Land Segmentation Research Articles

Longitudinal Perching Trajectory Planning for a Fixed-Wing Unmanned Aerial Vehicle at High Angle of Attack Based on the Estimation of Region of Attraction

In this paper, a method for planning the perching trajectory of a fixed-wing unmanned aerial vehicle (UAV) based on the estimation of the region of attraction (ROA) is proposed, to expand the feasible domain of a UAV in the presence of aerodynamic performance degradation and landing-limited conditions with high angle of attack (AOA). According to the aerodynamic characteristics of the system, the perching process is first decomposed into flight and landing segments, and the corresponding flight dynamic model and structural dynamic model are established, based on the Lagrange function, while the continuity of the two models is proved. Then, the structural dynamic model is analyzed for asymptotic stability based on the ROA estimation results from the Lyapunov function. On this basis, a fixed-wing UAV perching trajectory planning strategy is proposed. This strategy enables the UAV to achieve stable perching with a reasonable flight trajectory, as it fully considers the flight dynamic constraints of the UAV and the structural dynamic constraints of the landing gear. Our simulation results show that flight trajectory planning considering the ROA can significantly increase the number of available trajectories for fixed-wing UAVs during high AOA perching, which also greatly enhances its flexibility in trajectory selection.

Deep Learning and Remote Sensing for Restoring Abandoned Agricultural Lands in the Middle Volga (Russia)

Abandoned agricultural lands in the Middle Volga region of Russia, which appeared because of socio-economic transformations after the collapse of the USSR and the liquidation of collective farms, represent a significant potential for increasing agricultural production and economic development of the region. This study develops a comprehensive approach to assessing the suitability of these lands for return to agricultural turnover using machine learning methods and remote sensing data. Sentinel-2 satellite imagery and a deep neural network based on MAnet architecture with Mix Vision Transformer encoder (MiT-b5), which achieved an accuracy of 93.4% and an IoU coefficient of 0.84, were used for semantic segmentation of modern agricultural land. Land use dynamics since 1985 were analysed using Landsat 4–9 data, revealing significant areas of abandoned arable land. Land suitability was assessed, taking into account natural resource factors such as topography, soils and climatic conditions. The results showed that the total area of land suitable for reclaimed land is 2,014,845 ha, which could lead to an increase in wheat yield by 7.052 million tons. The potential cumulative net profit is estimated at 35.26 billion rubles (about US$352.6 million). The main conclusions indicate the significant economic and social potential of returning abandoned land to agricultural turnover, which requires a comprehensive approach that includes investment in infrastructure and the introduction of modern agro-technologies.

Research on coastline extraction and dynamic change from remote sensing images based on deep learning

Accurate coastline extraction is crucial for the scientific management and protection of coastal zones. Due to the diversity of ground object details and the complexity of terrain in remote sensing images, the segmentation of sea and land faces challenges such as unclear segmentation boundaries and discontinuous coastline contours. To address these issues, this study improve the accuracy and efficiency of coastline extraction by improving the DeepLabv3+ model. Specifically, this study constructs a sea-land segmentation network, DeepSA-Net, based on strip pooling and coordinate attention mechanisms. By introducing dynamic feature connections and strip pooling, the connection between different branches is enhanced, capturing a broader context. The introduction of coordinate attention allows the model to integrate coordinate information during feature extraction, thereby allowing the model to capture longer-distance spatial dependencies. Experimental results has shown that the model can achieves a land-sea segmentation mean intersection over union (mIoU) ration and Recall of over 99% on all datasets. Visual assessment results show more complete edge details of sea-land segmentation, confirming the model’s effectiveness in complex coastal environments. Finally, using remote sensing data from a coastal area in China as an application instance, coastline extraction and dynamic change analysis were implemented, providing new methods for the scientific management and protection of coastal zones.

Sea–Land Segmentation of Remote-Sensing Images with Prompt Mask-Attention

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.

