Search

Change detection (CD) is a challenging task considering land surface cover changes. Recently, deep learning has been introduced into CD. However, these methods suffer from shortcomings such as insufficient utilization of shallow features and inadequate aggregation of semantic context, which result in pseudo changes and poor integrity of change objects. To address this, an enhanced shallow feature difference and semantic context network (ESDSCNet) is proposed in this study for remote sensing CD. It uses HRNet to extract multi-scale features from bi-temporal images to obtain shallow and deep features. To fully exploit the shallow features, they are input into the difference statistical texture learning (DSTL) module to extract more discriminative features. Subsequently, the features enhanced by DSTL are fed into the change object contextual representation (COCR) module along with the deep difference features extracted by HRNet to characterize the contextual information of the change object. To verify the performance of ESDSCNet in different scenes, this paper takes building change detection as a case and conducts experiments based on three datasets. The experimental results reveal that ESDSCNet outperforms six other advanced methods, regardless of the intersection over union or the harmonic mean of precision rate and recall rate, which further confirms the effectiveness of the proposed network. In addition, another speciality of this paper is that ESDSCNet can identify not only 'Where has changed' but also 'What has changed what', so it has potential application in semantic change detection besides building change detection. [ABSTRACT FROM AUTHOR]

Background: Chondroblastoma is a primary bone tumor typically arising from the intramedullary space of the epiphysis or epimetaphysis. A non-epiphyseal chondroblastoma is uncommon. Case report: An 11-year-old girl presented with an eccentric cortical osteolytic lesion in the distal femur metaphysis. The typical morphology, diffuse H3.3 K36M immunohistochemical expression and H3F3B point mutation (c. 110A > T) unequivocally supported the diagnosis of chondroblastoma. Discussion: We described a non-epiphyseal cortical-based chondroblastoma involving the distal femur harboring the typical H3F3B mutation. Non-epiphyseal chondroblastoma may harbor the H3F3B mutation. [ABSTRACT FROM AUTHOR]

This survey aimed to describe the health-related quality of life (HRQoL) and to explore the relationship between chronic diseases and HRQoL among urban residents in Shanghai, China. A cross-sectional study of 9 426 adults was conducted in Xuhui District of Shanghai, China in 2015. The EuroQol five-dimension three-level (EQ-5D-3 L) was used to measure HRQoL. The average age of subjects was 55.6 ± 17.4 years and 53% were female. Their mean values of utility and visual analogue scale (VAS) were 0.974 ± 0.099 and 80.00 ± 12.36, respectively, which were above the Chinese norm values. Women had lower scores compared with men. The utility value decreased with age, which accelerated after the age of 55 years. Chronic conditions including diabetes, tumor, cardiovascular disease, and respiratory disease, were significantly related to HRQoL, and the reported proportions of problems in the five dimensions increased with the number of chronic diseases (p < 0.05). Chronic diseases except for respiratory disease had a negative effect on HRQoL utility value and VAS score after the adjustment for covariates (p < 0.05). Chronic diseases had a negative impact on both EQ-5D-3 L utility and VAS scores, although the health-related quality of life for the study was above the national average. [ABSTRACT FROM AUTHOR]

Remote sensing mapping is an important research direction in the development of geographic surveying and mapping. In order to successfully implement the project of Mapping Western China (MWC), a technical mapping system has been established. In this project, many problems have been solved through technological innovation, such as block adjustment with scarce control points, large-scale aerial/satellite image mapping, and intelligent interpretation of multi-source images. Several softwares were developed, e.g. PixelGrid for aerial/satellite image mapping in a large area, FeatureStation for the integration of multi-source data in the complex terrain areas, and an airborne multi-band and multi-polarization interferometric data acquisition system for SAR mapping. For the first time, full coverage of 1: 50,000 topographic data of China's land territory has been produced, which means the geospatial framework of digital China is basically completed. With the implementation of other key national plans and projects (i.e. national geographic conditions monitoring and national remote sensing mapping), the focus has changed from MWC to national dynamic mapping. Accordingly, a dynamic mapping system is established. The data acquisition capability has developed from a single source to multiple sources and multiple modalities. The mapping capability has developed into dynamic mapping, and the capability for database update shows the characteristics of collaboration. The national geographic condition monitoring creates a multi-scale index system for statistical analysis for various needs. A multi-level and multi-dimensional technical system for statistical computing and decision-making service is developed for the transformation from dynamic monitoring to information service. In this paper, we give a brief introduction about the recent development of remote sensing mapping in China with respect to data acquisition, map production, and information service. The purpose of this paper is to motivate the establishment of theory and method for remote sensing mapping, technical and equipment in the smart mapping era, to improve the capability of perceiving, analyzing, mining, and applying geographic data, and to promote the intelligent development of geographic surveying and mapping. [ABSTRACT FROM AUTHOR]

This paper presents a new object-oriented land cover classification method that integrates raster analysis and vector analysis. The method adopts an improved colour structure code (CSC) for segmentation and support vector machine (SVM) for classification using high resolution (HR) QuickBird data. It combines the advantages of digital image processing (efficient improved CSC segmentation), geographical information systems (GIS) (vector-based feature selection), and data mining (intelligent SVM classification) to interpret images from pixels to objects and thematic information. The improved CSC segmentation not only achieves robust and accurate results but also combines boundary information that the traditional CSC algorithm does not consider. The SVM used for classification has the advantages of solving sparse sampling, nonlinear, high-dimensional and global optimum problems, compared with other classifiers. The results demonstrate that the new object-oriented classification method significantly outperforms some other objected-oriented classification methods such as the objected-oriented method based on traditional CSC and SVM, and perfect classification results are obtained from the classification processing, including not only the classification method, but also preprocessing, sample selection and post-processing. [ABSTRACT FROM AUTHOR]