Search Results (216)

Automatic large-scale building extraction from the LiDAR point clouds and remote sensing images is a growing focus in the fields of the sensor applications and remote sensing. However, this building extraction task remains highly challenging due to the complexity of building sizes, shapes, and surrounding environments. In addition, the discreteness, sparsity, and irregular distribution of point clouds, lighting, and shadows, as well as occlusions of the images, also seriously affect the accuracy of building extraction. To address the above issues, we propose a new unsupervised building extraction algorithm PBEA (Point and Pixel Building Extraction Algorithm) based on a new dual P-snake model (Dual Point and Pixel Snake Model). The proposed dual P-snake model is an enhanced active boundary model, which uses both point clouds and images simultaneously to obtain the inner and outer boundaries. The proposed dual P-snake model enables interaction and convergence between the inner and outer boundaries to improve the performance of building boundary detection, especially in complex scenes. Using the dual P-snake model and polygonization, this proposed PBEA can accurately extract large-scale buildings. We evaluated our PBEA and dual P-snake model on the ISPRS Vaihingen dataset and the Toronto dataset. The experimental results show that our PBEA achieves an area-based quality evaluation metric of 90.0% on the Vaihingen dataset and achieves the area-based quality evaluation metric of 92.4% on the Toronto dataset. Compared with other methods, our method demonstrates satisfactory performance. Full article

Automated water body (WB) extraction is one of the hot research topics in the field of remote sensing image processing. To address the challenges of over-extraction and incomplete extraction in complex water scenes, we propose an encoder–decoder architecture semantic segmentation network for high-precision extraction of WBs called EDWNet. We integrate the Cross-layer Feature Fusion (CFF) module to solve difficulties in segmentation of WB edges, utilizing the Global Attention Mechanism (GAM) module to reduce information diffusion, and combining with the Deep Attention Module (DAM) module to enhance the model’s global perception ability and refine WB features. Additionally, an auxiliary head is incorporated to optimize the model’s learning process. In addition, we analyze the feature importance of bands 2 to 7 in Landsat 8 OLI images, constructing a band combination (RGB 763) suitable for algorithm’s WB extraction. When we compare EDWNet with various other semantic segmentation networks, the results on the test dataset show that EDWNet has the highest accuracy. EDWNet is applied to accurately extract WBs in the Weihe River basin from 2013 to 2021, and we quantitatively analyzed the area changes of the WBs during this period and their causes. The results show that EDWNet is suitable for WB extraction in complex scenes and demonstrates great potential in long time-series and large-scale WB extraction. Full article

Habitat loss due to wildfire is an increasing problem internationally for threatened animal species, particularly tree-dependent and arboreal animals. The koala (Phascolartos cinereus) is endangered in most of its range, and large areas of forest were burnt by widespread wildfires in Australia in 2019/2020, mostly areas dominated by eucalypts, which provide koala habitats. We studied the impact of fire and three subsequent years of recovery on a property in South-East Queensland, Australia. A classified Differenced Normalised Burn Ratio (dNBR) calculated from pre- and post-burn Sentinel-2 scenes encompassing the local study area was used to assess regional impact of fire on koala-habitat forest types. The geometrically structured composite burn index (GeoCBI), a field-based assessment, was used to classify fire severity impact. To detect lower levels of forest recovery, a manual classification of the multitemporal dNBR was used, enabling the direct comparison of images between recovery years. In our regional study area, the most suitable koala habitat occupied only about 2%, and about 10% of that was burnt by wildfire. From the five koala habitat forest types studied, one upland type was burnt more severely and extensively than the others but recovered vigorously after the first year, reaching the same extent of recovery as the other forest types. The two alluvial forest types showed a negligible fire impact, likely due to their sheltered locations. In the second year, all the impacted forest types studied showed further, almost equal, recovery. In the third year of recovery, there was almost no detectable change and therefore no more notable vegetative growth. Our field data revealed that the dNBR can probably only measure the general vegetation present and not tree recovery via epicormic shooting and coppicing. Eucalypt foliage growth is a critical resource for the koala, so field verification seems necessary unless more-accurate remote sensing methods such as hyperspectral imagery can be implemented. Full article

