This paper presents a cross-learning network (i.e., CLCFormer) integrating fine-grained spatial details within long-range global contexts based upon convolutional neural network (CNN) and transformer, for semantic segmentation of very high-resolution (VHR) remote sensing images. More specifically, CLCFormer comprises two parallel encoders, derived from CNN and transformer, and a CNN decoder. The encoders are backboned on SwinV2 and EfficientNet-B3, from which the extracted semantic features are aggregated at multiple levels using a bilateral feature fusion module. Firstly, we used attention gate modules to enhance feature representation, improving segmentation results for objects with various shapes and sizes. Secondly, we used an attention residual module to refine spatial features’s learning, alleviating boundary blurring of occluded objects. Finally, we developed a new strategy, called auxiliary supervise strategy, for model optimization to further improve segmentation performance. Our method was tested on the WHU, Inria, and Potsdam datasets, and compared with CNN-based and transformer-based methods. Results showed that our method achieved state-of-the-art performance on the WHU building dataset (92.31%IoU), Inria building dataset (83.71%IoU), and Potsdam dataset (80.27%MIoU). We concluded that CLCFormer is a flexible, robust, and effective method for the semantic segmentation of VHR images. The codes of the proposed model are avaliable at https://github.com/long123524/CLCFormer.

Accurate and efficient extraction of cultivated land data is of great significance for agricultural resource monitoring and national food security. Deep-learning-based classification of remote-sensing images overcomes the two difficulties of traditional learning methods (e.g., support vector machine (SVM), K-nearest neighbors (KNN), and random forest (RF)) when extracting the cultivated land: (1) the limited performance when extracting the same land-cover type with the high intra-class spectral variation, such as cultivated land with both vegetation and non-vegetation cover, and (2) the limited generalization ability for handling a large dataset to apply the model to different locations. However, the “pooling” process in most deep convolutional networks, which attempts to enlarge the sensing field of the kernel by involving the upscale process, leads to significant detail loss in the output, including the edges, gradients, and image texture details. To solve this problem, in this study we proposed a new end-to-end extraction algorithm, a high-resolution U-Net (HRU-Net), to preserve the image details by improving the skip connection structure and the loss function of the original U-Net. The proposed HRU-Net was tested in Xinjiang Province, China to extract the cultivated land from Landsat Thematic Mapper (TM) images. The result showed that the HRU-Net achieved better performance (Acc: 92.81%; kappa: 0.81; F1-score: 0.90) than the U-Net++ (Acc: 91.74%; kappa: 0.79; F1-score: 0.89), the original U-Net (Acc: 89.83%; kappa: 0.74; F1-score: 0.86), and the Random Forest model (Acc: 76.13%; kappa: 0.48; F1-score: 0.69). The robustness of the proposed model for the intra-class spectral variation and the accuracy of the edge details were also compared, and this showed that the HRU-Net obtained more accurate edge details and had less influence from the intra-class spectral variation. The model proposed in this study can be further applied to other land cover types that have more spectral diversity and require more details of extraction.

Tea is an important economic plant, which is widely cultivated in many countries, particularly in China. Accurately mapping tea plantations is crucial in the operations, management, and supervision of the growth and development of the tea industry. We propose an object-based convolutional neural network (CNN) to extract tea plantations from very high resolution remote sensing images. Image segmentation was performed to obtain image objects, while a fine-tuned CNN model was used to extract deep image features. We conducted feature selection based on the Gini index to reduce the dimensionality of deep features, and the selected features were then used for classifying tea objects via a random forest. The proposed method was first applied to Google Earth images and then transferred to GF-2 satellite images. We compared the proposed classification with existing methods: Object-based classification using random forest, Mask R-CNN, and object-based CNN without fine-tuning. The results show the proposed method achieved a higher classification accuracy than other methods and produced smaller over- and under-classification geometric errors than Mask R-CNN in terms of shape integrity and boundary consistency. The proposed approach, trained using Google Earth images, achieved comparable results when transferring to the classification of tea objects from GF-2 images. We conclude that the proposed method is effective for mapping tea plantations using very high-resolution remote sensing images even with limited training samples and has huge potential for mapping tea plantations in large areas.

The mountainous vegetation is important to regional sustainable development. However, the topographic effect is the main obstacle to the monitoring of mountainous vegetation using remote sensing. Aiming to retrieve the reflectance of frequently-used red–green–blue and near-infrared (NIR) wavebands of rugged mountains for vegetation mapping, we developed a new integrated topographic correction (ITC) using the SCS + C correction and the shadow-eliminated vegetation index. The ITC procedure consists of image processing, data training, and shadow correction and uses a random forest machine learning algorithm. Our study using the Landsat 8 Operational Land Imager (OLI) multi-spectral images in Fujian province, China, showed that the ITC achieved high performance in topographic correction of regional mountains and in transferability from the sunny area of a scene to the shadow area of three scenes. The ITC-corrected multi-spectral image with an NIR–red–green composite exhibited flat features with impressions of relief and topographic shadow removed. The linear regression of corrected waveband reflectance vs. the cosine of the solar incidence angle showed an inclination that nearly reached the horizontal, and the coefficient of determination decreased to 0.00~0.01. The absolute relative errors of the cast shadow and the self-shadow all dramatically decreased to the range of 0.30~6.37%. In addition, the achieved detection rate of regional vegetation coverage for the three cities of Fuzhou, Putian, and Xiamen using the ITC-corrected images was 0.92~6.14% higher than that using the surface reflectance images and showed a positive relationship with the regional topographic factors, e.g., the elevation and slope. The ITC-corrected multi-spectral images are beneficial for monitoring regional mountainous vegetation. Future improvements can focus on the use of the ITC in higher-resolution imaging.

It is challenging to investigate semantic change detection (SCD) in bi-temporal high-resolution (HR) remote sensing images. For the non-changing surfaces in the same location of bi-temporal images, existing SCD methods often obtain the results with frequent errors or incomplete change detection due to insufficient performance on overcoming the phenomenon of intraclass differences. To address the above-mentioned issues, we propose a novel multi-task consistency enhancement network (MCENet) for SCD. Specifically, a multi-task learning-based network is constructed by combining CNN and Transformer as the backbone. Moreover, a multi-task consistency enhancement module (MCEM) is introduced, and cross-task mapping connections are selected as auxiliary designs in the network to enhance the learning of semantic consistency in non-changing regions and the integrity of change features. Furthermore, we establish a novel joint loss function to alleviate the negative effect of class imbalances in quantity during network training optimization. We performed experiments on publicly available SCD datasets, including the SECOND and HRSCD datasets. MCENet achieved promising results, with a 22.06% Sek and a 37.41% Score on the SECOND dataset and a 14.87% Sek and a 30.61% Score on the HRSCD dataset. Moreover, we evaluated the applicability of MCENet on the NAFZ dataset that was employed for cropland change detection and non-agricultural identification, with a 21.67% Sek and a 37.28% Score. The relevant comparative and ablation experiments suggested that MCENet possesses superior performance and effectiveness in network design.