Impervious Surface Extraction Based on Improved Support Vector Data Description
Yuwen Fei
DOI: https://doi.org/10.59429/pest.v5i1.1747
Keywords: Impervious Surface; Support Vector Data Description; Multiresolution Segmentation; Remote Sensing Images
Abstract
The continuous expansion of urban impervious surfaces has brought negative impacts on the urban environment. In order to quickly extract urban impervious surfaces to monitor urban development, this paper proposes a multiresolution segmentation-based impervious surface extraction method. The method is an improvement on the deep support vector data description method. The study is carried out to validate the method using some areas of Shenzhen as the experimental area. The experimental results show that the improved DSVDD method has enhanced all accuracy indicators, while its landscape pattern index reflects that the improved model has less fragmentation.
References
Wu C, Murray A T. Estimating impervious surface distribution by spectral mixture analysis[J]. Remote Sensing of Environment, 2003, 84(4): 493-505.
Miao Z, Xiao Y, Shi W, et al. Integration of satellite images and open data for impervious surface classification[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2019, 12(4): 1120–1133.
Wan Y, Fei Y, Wu T, et al. A novel impervious surface extraction method integrating poi, vehicle trajectories, and satellite imagery[J]. Ieee Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2021, 14: 8804–8814.
eCognition Developer. eCognition Developer 9.0:Reference Book [M]. Munich, Germany: Trimble Germany GmbH,2014:35-40.
Chen C, Wu S, Meurk C, et al. Identifying and Evaluating Functional Connectivity for Building Urban Ecological Networks[J]. Acta Ecologica Sinica, 2015, 35(22):7367-7376.