Semantic change detection (SCD) is a newly important topic in the field of remote sensing (RS) image interpretation since it provides semantic comprehension for bi-temporal RS images via predicting change regions and change types and has great significance for urban planning and ecological monitoring. With the availability of large scale bi-temporal RS datasets, various models based on deep learning (DL) have been widely applied in SCD. Since convolution operators in DL extracts two-dimensional feature matrices in the spatial dimension of images and stack feature matrices in the dimension termed the channel, feature maps of images are tri-dimensional. However, recent SCD models usually overlook the stereoscopic property of feature maps. Firstly, recent SCD models are usually limited in capturing spatial global features in the process of bi-temporal global feature extraction and overlook the global channel features. Meanwhile, recent SCD models only focus on spatial cross-temporal interaction in the process of change feature perception and ignore the channel interaction. Thus, to address above two challenges, a novel fine-grained feature perception network (FFPNet) is proposed in this paper, which employs the Omni Transformer (OiT) module to capture bi-temporal channel–spatial global features before utilizing the Omni Cross-Perception (OCP) module to achieve channel–spatial interaction between cross-temporal features. According to the experiments on the SECOND dataset and the LandsatSCD dataset, our FFPNet reaches competitive performance on both countryside and urban scenes compared with recent typical SCD models. Full article

Satellite remote sensing images contain complex and diverse ground object information and the images exhibit spatial multi-scale characteristics, making the panoptic segmentation of satellite remote sensing images a highly challenging task. Due to the lack of large-scale annotated datasets for panoramic segmentation, existing methods still suffer from weak model generalization capabilities. To mitigate this issue, this paper leverages the advantages of the Segment Anything Model (SAM), which can segment any object in remote sensing images without requiring any annotations and proposes a high-resolution remote sensing image panoptic segmentation method called Remote Sensing Panoptic Segmentation SAM (RSPS-SAM). Firstly, to address the problem of global information loss caused by cropping large remote sensing images for training, a Batch Attention Pyramid was designed to extract multi-scale features from remote sensing images and capture long-range contextual information between cropped patches, thereby enhancing the semantic understanding of remote sensing images. Secondly, we constructed a Mask Decoder to address the limitation of SAM requiring manual input prompts and its inability to output category information. This decoder utilized mask-based attention for mask segmentation, enabling automatic prompt generation and category prediction of segmented objects. Finally, the effectiveness of the proposed method was validated on the high-resolution remote sensing image airport scene dataset RSAPS-ASD. The results demonstrate that the proposed method achieves segmentation and recognition of foreground instances and background regions in high-resolution remote sensing images without the need for prompt input, while providing smooth segmentation boundaries with a panoptic segmentation quality (PQ) of 57.2, outperforming current mainstream methods. Full article

The rapid development of sensor technology has made multi-modal remote sensing data valuable for land cover classification due to its diverse and complementary information. Many feature extraction methods for multi-modal data, combining light detection and ranging (LiDAR) and hyperspectral imaging (HSI), have recognized the importance of incorporating multiple spatial scales. However, effectively capturing both long-range global correlations and short-range local features simultaneously on different scales remains a challenge, particularly in large-scale, complex ground scenes. To address this limitation, we propose a multi-scale graph encoder–decoder network (MGEN) for multi-modal data classification. The MGEN adopts a graph model that maintains global sample correlations to fuse multi-scale features, enabling simultaneous extraction of local and global information. The graph encoder maps multi-modal data from different scales to the graph space and completes feature extraction in the graph space. The graph decoder maps the features of multiple scales back to the original data space and completes multi-scale feature fusion and classification. Experimental results on three HSI-LiDAR datasets demonstrate that the proposed MGEN achieves considerable classification accuracies and outperforms state-of-the-art methods. Full article

Land image recognition and classification and land environment detection are important research fields in remote sensing applications. Because of the diversity and complexity of different tasks of land environment recognition and classification, it is difficult for researchers to use a single model to achieve the best performance in scene classification of multiple remote sensing land images. Therefore, to determine which model is the best for the current recognition classification tasks, it is often necessary to select and experiment with many different models. However, finding the optimal model is accompanied by an increase in trial-and-error costs and is a waste of researchers’ time, and it is often impossible to find the right model quickly. To address the issue of existing models being too large for easy selection, this paper proposes a multi-path reconfigurable network structure and takes the multi-path reconfigurable residual network (MR-ResNet) model as an example. The reconfigurable neural network model allows researchers to selectively choose the required modules and reassemble them to generate customized models by splitting the trained models and connecting them through modules with different properties. At the same time, by introducing the concept of a multi-path input network, the optimal path is selected by inputting different modules, which shortens the training time of the model and allows researchers to easily find the network model suitable for the current application scenario. A lot of training data, computational resources, and model parameter experience are saved. Three public datasets, NWPU-RESISC45, RSSCN7, and SIRI-WHU datasets, were used for the experiments. The experimental results demonstrate that the proposed model surpasses the classic residual network (ResNet) in terms of both parameters and performance. Full article

