Integrating remote sensing and geospatial big data for urban land use mapping: A review

Remote Sensing (RS) has been used in urban mapping for a long time; however, the complexity and diversity of functional patterns are difficult to be captured by RS only. Emerging Geospatial Big Data (GBD) considered as supplement data, help contribute our understanding lands from physical aspects (i.e., land cover) socioeconomic use). Integrating GBD could an effective way combine with great potential high-quality use classification. In this study, we reviewed existing literature focused on state-of-the-art perspective categorization integrating GBD. Specifically, commonly features (e.g., spectral, textural, temporal, spatial features) spatial, semantic, sequence were identified analyzed The integration strategies categorized into feature-level (FI) decision-level (DI). To more specific, FI method integrates classifies types using integrated feature sets; DI processes independently then merges classification results based decision rules. We also discussed other critical issues, including analysis unit setting, parcel segmentation, labeling types, data integration. Our findings provide retrospect different GBD, integration, their pros cons, which define framework future better support planning, environment assessment, disaster monitoring traffic analysis.