Fine classification of vegetation types has always been the focus and difficulty in the application field of remote sensing. Unmanned Aerial Vehicle (UAV) sensors and platforms have become important data sources in various application fields due to their high spatial resolution and flexibility. Especially, UAV hyperspectral images can play a significant role in the fine classification of vegetation types. However, it is not clear how the ultrahigh resolution UAV hyperspectral images react in the fine classification of vegetation types in highly fragmented planting areas, and how the spatial resolution variation of UAV images will affect the classification accuracy. Based on UAV hyperspectral images obtained from a commercial hyperspectral imaging sensor (S185) onboard a UAV platform, this paper examines the impact of spatial resolution on the classification of vegetation types in highly fragmented planting areas in southern China by aggregating 0.025 m hyperspectral image to relatively coarse spatial resolutions (0.05, 0.1, 0.25, 0.5, 1, 2.5 m). The object-based image analysis (OBIA) method was used and the effects of several segmentation scale parameters and different number of features were discussed. Finally, the classification accuracies from 84.3% to 91.3% were obtained successfully for multi-scale images. The results show that with the decrease of spatial resolution, the classification accuracies show a stable and slight fluctuation and then gradually decrease since the 0.5 m spatial resolution. The best classification accuracy does not occur in the original image, but at an intermediate level of resolution. The study also proves that the appropriate feature parameters vary at different scales. With the decrease of spatial resolution, the importance of vegetation index features has increased, and that of textural features shows an opposite trend; the appropriate segmentation scale has gradually decreased, and the appropriate number of features is 30 to 40. Therefore, it is of vital importance to select appropriate feature parameters for images in different scales so as to ensure the accuracy of classification.

The use of remote sensing images for land cover classification is an important and challenging pixel-level classification task. However, the different distribution of the same land cover categories across different datasets, the accuracy of the classification is significantly reduced when a classification model trained on one dataset is used directly on another dataset. To address the issue, numerous unsupervised domain adaptation (UDA) methods have been proposed. However, the existing UDA methods focus mainly on natural images and are not suited to remote sensing images with large variations in spectral information and texture features. Therefore, we develop a new full-level domain adaptation network (FLDA-NET) applicable for cross-domain land cover classification of remote sensing images. It aligns the source domain and target domain through a two-stage process encompassing image-level, feature-level and output-level. In stage I, we align at image-level by converting the source domain image to the target domain image style. In stage II, at the feature-level we align the entropy of the two domain features. At the output-level we do not use simple global alignment, but category-level alignment. Furthermore, a self-training strategy (SPST) based on superpixel segmentation and softmax probability is proposed to further enhance the model's performance on the target domain. Extensive experiments on our proposed FLDA-NET are performed on the Potsdam and Vaihingen datasets and compared to other advanced UDA methods. The outcome demonstrates that this approach greatly improves improve the ability of cross-domain land cover classification in remote sensing images.

The scope of this research lies in the combination of pre-trained Convolutional Neural Networks (CNNs) and Quantum Convolutional Neural Networks (QCNN) in application to Remote Sensing Image Scene Classification(RSISC). Deep learning (RL) is improving by leaps and bounds pretrained CNNs in Remote Sensing Image (RSI) analysis, and pre-trained CNNs have shown remarkable performance in remote sensing image scene classification (RSISC). Nonetheless, CNNs training require massive, annotated data as samples. When labeled samples are not sufficient, the most common solution is using pre-trained CNNs with a great deal of natural image datasets (e.g., ImageNet). However, these pre-trained CNNs require a large quantity of labelled data for training, which is often not feasible in RSISC, especially when the target RSIs have different imaging mechanisms from RGB natural images. In this paper, we proposed an improved hybrid classical–quantum transfer learning CNNs composed of classical and quantum elements to classify open-source RSI dataset. The classical part of the model is made up of a ResNet network which extracts useful features from RSI datasets. To further refine the network performance, a tensor quantum circuit is subsequently employed by tuning parameters on near-term quantum processors. We tested our models on the open-source RSI dataset. In our comparative study, we have concluded that the hybrid classical–quantum transferring CNN has achieved better performance than other pre-trained CNNs based RSISC methods with small training samples. Moreover, it has been proven that the proposed algorithm improves the classification accuracy while greatly decreasing the amount of model parameters and the sum of training data.