Toward efficient and lightweight sea–land segmentation for remote sensing images

Sea–land segmentation is of great significance for autonomous coastline monitoring, which is fundamental research in the remote sensing community. Due to the diverse contents and easily confused sea–land boundaries contained in remote sensing images, it is always challenging to achieve precise sea–land segmentation for complex scenarios. Although existing deep learning-based methods have exhibited promising performance, excessive computational load and insufficient use of hierarchical features remain unresolved. In this paper, we contribute to addressing the problems by developing an efficient and lightweight convolutional neural network (CNN) termed E-Net. On the one hand, the proposed network adopts a novel E-shaped architecture that reforms the conventional U-codec structure to make full use of hierarchical features at different depths, so that the sea–land segmentation effect can be significantly improved without excessive computational load. On the other hand, a contextual aggregation attention mechanism (CA2M) is designed to further facilitate efficient aggregation and transmission of contextual information, so that the fuzzy and irregular sea–land boundaries can be accurately distinguished. Extensive experiments reveal that our approach not only produces superior sea–land segmentation effect but also demonstrates promising computational efficiency. Specifically, the proposed E-Net achieves state-of-the-art sea–land segmentation performance with 92.78% and 93.62% mean Intersection over Union (mIoU) on the SLSD and HRSC2016 datasets, respectively, while the frames per second (FPS) reaches 108.032 with as low as 52.287G floating point operations per second (FLOPs).

DAENet: Deformable Attention Edge Network for Automatic Coastline Extraction from Satellite Imagery

Sea–land segmentation (SLS) is a crucial step in coastline extraction. In CNN-based approaches for coastline feature extraction, downsampling is commonly used to reduce computational demands. However, this method may unintentionally discard small-scale features, hindering the capture of essential global contextual information and clear edge information necessary for SLS. To solve this problem, we propose a novel U-Net structure called Deformable Attention Edge Network (DAENet), which integrates edge enhancement algorithms and a deformable self-attention mechanism. First of all, we designed a multi-scale transformation (MST) to enhance edge feature extraction and model convergence through multi-scale transformation and edge detection, enabling the network to capture spatial–spectral changes more effectively. This is crucial because the deformability of the Deformable Attention Transformer (DAT) modules increases training costs for model convergence. Moreover, we introduced DAT, which leverages its powerful global modeling capabilities and deformability to enhance the model’s recognition of irregular coastlines. Finally, we integrated the Local Adaptive Multi-Head Attention-based Edge Detection (LAMBA) module to enhance the spatial differentiation of edge features. We designed each module to address the complexity of SLS. Experiments on benchmark datasets demonstrate the superiority of the proposed DAENet over state-of-the-art methods. Additionally, we conducted ablation experiments to evaluate the effectiveness of each module.

SRMA: a dual-branch parallel multi-scale attention network for remote sensing images sea-land segmentation

ABSTRACT The use of deep learning-based high resolution remote sensing image sea and land segmentation method has become prevalent in various fields such as environmental monitoring, resource assessment, and urban planning. However, the segmentation process faces challenges due to the complex coastline and the similarity in spectral colour difference between the sea and land in certain areas. The remote sensing images obtained from satellites often exhibit unclear boundaries between the sea and land, as well as intricate coastlines. Consequently, the segmentation of sea and land becomes a difficult task. The existing sea-land segmentation methods have limitations in accurately segmenting long and narrow waters, as well as areas with low differentiation between sea and land. In this paper, we propose a new sea-land segmentation method called SRMA (Swin-Res-Multi-Attention). SRMA performs parallel feature extraction using a dual-branch parallel: Swin-Transformer branch and ResNet branch. The combination of Swin-Transformer’s self-attention and ResNet’s residual design helps reduce the loss of feature information, thereby avoiding incorrect segmentation in regions with low distinctness. To improve overall stability, we introduce the MCA (Multiscale channel attention module) module, which combines feature information from different scales. The multi-scale pyramid design of MCA module ensures stability and improves segmentation accuracy in narrow waters. Experimental results on a public dataset demonstrate that our model outperforms existing methods. Additionally, we evaluate the model’s performance in complex scenarios by creating a new dataset that includes a complex urban water body and cloud interference. The results showcase the robustness and superiority of our model.