Substantial advancements have been achieved in hyperspectral image (HSI) classification through contemporary deep learning techniques. Nevertheless, the incorporation of an excessive number of irrelevant tokens in large-scale remote sensing data results in inefficient long-range modeling. To overcome this hurdle, this study introduces the Group-Sensitive Selective Perception Transformer (GSAT) framework, which builds upon the Vision Transformer (ViT) to enhance HSI classification outcomes. The innovation of the GSAT architecture is primarily evident in several key aspects. Firstly, the GSAT incorporates a Group-Sensitive Pixel Group Mapping (PGM) module, which organizes pixels into distinct groups. This allows the global self-attention mechanism to function within these groupings, effectively capturing local interdependencies within spectral channels. This grouping tactic not only boosts the model’s spatial awareness but also lessens computational complexity, enhancing overall efficiency. Secondly, the GSAT addresses the detrimental effects of superfluous tokens on model efficacy by introducing the Sensitivity Selection Framework (SSF) module. This module selectively identifies the most pertinent tokens for classification purposes, thereby minimizing distractions from extraneous information and bolstering the model’s representational strength. Furthermore, the SSF refines local representation through multi-scale feature selection, enabling the model to more effectively encapsulate feature data across various scales. Additionally, the GSAT architecture adeptly represents both global and local features of HSI data by merging global self-attention with local feature extraction. This integration strategy not only elevates classification precision but also enhances the model’s versatility in navigating complex scenes, particularly in urban mapping scenarios where it significantly outclasses previous deep learning methods. The advent of the GSAT architecture not only rectifies the inefficiencies of traditional deep learning approaches in processing extensive remote sensing imagery but also markededly enhances the performance of HSI classification tasks through the deployment of group-sensitive and selective perception mechanisms. It presents a novel viewpoint within the domain of hyperspectral image classification and is poised to propel further advancements in the field. Empirical testing on six standard HSI datasets confirms the superior performance of the proposed GSAT method in HSI classification, especially within urban mapping contexts, where it exceeds the capabilities of prior deep learning techniques. In essence, the GSAT architecture markedly refines HSI classification by pioneering group-sensitive pixel group mapping and selective perception mechanisms, heralding a significant breakthrough in hyperspectral image processing. Full article

Advancements in satellite and aerial imagery technology have made it easier to obtain high-resolution remote sensing images, leading to widespread research and applications in various fields. Remote sensing image semantic segmentation is a crucial task that provides semantic and localization information for target objects. In addition to the large-scale variation issues common in most semantic segmentation datasets, aerial images present unique challenges, including high background complexity and imbalanced foreground–background ratios. However, general semantic segmentation methods primarily address scale variations in natural scenes and often neglect the specific challenges in remote sensing images, such as inadequate foreground modeling. In this paper, we present a foreground-aware remote sensing semantic segmentation model. The model introduces a multi-scale convolutional attention mechanism and utilizes a feature pyramid network architecture to extract multi-scale features, addressing the multi-scale problem. Additionally, we introduce a Foreground–Scene Relation Module to mitigate false alarms. The model enhances the foreground features by modeling the relationship between the foreground and the scene. In the loss function, a Soft Focal Loss is employed to focus on foreground samples during training, alleviating the foreground–background imbalance issue. Experimental results indicate that our proposed method outperforms current state-of-the-art general semantic segmentation methods and transformer-based methods on the LS dataset benchmark. Full article