Actual evapotranspiration (ET) with high spatiotemporal resolution is very important for the research on agricultural water resource management and the water cycle processes, and it is helpful to realize precision agriculture and smart agriculture, and provides critical references for agricultural layout planning. Due to the impact of the clouds, weather environment, and the orbital period of optical satellite, there are difficulties in providing daily remote sensing data that are not contaminated by clouds for estimating daily ET with high spatial-temporal resolution. By improving the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM), this manuscript proposes the method to fuse high temporal and low spatial resolution Weather Research and Forecasting (WRF) model surface skin temperature (TSK) with the low temporal and high spatial resolution remote sensing surface temperature for obtaining high spatiotemporal resolution daily surface temperature to be used in the estimation of the high spatial resolution daily ET (ET_WRF_HR). The distinction of this study from the previous literatures can be summarized as the novel application of the fusion of WRF-simulated TSK and remote sensing surface temperature, giving full play to the availability of model surface skin temperature data at any time and region, making up for the shortcomings of the remote sensing data, and combining the high spatial resolution of remote sensing data to obtain ET with high spatial (Landsat-like scale) and temporal (daily) resolution. The ET_WRF_HR were cross-validated and quantitatively verified with MODIS ET products (MOD16) and observations (ET_Obs) from eddy covariance system. Results showed that ET_WRF_HR not only better reflects the difference and dynamic evolution process of ET for different land types but also better identifies the details of various fine geographical objects. It also represented a high correlation with the ET_Obs by the R² amount reaching 0.9186. Besides, the RMSE and BIAS between ET_WRF_HR and the ET_Obs are obtained as 0.77 mm/d and −0.08 mm/d respectively. High R², as well as the small RMSE and BIAS amounts, indicate that ET_WRF_HR has achieved a very good performance.

Cloud and cloud shadow detection in remote sensing images is an important preprocessing technique for quantitative analysis and large-scale mapping. To solve the problems of cloud and cloud shadow detection based on Convolutional Neural Network models, such as rough edges and insufficient overall accuracy, cloud and cloud shadow segmentation based on Swin-UNet was studied in the wide field of view (WFV) images of GaoFen-1 (GF-1). The Swin Transformer blocks help the model capture long-distance features and obtain deeper feature information in the network. This study selects a public GF1_WHU cloud and cloud shadow detection dataset for preprocessing and data optimization and conducts comparative experiments in different models. The results show that the algorithm performs well on vegetation, water, buildings, barren and other types. The average accuracy of cloud detection is 98.01%, the recall is 96.84% and the F1-score is 95.48%. The corresponding results of cloud shadow detection are 84.64%, 83.12% and 97.55%. In general, compared to U-Net, PSPNet and DeepLabV3+, this model performs better in cloud and cloud shadow detection, with clearer detection boundaries and a higher accuracy in complex surface conditions. This proves that Swin-UNet has great feature extraction capability in moderate and high-resolution remote sensing images.

As one of the most important active remote sensing technologies, synthetic aperture radar (SAR) provides advanced advantages of all-day, all-weather, and strong penetration capabilities. Due to its unique electromagnetic spectrum and imaging mechanism, the dimensions of remote sensing data have been considerably expanded. Important for fundamental research in microwave remote sensing, SAR image classification has been proven to have great value in many remote sensing applications. Many widely used SAR image classification algorithms rely on the combination of hand-designed features and machine learning classifiers, which still experience many issues that remain to be resolved and overcome, including optimized feature representation, the fuzzy confusion of speckle noise, the widespread applicability, and so on. To mitigate some of the issues and to improve the pattern recognition of high-resolution SAR images, a ConvCRF model combined with superpixel boundary constraint is developed. The proposed algorithm can successfully combine the local and global advantages of fully connected conditional random fields and deep models. An optimizing strategy using a superpixel boundary constraint in the inference iterations more efficiently preserves structure details. The experimental results demonstrate that the proposed method provides competitive advantages over other widely used models. In the land cover classification experiments using the MSTAR, E-SAR and GF-3 datasets, the overall accuracy of our proposed method achieves 90.18 ± 0.37, 91.63 ± 0.27, and 90.91 ± 0.31, respectively. Regarding the issues of SAR image classification, a novel integrated learning containing local and global image features can bring practical implications.