STIRUnet: SwinTransformer and inverted residual convolution embedding in unet for Sea–Land segmentation

Extraction of coastline from optical remote sensing images is of paramount importance for coastal zone management, erosion monitoring, and intelligent ocean construction. However, nearshore marine environment complexity presents a challenge when capturing small-scale and detailed information regarding coastlines. Furthermore, the presence of numerous tidal flats, suspended sediments, and coastal biological communities exacerbates the reduction in segmentation accuracy, which is particularly noticeable in medium–high-resolution remote sensing image segmentation tasks. Most previous related studies, based primarily on convolutional neural networks (CNNs) or traditional feature extraction methods, faced challenges in detailed pixel-level refinement and lacked comprehensive understanding of the studied images. Therefore, we proposed a new U-shaped deep learning model (STIRUnet) that combines the excellent global modeling ability of SwinTransformer with an improved CNN using an inverted residual module. The proposed method has the capability of global supervised feature learning and layer-by-layer feature extraction, and we conducted sea–land segmentation experiments using GF-HNCD and BSD remote sensing image datasets to validate the performance of the proposed model. The results indicate the following: 1) suspended sediments and coastal biological communities are major contributors to coastline blurring, and 2) the recovery of minute features (e.g., narrow watercourses and microscale artificial structures) effectively enhances edge details and leads to more realistic segmentation outcomes. The findings of this study are highly important in relation of accurate extraction of sea–land information in complex marine environments, and they offer novel insights regarding mixed-pixel identification.

Nearshore Ship Detection in PolSAR Images by Integrating Superpixel-Level GP-PNF and Refined Polarimetric Decomposition

Nearshore ship detection has significant applications in both the military and civilian domains. Compared to synthetic aperture radar (SAR), polarimetric synthetic aperture radar (PolSAR) provides richer information for analyzing the scattering mechanisms of ships and enables better detection of ship targets. However, ships in nearshore areas tend to be highly concentrated, and ship detection is often affected by adjacent strong scattering, resulting in false alarms or missed detections. While the GP-PNF detector performs well in PolSAR ship detection, it cannot obtain satisfactory results in these scenarios, and it also struggles in the presence of azimuthal ambiguity or strong clutter interference. To address these challenges, we propose a nearshore ship detection method named ECD-PNF by integrating superpixel-level GP-PNF and refined polarimetric decomposition. Firstly, polarimetric superpixel segmentation and sea–land segmentation are performed to reduce the influence of land on ship detection. To estimate the sea clutter more accurately, an automatic censoring (AC) mechanism combined with superpixels is used to select the sea clutter superpixels. By utilizing refined eight-component polarimetric decomposition to improve the scattering vector, the physical interpretability of the detector is enhanced. Additionally, the expression of polarimetric coherence is improved to enhance the target clutter ratio (TCR). Finally, this paper combines the third eigenvalue of eigenvalue–eigenvector decomposition to reduce the impact of azimuthal ambiguity. Three spaceborne PolSAR datasets from Radarsat-2 and GF-3 are adopted in the experiments for comparison. The proposed ECD-PNF method achieves the highest figure of merit (FoM) value of 0.980, 1.000, and 1.000 for three datasets, validating the effectiveness of the proposed method.

Sensitivity of the Land–Atmosphere Coupling to Soil Moisture Anomalies during the Warm Season in China and its Surrounding Areas

