Semantic Network-Based Impervious Surface Extraction Method for Rural-Urban Fringe From High Spatial Resolution Remote Sensing Images

Abstract

Impervious surfaces, as a key indicator of urban spatial environmental factors, have great significance in exploring the distribution law and spatial pattern of rural-urban fringe areas. To handle the increasingly rich feature information and complicated urban spatial structure in high spatial resolution remote sensing images (HSRRSIs), a semantic network modelguided extraction method for HSRRSI impervious surfaces in rural-urban fringes is proposed. The proposed method mainly includes three parts: (1) Construction of a semantic network model of ground covers in the rural-urban fringe and dimensionality reduction of its features. (2) Optimization of a multi-scale segmentation algorithm based on the estimation of scale parameter 2 (ESP2) method and the fitness function. (3) Proposal of a feature reduction method based on the ReliefF feature selection algorithm for spectral, texture, and geometry features to reduce the data redundancy in HSRRSIs. Finally, with the Geoeye-1 image of the rural-urban fringe of Zhanggong District as the data source, CART, RF, and SVM classifiers are used to extract the impervious surfaces of two different areas (named as Q1 and Q2), Q1 comprises the edge of rural-urban fringe with densely distributed industrial plants, and Q2 comprises a rural-urban fringe with a pronounced transition from urban to rural areas. Results show that the highest impervious surface extraction accuracy of the SVM classifier based on the semantic network model is obtained when the segmentation scale is at 210 and 215. The producer accuracy and overall accuracy for Q1 and Q2 are (94.27%, 86.41%) and (94.46%, 89.47%), respectively.

Zero-Shot Remote Sensing Scene Classification Method Based on Local-Global Feature Fusion and Weight Mapping Loss

“…Therefore, the classification models trained on specific datasets are usually not transferable, and it is difficult to directly apply them to the classification of remote sensing scenes in different cities. 2) Modern urban remote sensing scenes are diverse and in continuous evolution [21], [22], while existing models can only classify the limited number of labeled scene categories provided in the training set. For other unlabeled or newly emerging scene categories, the models do not have classification capabilities, that is, the generalization ability and scalability of the models are poor.…”

Detecting Changes in Impervious Surfaces Using Multi-Sensor Satellite Imagery and Machine Learning Methodology in a Metropolitan Area

“…In recent years, the use of advanced machine learning techniques has significantly improved the detection of impervious surfaces from satellite imagery [26,27]. Techniques such as Classification and Regression Trees (CARTs) [28][29][30], the Random Forest (RF) method [31,32], Artificial Neural Networks (ANNs) [33][34][35][36], and Support Vector Machines (SVMs) [37][38][39][40] are examples of these methodologies. For instance [41], Lodato et al (2023) employed RF classification on Landsat imagery and, through remote sensing techniques and innovative cloud services, documented the transformation of the northern coastal region of Rome, an important rural area, into new residential and commercial services [42].…”