Automatically extracting 2D buildings from high-resolution remote sensing images is among the most popular research directions in the area of remote sensing information extraction. Semantic segmentation based on a CNN or transformer has greatly improved building extraction accuracy. A CNN is good at local feature extraction, but its ability to acquire global features is poor, which can lead to incorrect and missed detection of buildings. The advantage of transformer models lies in their global receptive field, but they do not perform well in extracting local features, resulting in poor local detail for building extraction. We propose a CNN-based and transformer-based dual-stream feature extraction network (DSFENet) in this paper, for accurate building extraction. In the encoder, convolution extracts the local features for buildings, and the transformer realizes the global representation of the buildings. The effective combination of local and global features greatly enhances the network’s feature extraction ability. We validated the capability of DSFENet on the Google Image dataset and the ISPRS Vaihingen dataset. DSEFNet achieved the best accuracy performance compared to other state-of-the-art models.

Accurate, timely, and reliable farmland mapping is a prerequisite for agricultural management and environmental assessment in mountainous areas. However, in these areas, high spatial heterogeneity and diversified planting structures together generate various small farmland parcels with irregular shapes that are difficult to accurately delineate. In addition, the absence of optical data caused by the cloudy and rainy climate impedes the use of time-series optical data to distinguish farmland from other land use types. Automatic delineation of farmland parcels in mountain areas is still a very difficult task. This paper proposes an innovative precise farmland parcel extraction approach supported by very high resolution(VHR) optical image and time series synthetic aperture radar(SAR) data. Firstly, Google satellite imagery with a spatial resolution of 0.55 m was used for delineating the boundaries of ground parcel objects in mountainous areas by a hierarchical extraction scheme. This scheme divides farmland into four types based on the morphological features presented in optical imagery, and designs different extraction models to produce each farmland type, respectively. The potential farmland parcel distribution map is then obtained by the layered recombination of these four farmland types. Subsequently, the time profile of each parcel in this map was constructed by five radar variables from the Sentinel-1A dataset, and the time-series classification method was used to distinguish farmland parcels from other types. An experiment was carried out in the north of Guiyang City, Guizhou Province, Southwest China. The result shows that, the producer’s accuracy of farmland parcels obtained by the hierarchical scheme is increased by 7.39% to 96.38% compared with that without this scheme, and the time-series classification method produces an accuracy of 80.83% to further obtain the final overall accuracy of 96.05% for the farmland parcel maps, showing a good performance. In addition, through visual inspection, this method has a better suppression effect on background noise in mountainous areas, and the extracted farmland parcels are closer to the actual distribution of the ground farmland.

High-quality road network information plays a vital role in regional economic development, disaster emergency management and land planning. To date, studies have primarily focused on sampling flat urban roads, while fewer have paid attention to road extraction in mountainous regions. Compared with road extraction in flat regions, road extraction in mountainous regions suffers more interference, due to shadows caused by mountains and road-like terrain. Furthermore, there are more practical problems involved when researching an entire region rather than at the sample level. To address the difficulties outlined regarding mountain road extraction, this paper takes Jiuzhaigou county in China as an example and studies road extraction in practical applications. Based on deep learning methods, we used a multistage optimization method to improve the extraction effect. First, we used the contrast limited adaptive histogram equalization (CLAHE) algorithm to attenuate the influence of mountain shadows and improve the quality of the image. Then the road was extracted by the improved DSDNet network. Finally, the terrain constraint method is used to reduce the false detection problem caused by the terrain factor, and after that the final road extraction result is obtained. To evaluate the effect of road extraction comprehensively, we used multiple data sources (i.e., points, raster and OpenStreetMap data) in different evaluation schemes to verify the accuracy of the road extraction results. The accuracy of our method for the three schemes was 0.8631, 0.8558 and 0.8801, which is higher than other methods have obtained. The results show that our method can effectively solve the interference of shadow and terrain encountered in road extraction over mountainous regions, significantly improving the effect of road extraction.

In order to comprehensively and accurately evaluate the adsorption effect of Eichhornia crassipes planting on algae in water, this study used 131 cloudless Sentinel-2 images to monitor the scale and growth dynamics of Eichhornia crassipes planting in Caohai and its surrounding waters. Based on the single and multi-peak histogram characteristics of the NDWI image in the study area, the empirical threshold and the optimized histogram slope adaptive threshold (OHSAT) segmentation methods were respectively used and manual inspection was added to accurately segment the water bodies and Eichhornia crassipes. The results of the analysis of Eichhornia crassipes area, growth status (NDVI), water body algae density (NDVI), and their spatial–temporal co-variation and trends show that the Eichhornia crassipes has a significant enrichment effect on algae, showing a significant decreasing trend of water bloom centered on it. The size and growth status of Eichhornia crassipes are inversely proportional to the water body NDVI, and reasonable harvesting plans based on these findings are expected to achieve optimized pollution control effects.

The unique structure of ancient buildings poses a significant risk of fire hazards, so the assessment of potential fire risk is of great significance to fire safety management. This paper examines the fire risk associated with the building complex of the Palace Museum. Firstly, a fire risk assessment indicator system was constructed based on three dimensions: hazard factors, sensitivity of hazard-bearing bodies, and loss control factors. Secondly, the weight values for each index were calculated based on the entropy weight method. Finally, the monthly fire risk assessment levels in the year 2019 were visualized by using a geographic information system. Based on the fire risk assessment results, this study quantitatively reveals the fire risk driving mechanism of ancient buildings in the Palace Museum from the perspective of spatial stratified heterogeneity by using the geodetector model. The results show that there are differences between the main factors that affect the weight of fire risk assessment and the main factors that cause the spatial heterogeneity of fire risk. Factors such as the safety protective grade and staff number contribute to a stronger explanation of the spatial stratified heterogeneity for fire risk within the museum. The results can help us to understand the driving factors affecting the distribution patterns of fire risk for the Palace Museum and could provide support for the formulation of fire prevention and safety management measures.

Fine-grained classification of urban green spaces (UGSs) is important for urban ecological assessment and management but remains challenging because of spectral similarity among vegetation types and inaccurate object delineation in complex urban environments. This study proposes a pixel-to-object framework that combines semantic segmentation-guided object construction with multi-periodic phenological modeling. A semantic green-space mask derived from 0.27 m very-high-resolution imagery constrains superpixel segmentation to generate spatially coherent, boundary-aware green space object-level patches (GSOPs). Pixel-level temporal representations are then derived from Sentinel-2 normalized difference vegetation index (NDVI) time series using TimesNet, aggregated into GSOP-level phenological features, and combined with spatial attributes to classify urban trees, grasslands, and farmlands. Applied to the built-up area of Chengdu, China, the framework achieved an overall accuracy of 91.6%, with F1-scores of 92.5%, 91.9%, and 87.6% for urban trees, grasslands, and farmlands, respectively. Ablation experiments showed that removing phenological features reduced overall accuracy by 13.1 percentage points and decreased the F1-scores of grasslands and farmlands by 16.0 and 23.0 percentage points, respectively. These results demonstrate that semantically constrained object delineation and phenological information jointly reduce boundary fragmentation and improve the discrimination of spectrally similar urban vegetation types.