Significant temporal and spatial variability in soil moisture (SM) is observed during the warm season in China and its surrounding regions. Because of the existence of two different evapotranspiration regimes, i.e., soil moisture-limited and energy-limited, averaging the land–atmosphere (L–A) coupling strength for all soil wetness scenarios may result in the loss of coupling signals. This study examines the daytime-only L–A interactions under different soil moisture conditions, by using two-legged metrics in the warm season from May to September 1981–2020, partitioning the interactions between SM and latent heat flux (SM–LH, the land leg) from the interactions between latent heat flux and the lifting condensation level (LH–LCL, the atmospheric leg). The statistical results reveal large regional differences in warm-season daytime L–A feedback in China and its surrounding areas. As the soil becomes wetter, the positive SM–LH coupling strength increases in arid regions (e.g., northwest China, Hetao, and the Great Indian Desert) and the positive feedback shifts to the negative one in semi-arid/semi-humid regions (northeast and northern China). The negative LH–LCL coupling is most pronounced in wet soil months in arid regions, while the opposite is true for the Tibetan Plateau. In terms of intraseasonal variation, the large variability of SM in north China, the Tibetan Plateau, and India due to the influence of the summer monsoon leads to the sign change in the land segment coupling index, comparing pre- and post-monsoon periods. To further examine the impact of SM anomalies on L–A coupling and to explore evapotranspiration regimes in the North China Plain, four sets of sensitivity experiments with different soil moisture levels over a period of 10 years were conducted. Under relatively dry soil conditions, evapotranspiration is dominated by the soil moisture-limited regime with positive L–A coupling, regardless of external moisture inflow. The critical soil moisture value separating a soil moisture-limited and an energy-limited regime lies between 0.24 m3/m3 and 0.29 m3/m3. Stronger positive feedback under negative soil moisture anomalies may increase the risk of drought in the North China Plain.

Difference-Focusing Fusion Decision Method: An Ensemble Learning Framework and Its Application in Improving Deep Learning Sea–Land Segmentation for Waterline Extraction in Synthetic Aperture Radar Imagery

Difference-Focusing Fusion Decision Method: An Ensemble Learning Framework and Its Application in Improving Deep Learning Sea–Land Segmentation for Waterline Extraction in Synthetic Aperture Radar Imagery

WRBSNet: A Novel Sea–Land Segmentation Network With a Wider Range of Batch Sizes

WRBSNet: A Novel Sea–Land Segmentation Network With a Wider Range of Batch Sizes

Land Survey and Mapping for Agricultural Purpose using UAV

Unmanned Aerial Vehicles (UAVs) are a group of aerial vehicles that include drones. Agriculture has always been the backbone of India’s sustained growth. Land surveying is the most challenging task in the agricultural field in terms of accuracy and time required for surveying using the traditional method. We have built a fully autonomous UAV and calibrated it for agricultural land survey purposes. The navigation and mapping process, in which a predefined path is provided to the UAV flight controller. During its autonomous flight, the drone's camera captures multiple images. Using a threshold-based segmentation method, the cultivated land and uncultivated land areas are determined using this system. Pre-processing of the images, land area segmentation, and post-processing of the images are carried out. The pre-processed image is divided into several distinct regions by applying a colour thresholding technique, which serves as the foundation for the segmentation of land. The results illustrate that the proposed method outperforms the existing method.

Polarimetric Synthetic Aperture Radar Ship Potential Area Extraction Based on Neighborhood Semantic Differences of the Latent Dirichlet Allocation Bag-of-Words Topic Model

Recently, deep learning methods have been widely studied in the field of polarimetric synthetic aperture radar (PolSAR) ship detection. However, extracting polarimetric and spatial features on the whole PolSAR image will result in high computational complexity. In addition, in the massive data ship detection task, the image to be detected contains a large number of invalid areas, such as land and seawater without ships. Therefore, using ship coarse detection methods to quickly locate the potential areas of ships, that is, ship potential area extraction, is an important prerequisite for PolSAR ship detection. Since existing unsupervised PolSAR ship detection methods based on pixel-level features often rely on fine sea–land segmentation pre-processing and have poor applicability to images with complex backgrounds, in order to solve the abovementioned issue, this paper proposes a PolSAR ship potential area extraction method based on the neighborhood semantic differences of an LDA bag-of-words topic model. Specifically, a polarimetric feature suitable for the scattering diversity condition is selected, and a polarimetric feature map is constructed; the superpixel segmentation method is used to generate the bag of words on the feature map, and latent high-level semantic features are extracted and classified with the improved LDA bag-of-words topic model method to obtain the PolSAR ship potential area extraction result, i.e., the PolSAR ship coarse detection result. The experimental results on the self-established PolSAR dataset validate the effectiveness and demonstrate the superiority of our method.

