With the continuous enhancement of remote sensing image resolution and the rapid advancement of deep learning techniques, land cover mapping is undergoing a significant transformation from pixel-level segmentation to object-based vector modeling. This shift imposes higher demands on deep learning models, requiring not only precise delineation of object boundaries but also the preservation of topological consistency among geographic elements. However, existing public datasets face three major limitations: limited class annotations, restricted data scale, and the lack of spatial structural information, which severely hinder the development of breakthrough methods in high-resolution remote sensing vectorization. To address these challenges, we present IRSAMap, the first global remote sensing dataset designed for large-scale, high-resolution, multi-feature land cover vector mapping. This dataset offers four key advantages: First, a comprehensive element vector annotation system that includes over 1.8 million instances of 10 typical natural and man-made objects, such as buildings, roads, rivers, and trees, employing a unified vector annotation standard framework that ensures both semantic integrity and spatial structural accuracy. Second, an intelligent annotation workflow incorporating “manual pre-annotation + AI-based training and inference + manual review and correction,” which enhances annotation efficiency while ensuring consistency. Third, a global coverage that spans 67 regions across six continents, representing diverse terrain types, including urban and rural areas, with a total coverage area exceeding 1,000 square kilometers. Fourth, multi-task adaptability, supporting various tasks such as pixel-level land cover classification, building outline regularization extraction, road centerline extraction, and panoramic segmentation. As a fundamental resource for remote sensing intelligent interpretation, IRSAMap provides a standardized benchmark for the paradigm shift from pixels to objects, which will significantly advance the development of high-precision geographic feature automation, collaborative modeling, and other cutting-edge research directions. The dataset is of great value for applications such as global geographic information updating and digital twin construction. IRSAMap is publicly available at https://github.com/ucas-dlg/IRSAMap.

The semantic segmentation of high-resolution (HR) remote sensing images (RSIs) has been extensively researched in various applications. However, segmentation networks are prone to significant performance degradation on unlabeled data due to domain shift, such as data distribution shifts arising from distinct geographic locations. To address this issue, we propose a multilevel-guided curriculum domain adaptation (MuGCDA) approach for joint samplewise, categorywise, and pixelwise tasks, which facilitates the final fine-grained segmentation task by guiding the target domain to acquire samplewise and categorywise domain-robust properties. Concretely, at the sample level, we formulate a sample spatial relationship consistency guidance (SSCG) loss that guides the target domain to acquire similar sample spatial relationship properties to the source domain. At the category level, we propose a category layout structure consistency guidance (CLCG) module that guides the target domain to acquire consistent layout properties. At the pixel level, we design an adaptive hierarchical pseudolabel weight setting (AHPWS) method with a self-training (ST) paradigm to reduce the effect of label noise while improving the quality of the generated pseudolabels. Furthermore, to improve the stability of the training process, we use a momentum network (MN) as the teacher network to obtain the property knowledge and pseudolabels, and then guide the whole domain transfer process of the segmentation network, which acts as the student network. Extensive comparison and ablation experiments are conducted in several cross-space and cross-spectral scenes, and the results show that our method achieves significant performance improvements in cross-domain scenes for HR RSIs.

Semantic segmentation of the remote sensing images (RSIs) has attracted increasing interest in recent years. However, large-area segmentation of the woodland presents challenges. The wide distribution and diverse tree species of the woodland make feature extraction difficult. For this reason, an infrared attention network (InfAttNet) is proposed to extract woodland from multispectral RSIs. InfAttNet has an extra infrared spectral encoder which makes use of the sensitivity of vegetation to near infrared and red edge spectrums. This extra encoder applies learning about vegetation to improve woodland segmentation. Several attention blocks are designed to enhance learning about vegetation features and so improve the performance. In addition, a new dataset is built, containing a large number of woodland RSIs and covering several typical woodland distribution regions in China. The experimental results demonstrate that, compared with other networks, InfAttNet has the highest accuracy and is capable of rapid extraction of the woodland in RSIs.

Gaofen-6 (GF-6) is a geostationary, earth-observation satellite, rely on it's multi-spectral images, GF-6 has the ability to support the monitoring of woodland resources. In this paper, the multi-spectral images sent by GF-6 are studied as dataset, and a model called Infrared Attention Network (InfAttNet) which based on semantic segmentation method is proposed to distinguish woodland from other land types to achieve the purpose of woodland extraction. To make full use of the spectral information, InfAttNet has an additional encoder to extract the features of infrared bands independently. Besides, infrared attention blocks help InfAttNet to enhance the characteristics of woodland. The experimental results proved that InfAttNet improves the accuracy of woodland extraction, and the segmentation effect is strengthened compared with classical networks.

Landslides are a kind of geologic hazard triggered by anthropogenic or natural factors. Change detection is an important technique to extract the landslide area from pre- and postdisaster images. As landslides are similar in spectrum to bare land and it is difficult to absolutely calibrate the radiation of multitemporal images, the detection method may lead to significant errors or omissions. By modeling the relative relationship between adjacent pixels from multitemporal images, errors or omissions and illumination influences will be reduced during detection. With the aim of extracting landslides with an automatic and robust process, this letter proposes a practical method based on multitemporal data and spatiotemporal model. First, the normalized difference vegetation index (NDVI) and built-up area presence index (PanTex) features series were produced, which can reflect changes in vegetated and built-up areas, respectively. Then, we used a spatiotemporal context (STC) model to detect landslide from feature series. Finally, the landslide map could be derived. The proposed method was applied to detect landslide using GaoFen (GF) series satellite. The experimental results demonstrated the effectiveness and robustness of our method.

