
Since different objects have different reflection characteristics corresponding to different spectral bands, many indexes have proposed as classification clues, such as normalized difference vegetation index (NDVI) [7], normalized difference water index (NDWI) [8] and normalized differenced snow index (NDSI_snow) [9]
As mentioned, the above-ground objects segmentation which decides the boundaries of each object and the corresponding textures is critical for the side-view information extraction
Summary
Land-cover classification of high resolution data is an intensively investigated area of research in remote sensing [1,2,3]. Since different objects have different reflection characteristics corresponding to different spectral bands, many indexes have proposed as classification clues, such as normalized difference vegetation index (NDVI) [7], normalized difference water index (NDWI) [8] and normalized differenced snow index (NDSI_snow) [9]. Based on these indexes, there are many variations, including near surface moisture index (NSMI), which models the relative surface snow moisture [10], and normalized difference soil index (NDSI_soil) [11]. The segment-level classification can reduce the local distributed spectral variation, generalize the spectral information and offer useful shape-related spatial descriptions [20]
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.