With the rapid development of remote sensing image data, the efficient retrieval of target images of interest has become an important issue in various applications including computer vision and remote sensing. This research addressed the low-accuracy problem in traditional content-based image retrieval algorithms, which largely rely on comparing entire image features without capturing sufficient semantic information. We proposed a scene graph similarity-based remote sensing image retrieval algorithm. Firstly, a one-shot object detection algorithm was designed for remote sensing images based on Siamese networks and tailored to the objects of an unknown class in the query image. Secondly, a scene graph construction algorithm was developed, based on the objects and their attributes and spatial relationships. Several construction strategies were designed based on different relationships, including full connections, random connections, nearest connections, star connections, or ring connections. Thirdly, by making full use of edge features for scene graph feature extraction, a graph feature extraction network was established based on edge features. Fourthly, a neural tensor network-based similarity calculation algorithm was designed for graph feature vectors to obtain image retrieval results. Fifthly, a dataset named remote sensing images with scene graphs (RSSG) was built for testing, which contained 929 remote sensing images with their corresponding scene graphs generated by the developed construction strategies. Finally, through performance comparison experiments with remote sensing image retrieval algorithms AMFMN, MiLaN, and AHCL, in precision rates, Precision@1 improved by 10%, 7.2%, and 5.2%, Precision@5 improved by 3%, 5%, and 1.7%; and Precision@10 improved by 1.7%, 3%, and 0.6%. In recall rates, Recall@1 improved by 2.5%, 4.3%, and 1.3%; Recall@5 improved by 3.7%, 6.2%, and 2.1%; and Recall@10 improved by 4.4%, 7.7% and 1.6%. Full article

Human urine and its detection are of interest in forensic studies in numerous contexts. Both crystalline urea and 1.0 M solutions of urea, as synthetic analog endmember components of human urine, were investigated as a proof-of-concept study to determine if detailed lab spectroscopy would be viable. Urea was reliably detected on Ottawa sand at concentrations of approximately 3.2% in dried experiments. Urea was detectable after 1 week of solution evaporation under lab conditions, at 9.65 wt.% 1 M solution. This investigation successfully establishes urea as a material of interest for reflective spectroscopy and hyperspectral remote sensing/image spectroscopy on a wide range of spatial scales, from specific centimeter-scale areas in a crime scene to searching large outdoor regions > 1 km². In addition, this investigation is relevant to improving the monitoring of human trafficking, status and condition of refugee camps, and monitoring sewage. Full article

Remote-sensing technology has gradually become one of the most important ways to extract sea–land boundaries due to its large scale, high efficiency, and low cost. However, sea–land segmentation (SLS) is still a challenging problem because of data diversity and inconsistency, “different objects with the same spectrum” or “the same object with different spectra”, and noise and interference problems, etc. In this paper, a new sea–land segmentation method (PMFormer) for remote-sensing images is proposed. The contributions are mainly two points. First, based on Mask2Former architecture, we introduce the prompt mask by normalized difference water index (NDWI) of the target image and prompt encoder architecture. The prompt mask provides more reasonable constraints for attention so that the segmentation errors are alleviated in small region boundaries and small branches, which are caused by insufficiency of prior information by large data diversity or inconsistency. Second, for the large intra-class difference problem in the foreground–background segmentation in sea–land scenes, we use deep clustering to simplify the query vectors and make them more suitable for binary segmentation. Then, traditional NDWI and eight other deep-learning methods are thoroughly compared with the proposed PMFormer on three open sea–land datasets. The efficiency of the proposed method is confirmed, after the quantitative analysis, qualitative analysis, time consumption, error distribution, etc. are presented by detailed contrast experiments. Full article

The precise estimation of above-ground biomass (AGB) is imperative for the advancement of breeding programs. Optical variables, such as vegetation indices (VI), have been extensively employed in monitoring AGB. However, the limited robustness of inversion models remains a significant impediment to the widespread application of UAV-based multispectral remote sensing in AGB inversion. In this study, a novel stem–leaf separation strategy for AGB estimation is delineated. Convolutional neural network (CNN) and transfer learning (TL) methodologies are integrated to estimate leaf biomass (LGB) across multiple growth stages, followed by the development of an allometric growth model for estimating stem biomass (SGB). To enhance the precision of LGB inversion, the large-scale remote sensing data and image simulation framework over heterogeneous scenes (LESS) model, which is a three-dimensional (3D) radiative transfer model (RTM), was utilized to simulate a more extensive canopy spectral dataset, characterized by a broad distribution of canopy spectra. The CNN model was pre-trained in order to gain prior knowledge, and this knowledge was transferred to a re-trained model with a subset of field-observed samples. Finally, the allometric growth model was utilized to estimate SGB across various growth stages. To further validate the generalizability, transferability, and predictive capability of the proposed method, field samples from 2022 and 2023 were employed as target tasks. The results demonstrated that the 3D RTM + CNN + TL method outperformed best in LGB estimation, achieving an R² of 0.73 and an RMSE of 72.5 g/m² for the 2022 dataset, and an R² of 0.84 and an RMSE of 56.4 g/m² for the 2023 dataset. In contrast, the PROSAIL method yielded an R² of 0.45 and an RMSE of 134.55 g/m² for the 2022 dataset, and an R² of 0.74 and an RMSE of 61.84 g/m² for the 2023 dataset. The accuracy of LGB inversion was poor when using only field-measured samples to train a CNN model without simulated data, with R² values of 0.30 and 0.74. Overall, learning prior knowledge from the simulated dataset and transferring it to a new model significantly enhanced LGB estimation accuracy and model generalization. Additionally, the allometric growth model’s estimation of SGB resulted in an accuracy of 0.87 and 120.87 g/m² for the 2022 dataset, and 0.74 and 86.87 g/m² for the 2023 dataset, exhibiting satisfactory results. Separate estimation of both LGB and SGB based on stem and leaf separation strategies yielded promising results. This method can be extended to the monitor and inversion of other critical variables. Full article

