Abstract
The high interior heterogeneity of land surface covers in high-resolution image of coastal cities makes classification challenging. To meet this challenge, a Multi-Scale Superpixels-based Classification method using Optimized Spectral–Spatial features, denoted as OSS-MSSC, is proposed in this paper. In the proposed method, the multi-scale superpixels are firstly generated to capture the local spatial structures of the ground objects with various sizes. Then, the normalized difference vegetation index and extend multi-attribute profiles are introduced to extract the spectral–spatial features from the multi-spectral bands of the image. To reduce the redundancy of the spectral–spatial features, the crossover-based search algorithm is utilized for feature optimization. The pre-classification results at each single scale are, therefore, obtained based on the optimized spectral–spatial features and random forest classifier. Finally, the ultimate classification is generated via the majority voting of those pre-classification results in each scale. Experimental results on the Gaofen-2 image of Qingdao and WorldView-2 image of Hong Kong, China confirmed the effectiveness of the proposed method. The experiments verify that the OSS-MSSC method not only works effectively on the homogeneous regions, but also is able to preserve the small local spatial structures in the high-resolution remote sensing images of coastal cities.
Highlights
The term “coastal cities” usually refers to cities located within 100 km from the shoreline where many physical, natural, social and economic elements intersect [1,2]
The Gaofen-2 data contained 4 multispectral bands spanning from visible to Near Infrared (NIR) spectral region, i.e., 3 visible spectral bands, 1 NIR band (770~890 nm defined as B4) with a spatial resolution of 4 m, and 1 panchromatic band (450–900 nm) with a resolution of 1 m
The Extended Multi-Attribute Profiles (EMAPs) are extracted to provide multilevel spatial description of the various land surface covers in a coastal city, and thereby decrease the inter-class variability and improve their intra-class variability
Summary
The term “coastal cities” usually refers to cities located within 100 km from the shoreline where many physical, natural, social and economic elements intersect [1,2]. The related mapping techniques have evolved from the pixel-based approaches to superpixels-based methods [7,8,9,10,11,12,13] This is mainly due to the complex structure of diverse urban land covers which make the pixel-based classification methods hardly applicable for high-resolution remote sensing images. In [15], to improve the classification accuracy, both supervised and unsupervised Fractal Net Evolution Approach (FNEA, has been embedded in the commercial software eCognition) were developed for extracting buildings from very high-resolution imagery These methods can firstly segment the high-resolution image into a number of homogeneous regions to reduce the interior heterogeneity of different kinds of land surface covers. The efficiency of the superpixel-based methods have been verified in the classification of highly built-up urban areas with abundant fine spatial details [16,17,18]
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.
