The fully convolutional network (FCN) with an encoder-decoder architecture has been the standard paradigm for semantic segmentation. The encoder-decoder architecture utilizes an encoder to capture multilevel feature maps, which are incorporated into the final prediction by a decoder. As the context is crucial for precise segmentation, tremendous effort has been made to extract such information in an intelligent fashion, including employing dilated/atrous convolutions or inserting attention modules. However, these endeavors are all based on the FCN architecture with ResNet or other backbones, which cannot fully exploit the context from the theoretical concept. By contrast, we introduce the Swin Transformer as the backbone to extract the context information and design a novel decoder of densely connected feature aggregation module (DCFAM) to restore the resolution and produce the segmentation map. The experimental results on two remotely sensed semantic segmentation datasets demonstrate the effectiveness of the proposed scheme.

As an important carrier of human productive activities, the extraction of buildings is not only essential for urban dynamic monitoring but also necessary for suburban construction inspection. Nowadays, accurate building extraction from remote sensing images remains a challenge due to the complex background and diverse appearances of buildings. The convolutional neural network (CNN)-based building extraction methods, although increased the accuracy significantly, are criticized for their inability for modeling global dependencies. Thus, this article applies the vision transformer (ViT) for building extraction. However, the actual utilization of the ViT often comes with two limitations. First, the ViT requires more GPU memory and computational costs compared with CNNs. This limitation is further magnified when encountering large-sized inputs like fine-resolution remote sensing images. Second, spatial details are not sufficiently preserved during the feature extraction of the ViT, resulting in the inability for fine-grained building segmentation. To handle these issues, we propose a novel ViT (BuildFormer), with a dual-path structure. Specifically, we design a spatial-detailed context path to encode rich spatial details and a global context path to capture global dependencies. Besides, we design a window-based linear multihead self-attention whose complexity is linear with the window size. Such a design allows the BuildFormer to apply large windows for capturing global context, which greatly improves its potential in processing large-sized remote sensing images. The proposed method yields the state-of-the-art performance (75.74% IoU) on the Massachusetts building dataset. Code will be available at https://github.com/WangLibo1995/BuildFormer .

The accurate assessment of rice yield is crucially important for China’s food security and sustainable development. Remote sensing (RS), as an emerging technology, is expected to be useful for rice yield estimation especially at regional scales. With the development of unmanned aerial vehicles (UAVs), a novel approach for RS has been provided, and it is possible to acquire high spatio-temporal resolution imagery on a regional scale. Previous reports have shown that the predictive ability of vegetation index (VI) decreased under the influence of panicle emergence during the later stages of rice growth. In this study, a new approach which integrated UAV-based VI and abundance information obtained from spectral mixture analysis (SMA) was established to improve the estimation accuracy of rice yield at heading stage. The six-band image of all studied rice plots was collected by a camera system mounted on an UAV at booting stage and heading stage respectively. And the corresponding ground measured data was also acquired at the same time. The relationship of several widely-used VIs and Rice Yield was tested at these two stages and a relatively weaker correlation between VI and yield was found at heading stage. In order to improve the estimation accuracy of rice yield at heading stage, the plot-level abundance of panicle, leaf and soil, indicating the fraction of different components within the plot, was derived from SMA on the six-band image and in situ endmember spectra collected for different components. The results showed that VI incorporated with abundance information exhibited a better predictive ability for yield than VI alone. And the product of VI and the difference of leaf abundance and panicle abundance was the most accurate index to reliably estimate yield for rice under different nitrogen treatments at heading stage with the coefficient of determination reaching 0.6 and estimation error below 10%.

Background: The accurate estimation of rice LAI is particularly important to monitor rice growth status. Remote sensing, as a non-destructive measurement technology, has been proved to be useful for estimating vegetation growth parameters, especially at large scale. With the development of unmanned aerial vehicles (UAVs), this novel remote sensing platform has been widely used to provide remote sensing images which have much higher spatial resolution. Previous reports have shown that the spectral feature of remote sensing images could be an effective indicator to estimate vegetation growth parameters. However, the texture feature of high-resolution remote sensing images is rarely employed for this purpose. Besides, the physical mechanism between the texture feature and vegetation growth parameters is still unclear. Results: In this study, a Fourier spectrum texture based on the UAV Image was developed to estimate rice LAI. And the relationship between Fourier spectrum texture and rice LAI was also analyzed. The results showed that Fourier spectrum texture could improve the accuracy of rice LAI estimation. Conclusions: In conclusion, the texture feature of high-resolution remote sensing images may be more effective in rice LAI estimation than the spectral feature.

Monitoring fine particulate matter with diameters of less than 2.5 μm (PM2.5) is a critical endeavor in the Beijing–Tianjin–Hebei (BTH) region, which is one of the most polluted areas in China. Polar orbit satellites are limited by observation frequency, which is insufficient for understanding PM2.5 evolution. As a geostationary satellite, Himawari-8 can obtain hourly optical depths (AODs) and overcome the estimated PM2.5 concentrations with low time resolution. In this study, the evaluation of Himawari-8 AODs by comparing with Aerosol Robotic Network (AERONET) measurements showed Himawari-8 retrievals (Level 3) with a mild underestimate of about −0.06 and approximately 57% of AODs falling within the expected error established by the Moderate-resolution Imaging Spectroradiometer (MODIS) (±(0.05 + 0.15AOD)). Furthermore, the improved linear mixed-effect model was proposed to derive the surface hourly PM2.5 from Himawari-8 AODs from July 2015 to March 2017. The estimated hourly PM2.5 concentrations agreed well with the surface PM2.5 measurements with high R² (0.86) and low RMSE (24.5 μg/m³). The average estimated PM2.5 in the BTH region during the study time range was about 55 μg/m³. The estimated hourly PM2.5 concentrations ranged extensively from 35.2 ± 26.9 μg/m³ (1600 local time) to 65.5 ± 54.6 μg/m³ (1100 local time) at different hours.