Search

The coastline of Zhanjiang Bay has undergone profound changes under the combined action of natural and human factors, making the rational protection and utilization of coastal resources a research hotspot. As a typical tropical bay in China, analyzing the coastline changes in Zhanjiang Bay can provide basic data to support the development and utilization of coastal zones. In this study, 42 optical satellite images from 1973 to 2023 were used in conjunction with the random forest method to extract the shoreline, analyze the spatiotemporal evolution of the Zhanjiang Bay coastline, and investigate its driving factors. Additionally, shoreline complexity changes were explored, and Gross Domestic Product (GDP) was introduced for the correlation analysis of shoreline indicators. The results showed that the total length of the Zhanjiang Bay coastline increased by 103.13 km over the past 50 years. Coastline changes are influenced by both natural and anthropogenic factors, with anthropogenic factors having the most significant impact. Natural factors include erosion caused by storm surges, sea level rise, and dynamic coastal conditions. Anthropogenic factors include construction of coastal aquaculture farms, land reclamation, coastal engineering projects, coastal infrastructure development, and industrial land development. The main areas of change were concentrated along the main channel and the Nansan Waterway. The proportions of shoreline segments expanding seaward on the east and west coasts were 51.4% and 71.6%, respectively, whereas the landward erosion shoreline segment on Donghai Island was 58.0%. Specifically, the southeastern section of the east coast experienced massive shoreline expansion. Coastal engineering along the west coast, southeastern village, and town construction projects on the east coast resulted in shoreline advancement of more than 2 km seaward. Erosion was observed at the western end of the coastline, across several estuaries from the west coast, and along the shoreline of the Nansan Channel on the south side of the east coast, with the most severe shoreline erosion occurring at the end of the west coast shoreline, where the average setback was 1 km, with a maximum setback of nearly 1.8 km. Except for the 2010s, the change in the intensity of the coastline of Zhanjiang Bay was positive. The fractal dimension of the coastline increased from 1.086 to 1.124, consistent with the trend in its length. The primary driver of coastline expansion was large-scale land reclamation on the western bank of Zhanjiang Bay, southwestern bank of the eastern bank, and northern part of Donghai Island, with a total reclaimed area of 82.82 km2. The proportion of the reclaimed area after 2010 reached 57.5%, the area of coastal aquaculture farms increased by 26.98 km2 over the past 30 years. Large-scale erosion occurred on the eastern and southern sides of Donghai Island. In addition, the fractal dimension and length of the Zhanjiang Bay coastline were strongly negatively correlated with the inverse of the GDP of Zhanjiang, with correlation coefficients of -0.96 and -0.99, respectively. These findings suggests that the economic benefits of shoreline shifting can be quantified using shoreline indicators, whereas differences in shoreline indices between different harbors affect the relevance of the economic benefits. Owing to the narrow and long topographic structure of Zhanjiang Bay, there is a delay in tidal signal propagation from the bay mouth to the interior. Therefore, when exploring the water margins obtained from optical remote sensing images, the water level information of the corresponding region must be utilized to correct the tidal variations in Zhanjiang Bay. Based on this, numerical models will be used in the future to obtain tidal data for each region and the corresponding water margins. [ABSTRACT FROM AUTHOR]

The contamination of marine ecosystems by oil spills poses a significant threat to the marine environment, necessitating the prompt and effective implementation of measures to mitigate the associated damage. Satellites offer a spatial and temporal advantage over aircraft and unmanned aerial vehicles (UAVs) in oil spill detection due to their wide-area monitoring capabilities. While oil spill detection has traditionally relied on synthetic aperture radar (SAR) images, the combined use of optical satellite sensors alongside SAR can significantly enhance monitoring capabilities, providing improved spatial and temporal coverage. The advent of deep learning methodologies, particularly convolutional neural networks (CNNs) and Transformer models, has generated considerable interest in their potential for oil spill detection. In this study, we conducted a comprehensive and objective comparison to evaluate the suitability of CNN and Transformer models for marine oil spill detection. High-resolution optical satellite images were used to optimize DeepLabV3+, a widely utilized CNN model; Swin-UPerNet, a representative Transformer model; and Mask2Former, which employs a Transformer-based architecture for both encoding and decoding. The results of cross-validation demonstrate a mean Intersection over Union (mIoU) of 0.740, 0.840 and 0.804 for all the models, respectively, indicating their potential for detecting oil spills in the ocean. Additionally, we performed a histogram analysis on the predicted oil spill pixels, which allowed us to classify the types of oil. These findings highlight the considerable promise of the Swin Transformer models for oil spill detection in the context of future marine disaster monitoring. [ABSTRACT FROM AUTHOR]