TCUNet: A Lightweight Dual-Branch Parallel Network for Sea–Land Segmentation in Remote Sensing Images

Remote sensing techniques for shoreline extraction are crucial for monitoring changes in erosion rates, surface hydrology, and ecosystem structure. In recent years, Convolutional neural networks (CNNs) have developed as a cutting-edge deep learning technique that has been extensively used in shoreline extraction from remote sensing images, owing to their exceptional feature extraction capabilities. They are progressively replacing traditional methods in this field. However, most CNN models only focus on the features in local receptive fields, and overlook the consideration of global contextual information, which will hamper the model’s ability to perform a precise segmentation of boundaries and small objects, consequently leading to unsatisfactory segmentation results. To solve this problem, we propose a parallel semantic segmentation network (TCU-Net) combining CNN and Transformer, to extract shorelines from multispectral remote sensing images, and improve the extraction accuracy. Firstly, TCU-Net imports the Pyramid Vision Transformer V2 (PVT V2) network and ResNet, which serve as backbones for the Transformer branch and CNN branch, respectively, forming a parallel dual-encoder structure for the extraction of both global and local features. Furthermore, a feature interaction module is designed to achieve information exchange, and complementary advantages of features, between the two branches. Secondly, for the decoder part, we propose a cross-scale multi-source feature fusion module to replace the original UNet decoder block, to aggregate multi-scale semantic features more effectively. In addition, a sea–land segmentation dataset covering the Yellow Sea region (GF Dataset) is constructed through the processing of three scenes from Gaofen-6 remote sensing images. We perform a comprehensive experiment with the GF dataset to compare the proposed method with mainstream semantic segmentation models, and the results demonstrate that TCU-Net outperforms the competing models in all three evaluation indices: the PA (pixel accuracy), F1-score, and MIoU (mean intersection over union), while requiring significantly fewer parameters and computational resources compared to other models. These results indicate that the TCU-Net model proposed in this article can extract the shoreline from remote sensing images more effectively, with a shorter time, and lower computational overhead.

SNOWED: Automatically Constructed Dataset of Satellite Imagery for Water Edge Measurements.

Monitoring the shoreline over time is essential to quickly identify and mitigate environmental issues such as coastal erosion. Monitoring using satellite images has two great advantages, i.e., global coverage and frequent measurement updates; but adequate methods are needed to extract shoreline information from such images. To this purpose, there are valuable non-supervised methods, but more recent research has concentrated on deep learning because of its greater potential in terms of generality, flexibility, and measurement accuracy, which, in contrast, derive from the information contained in large datasets of labeled samples. The first problem to solve, therefore, lies in obtaining large datasets suitable for this specific measurement problem, and this is a difficult task, typically requiring human analysis of a large number of images. In this article, we propose a technique to automatically create a dataset of labeled satellite images suitable for training machine learning models for shoreline detection. The method is based on the integration of data from satellite photos and data from certified, publicly accessible shoreline data. It involves several automatic processing steps, aimed at building the best possible dataset, with images including both sea and land regions, and correct labeling also in the presence of complicated water edges (which can be open or closed curves). The use of independently certified measurements for labeling the satellite images avoids the great work required to manually annotate them by visual inspection, as is done in other works in the literature. This is especially true when convoluted shorelines are considered. In addition, possible errors due to the subjective interpretation of satellite images are also eliminated. The method is developed and used specifically to build a new dataset of Sentinel-2 images, denoted SNOWED; but is applicable to different satellite images with trivial modifications. The accuracy of labels in SNOWED is directly determined by the uncertainty of the shoreline data used, which leads to sub-pixel errors in most cases. Furthermore, the quality of the SNOWED dataset is assessed through the visual comparison of a random sample of images and their corresponding labels, and its functionality is shown by training a neural model for sea-land segmentation.