Land-cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. We address the challenges in land-cover segmentation of remote-sensing imagery and complete the following work. Firstly, to tackle the issues of foreground–background imbalance and scale variation, a module based on multi-dilated rate convolution fusion was integrated into a decoder. This module extended the receptive field through multi-dilated convolution, enhancing the model’s capability to capture global features. Secondly, to address the diversity of scenes and background interference, a hybrid attention module based on large-kernel convolution was employed to improve the performance of the decoder. This module, based on a combination of spatial and channel attention mechanisms, enhanced the extraction of contextual information through large-kernel convolution. A convolution kernel selection mechanism was also introduced to dynamically select the convolution kernel of the appropriate receptive field, suppress irrelevant background information, and improve segmentation accuracy. Ablation studies on the Vaihingen and Potsdam datasets demonstrate that our decoder significantly outperforms the baseline in terms of mean intersection over union and mean F1 score, achieving an increase of up to 1.73% and 1.17%, respectively, compared with the baseline. In quantitative comparisons, the accuracy of our improved decoder also surpasses other algorithms in the majority of categories. The results of this paper indicate that our improved decoder achieves significant performance improvement compared with the old decoder in remote-sensing image-segmentation tasks, which verifies its application potential in the field of land-cover segmentation. Full article

Quantifying the effect of maize tassel on canopy reflectance is essential for creating a tasseling progress monitoring index, aiding precision agriculture monitoring, and understanding vegetation canopy radiative transfer. Traditional field measurements often struggle to detect the subtle reflectance differences caused by tassels due to complex environmental factors and challenges in controlling variables. The three-dimensional (3D) radiative transfer model offers a reliable method to study this relationship by accurately simulating interactions between solar radiation and canopy structure. This study used the LESS (large-scale remote sensing data and image simulation framework) model to analyze the impact of maize tassels on visible and near-infrared reflectance in heterogeneous 3D scenes by modifying the structural and optical properties of canopy components. We also examined the anisotropic characteristics of tassel effects on canopy reflectance and explored the mechanisms behind these effects based on the quantified contributions of the optical properties of canopy components. The results showed that (1) the effect of tassels under different planting densities mainly manifests in the near-infrared band of the canopy spectrum, with a variation magnitude of ±0.04. In contrast, the impact of tassels on different leaf area index (LAI) shows a smaller response difference, with a magnitude of ±0.01. As tassels change from green to gray during growth, their effect on reducing canopy reflectance increases. (2) The effect of maize tassel on canopy reflectance varied with spectral bands and showed an obvious directional effect. In the red band at the same sun position, the difference in tassel effect caused by the observed zenith angle on canopy reflectance reaches 200%, while in the near-infrared band, the difference is as high as 400%. The hotspot effect of the canopy has a significant weakening effect on the shadow effect of the tassel. (3) The non-transmittance optical properties of maize tassels reduce canopy reflectance, while their high reflectance increases it. Thus, the dual effects of tassels create a game in canopy reflectance, with the final outcome mainly depending on the sensitivity of the canopy spectrum to transmittance. This study demonstrates the potential of using 3D radiative transfer models to quantify the effects of crop fine structure on canopy reflectance and provides some insights for optimizing crop structure and implementing precision agriculture management (such as selective breeding of crop optimal plant type). Full article