Featured Application: coastal change analysis, coastal land cover/land use analysis, coastal bio-environment analysis, human–nature interaction on coastal land use. Coastal land use represents the combination of various land cover forms in a coastal area, which helps us understand the historical events, current conditions, and future progress of a coastal area. Currently, the emergence of high-resolution optical satellite images significantly extends the scope of coastal land cover recognition, and deep learning models provide a significant possibility of extracting high-level abstract features from an optical satellite image to characterize complicated coastal land covers. However, recognition systems for labeling are always defined differently for specific departments, organizations, and institutes. Moreover, considering the complexity of coastal land uses, it is impossible to create a benchmark dataset that fully covers all types of coastal land uses. To improve the transferability of high-level features generated by deep learning to reduce the burden of creating a massive amount of labeled data, this paper proposes an integrated framework to support semantically enriched coastal land use recognition, including foundation model-powered multi-label coastal land cover classification and conversion from coastal land cover mapping into coastal land use semantics with a vector space model (VSM). The experimental results prove that the proposed method outperformed the state-of-the-art deep learning approaches in complex coastal land use recognition. [ABSTRACT FROM AUTHOR]

The coastline of Zhanjiang Bay has undergone profound changes under the combined action of natural and human factors, making the rational protection and utilization of coastal resources a research hotspot. As a typical tropical bay in China, analyzing the coastline changes in Zhanjiang Bay can provide basic data to support the development and utilization of coastal zones. In this study, 42 optical satellite images from 1973 to 2023 were used in conjunction with the random forest method to extract the shoreline, analyze the spatiotemporal evolution of the Zhanjiang Bay coastline, and investigate its driving factors. Additionally, shoreline complexity changes were explored, and Gross Domestic Product (GDP) was introduced for the correlation analysis of shoreline indicators. The results showed that the total length of the Zhanjiang Bay coastline increased by 103.13 km over the past 50 years. Coastline changes are influenced by both natural and anthropogenic factors, with anthropogenic factors having the most significant impact. Natural factors include erosion caused by storm surges, sea level rise, and dynamic coastal conditions. Anthropogenic factors include construction of coastal aquaculture farms, land reclamation, coastal engineering projects, coastal infrastructure development, and industrial land development. The main areas of change were concentrated along the main channel and the Nansan Waterway. The proportions of shoreline segments expanding seaward on the east and west coasts were 51.4% and 71.6%, respectively, whereas the landward erosion shoreline segment on Donghai Island was 58.0%. Specifically, the southeastern section of the east coast experienced massive shoreline expansion. Coastal engineering along the west coast, southeastern village, and town construction projects on the east coast resulted in shoreline advancement of more than 2 km seaward. Erosion was observed at the western end of the coastline, across several estuaries from the west coast, and along the shoreline of the Nansan Channel on the south side of the east coast, with the most severe shoreline erosion occurring at the end of the west coast shoreline, where the average setback was 1 km, with a maximum setback of nearly 1.8 km. Except for the 2010s, the change in the intensity of the coastline of Zhanjiang Bay was positive. The fractal dimension of the coastline increased from 1.086 to 1.124, consistent with the trend in its length. The primary driver of coastline expansion was large-scale land reclamation on the western bank of Zhanjiang Bay, southwestern bank of the eastern bank, and northern part of Donghai Island, with a total reclaimed area of 82.82 km2. The proportion of the reclaimed area after 2010 reached 57.5%, the area of coastal aquaculture farms increased by 26.98 km2 over the past 30 years. Large-scale erosion occurred on the eastern and southern sides of Donghai Island. In addition, the fractal dimension and length of the Zhanjiang Bay coastline were strongly negatively correlated with the inverse of the GDP of Zhanjiang, with correlation coefficients of -0.96 and -0.99, respectively. These findings suggests that the economic benefits of shoreline shifting can be quantified using shoreline indicators, whereas differences in shoreline indices between different harbors affect the relevance of the economic benefits. Owing to the narrow and long topographic structure of Zhanjiang Bay, there is a delay in tidal signal propagation from the bay mouth to the interior. Therefore, when exploring the water margins obtained from optical remote sensing images, the water level information of the corresponding region must be utilized to correct the tidal variations in Zhanjiang Bay. Based on this, numerical models will be used in the future to obtain tidal data for each region and the corresponding water margins.