Assessing Urban Flooding Extent of the Baunia Khal Watershed in Dhaka, Bangladesh

Due to the gradual encroachment of natural drainage channels (also known as khals) and the poor management of drainage infrastructures, any rainfall of higher intensity for a few hours causes urban flooding in Dhaka, Bangladesh, hindering the daily lives of city dwellers, especially in slum areas. The Intensity–Duration–Frequency (IDF) curves with return intervals of 2, 5, 10, 25, 50, and 100 years were estimated for a 3 h duration of rainfall using the Gumbel statistical method to assess urban flooding extent around the Baganbari slum within the Baunia Khal watershed. The spatial land use changes of the Baunia Khal were also delineated through the analysis of the areal changes of the khal from 2004 to 2020. The area of the khal was found to be 7.00 km2, 2.17 km2 and 0.41 km2 for the years 2004, 2010, and 2020, respectively. It appears that a gradual massive areal decrease of the khal (impervious land segment) was in progress during this period for high encroachments driven by various governmental agencies and other private entities’ urban developmental projects. The runoff coefficient was computed as 0.76 based on the existing land use pattern, slope, and soil type of the study area. The average runoff generated from the catchment was estimated using the rational method and was 103.41 m3/hr. The drainage length was calculated as 9.1 km using the Kirpich method, whereas the present drainage length was reported as only 6.95 km. The multiple rainfall intensities with return periods of 2, 5, 10, 25, 50, and 100 years were also applied to replicate a heightened extent of urban flooding in the Baunia Khal watershed. The study suggests that the depth, length and width of the Baunia Khal need to increase to hold the generated runoff to manage urban flooding around the Baunia Khal watershed.

Water–Land Segmentation via Structure-Aware CNN–Transformer Network on Large-Scale SAR Data

Water–land segmentation has important applications in many aspects, such as environmental protection and flood prevention. Synthetic aperture radar (SAR) is one of the important tools for watershed monitoring. However, neither the traditional SAR water–land segmentation methods nor convolutional neural network (CNN)-based algorithms have satisfactory accuracy for the boundaries of water, especially for fine rivers/lakes. Transformer can effectively extract global information and has achieved amazing success in image interpretation. In this article, a structure-aware CNN–Transformer network with U-shaped structure is designed to solve the water segmentation problem, named Trans-SANet. Also, an edge refinement postprocessing module is added to Trans-SANet to refine the water edges, named Trans-SANet+. First, a cascaded attentional upsampler (CAUP) is designed in the decoder to combine spatial and temporal attentional serialization to fully capture feature information and avoid feature omission. Second, a structure-aware loss (SA-Loss) function is designed to give sufficient attention to the overall boundary structure while avoiding the loss of small-scale features to reduce the segmentation error of the boundary, thus improving the segmentation accuracy of the fine water region. Finally, combining fully connected conditional random field (CRF) with edge extraction, a postprocessing module is proposed to further optimize the results of water–land segmentation. Experiments on three SAR datasets show that Trans-SANet+ outperforms several most advanced depth segmentation networks in terms of accuracy and speed.

DWin-HRFormer: A High-Resolution Transformer Model With Directional Windows for Semantic Segmentation of Urban Construction Land

In this paper, a deep neural network for semantic segmentation of high-resolution remote sensing images is proposed for urban construction land classification. The network follows a high-resolution network architecture. Specifically, a directional self-attention on the paths of different resolutions is proposed, aiming to correct the directional bias caused by the attention of strip windows during the model learning, while also reducing the computational complexity, and allowing the model to improve both the accuracy and speed. At the end of the network, a distributed alignment module with spatial information is constructed to train additional learnable parameters, to adjust the biased decision boundaries through a two-stage learning strategy, and alleviate the problem of accuracy degradation due to the unbalanced training data. We tested the proposed method and compared it with the current state-of-the-art semantic segmentation methods on the Luojia-FGLC and WHDLD datasets, and the proposed one obtained the best performance. We also verified the effectiveness of each component of the network through ablation experiments. The code and model will be available at https://github.com/Zhzhyd/DWin-HRFormer.

Sea–Land Segmentation Algorithm Based on Multiframe Radar Echoes

Sea–Land Segmentation Algorithm Based on Multiframe Radar Echoes