For obtaining information about ecosystem resource, GF-1 satellite was launched on April 26, 2013, which is the first satellite of the China's High-Resolution Earth Observation System. After obtaining some of the remote sensing images from GF-1, we selected WFV(wide field vision) images and detected the woodland to separate it from other geography types in the images. First, WFV images were clipped and labeled, then two deep learning models, POI-Net and Deep-UNet were used for training. We fused the prediction matrixes of deep learning networks using proposed "Most-sure strategy". The results show that our method can effectively improve the accuracy of woodland detection and segmentation results are outstanding. In addition, the proposed framework can also detect woodland in images returned by GF-6 satellite.

Landslides occur frequently and it is very meaningful to monitor them in disaster researches. Extracting the landslide from the high resolution satellite with fewer false changes is an important problem to be solved for remote sensing change detection research. In high spatial resolution and multi-temporal remote sensing images, landslides show significant differences with the background in both temporal and spatial neighborhoods, the knowledge of fusing temporal and spatial information is more favorable for landslide detection. NDVI (Normalized Difference Vegetable Index) and PanTex (built-up area presence index) features can reflect these changes in vegetable and built-up area respectively. Based on GF-1 CCD data and the change detection method of spatio-temporal context, the proposed method can detect the landslide area accurately by using NDVI and PanTex features.

The Separability and Thresholds (SEaTH) algorithm calculates the the SEparability and the corresponding THresholds of object classes for any number of given features. However, it is applicable only to the normally distributed training data. To cope with the problem, The Classification And Regression Tree (CART) coupled with SEaTH for object-based classification approach is proposed in the paper. The idea of this method is derived from the merits of the CART which can effectively analyze the non-normally distributed data and automatically create the classification tree. A comparison of classification results demonstrate that the solution for object-based classification proposed in this article can be used to obtain a higher classification accuracy than SEaTH classification.

Multi-scale spatial context which integrates spatial metrics and textural metrics is used to characterize land-use parcel and a hybrid land-use mapping approach is proposed in this paper. In terms of land-use characterization, the contributions of textural and spatial metrics are evaluated quantitatively. In terms of land-use categorization, a hybrid land-use classification scheme which combines Pairwise Decision Tree based Support Vector Machine (PDTSVM) and rule based decision tree is designed to classify parcels into construction, cultivated and uncultivated agricultural parcels. Experiment show that applying the presented technique can facilitate land-use mapping.

Monitoring snow distribution area plays an important role in researching climate change and energy exchange process. Chinese small satellite constellation (abbreviated HJ constellation) is special for environment and disaster continuously monitoring or forecasting. By using HJ-1B CCD and infrared data or only using its infrared data, it can construct NDSI (Normalized Difference Snow Index) or MNDSI (Modified Normalized Difference Snow Index) respectively to detect snow area. However, obtaining the CCD and infrared images at the same time is impossible for the long time monitoring. Furthermore, snow area is mixed with vegetation, the snow index's value will be reduced, and snow area in these places could not be detected accurately. Therefore, this paper introduces an improved snow cover monitoring method based on MNDSI and priori information of vegetation to increase the detection accuracy of snow area by using HJ-1B infrared image. The proposed method has the higher precision than the compared method.

Road traffic volume monitoring plays an important role in transportation planning and spatial development, particularly in urban areas. The high-resolution satellite imagery provides a new data source to detect vehicles. Meanwhile, Satellite image covers large areas instantaneously, providing a possibility for snapshotting road traffic conditions. In this paper, we proposed an approach based on watershed image segmentation to detect the urban road vehicles from GF-2 imagery. The vehicles detection involves the two main steps: Firstly, a GIS road vector map and vegetation masks were applied to the image to guide vehicle detection by restricting the roads only. Secondly, watershed image segmentation was performed to separate bright and dark vehicles from the background in the road region. Then, a rule-based classifier was established to classify the image objects into the vehicle and the non-vehicle objects by using the spectral and shape feature information of image objects. Finally, the overall performance of the vehicle detection were compared with the manually counts, yielding overall accuracy of 81% with 93% classification accuracy. This detection accuracy may be considered acceptable for operational use in traffic monitoring.

The parcel-based changed detection by adopting the holistic feature can extract the changed parcels in land-use maps[1]. This method of parcel-based change detection uses the holistic feature, which represents each land use parcels clipped by polygons in the land use map with the energy spectrum of WFT and extracts the changed parcels according to the distance threshold between feature vectors associated with pairs of corresponding parcels. In this procedure, a key point is deriving the “Spatial Envelope” feature of each land-use parcel segmented by the land use map, so the three parameters used to calculate this feature will surely influence the descriptor and the change detection results. In this article, we conduct experimental analysis to analyze the influence of different parameters on the results in order to find out the optimal parameters for parcel-based change detection. After comparisons and analysis, we have concluded that the optimal scale number parameter is 4, the optimal angle number parameter is 8 and the optimal block number parameter is 16 blocks(4*4) for parcel-based change detection.