Electric pylons are crucial components of power infrastructure, requiring accurate detection and identification for effective monitoring of transmission lines. This paper proposes an innovative model, the EP-YOLOv8 network, which incorporates new modules: the DSLSK-SPPF and EMS-Head. The DSLSK-SPPF module is designed to capture the surrounding features of electric pylons more effectively, enhancing the model's adaptability to the complex shapes of these structures. The EMS-Head module enhances the model's ability to capture fine details of electric pylons while maintaining a lightweight design. The EP-YOLOv8 network optimizes traditional YOLOv8n parameters, demonstrating a significant improvement in electric pylon detection accuracy with an average mAP@0.5 value of 95.5%. The effective detection of electric pylons by the EP-YOLOv8 demonstrates its ability to overcome the inefficiencies inherent in existing optical satellite image-based models, particularly those related to the unique characteristics of electric pylons. This improvement will significantly aid in monitoring the operational status and layout of power infrastructure, providing crucial insights for infrastructure management and maintenance. [ABSTRACT FROM AUTHOR]

Optical satellite images frequently suffer from thin clouds, degrading the data quality. A thin cloud correction method is developed based on complementary dark objects on multiple visible bands to address this problem. First, thin cloud images are divided into irregular subareas using the superpixel segmentation algorithm, enabling the proper identification of dark objects in the spatial domain across different visible bands. A criterion is then established to classify the dark objects into two types, namely, absolute dark objects (ADOs) and relative dark objects (RDOs). Subsequently, the quantitative correlation of thin clouds between visible bands is estimated by adopting the ADOs. Dark objects present complementarity in visible bands; thus, the RDOs on one band are spatially densified by referencing the RDOs on the other visible bands. Thereby, a thin cloud map with fine spatial details is interpolated by using all the ADOs and RDOs on a band, and the correction procedure is performed through subtraction. Eight visible data captured by Landsat platforms are collected for simulated and real experiments to evaluate the method's performance. Three representative thin cloud correction approaches are selected for visual and quantitative comparisons. The proposed method can correct thin clouds effectively and restore various scenes accurately. The interpolated thin cloud maps show enhanced texture details and finer representation compared with the benchmarks. In addition, the advantages of dark-object densification for thin cloud map generation and the limitations of the proposed method are investigated.

The contamination of marine ecosystems by oil spills poses a significant threat to the marine environment, necessitating the prompt and effective implementation of measures to mitigate the associated damage. Satellites offer a spatial and temporal advantage over aircraft and unmanned aerial vehicles (UAVs) in oil spill detection due to their wide-area monitoring capabilities. While oil spill detection has traditionally relied on synthetic aperture radar (SAR) images, the combined use of optical satellite sensors alongside SAR can significantly enhance monitoring capabilities, providing improved spatial and temporal coverage. The advent of deep learning methodologies, particularly convolutional neural networks (CNNs) and Transformer models, has generated considerable interest in their potential for oil spill detection. In this study, we conducted a comprehensive and objective comparison to evaluate the suitability of CNN and Transformer models for marine oil spill detection. High-resolution optical satellite images were used to optimize DeepLabV3+, a widely utilized CNN model; Swin-UPerNet, a representative Transformer model; and Mask2Former, which employs a Transformer-based architecture for both encoding and decoding. The results of cross-validation demonstrate a mean Intersection over Union (mIoU) of 0.740, 0.840 and 0.804 for all the models, respectively, indicating their potential for detecting oil spills in the ocean. Additionally, we performed a histogram analysis on the predicted oil spill pixels, which allowed us to classify the types of oil. These findings highlight the considerable promise of the Swin Transformer models for oil spill detection in the context of future marine disaster monitoring.

Coastal land use represents the combination of various land cover forms in a coastal area, which helps us understand the historical events, current conditions, and future progress of a coastal area. Currently, the emergence of high-resolution optical satellite images significantly extends the scope of coastal land cover recognition, and deep learning models provide a significant possibility of extracting high-level abstract features from an optical satellite image to characterize complicated coastal land covers. However, recognition systems for labeling are always defined differently for specific departments, organizations, and institutes. Moreover, considering the complexity of coastal land uses, it is impossible to create a benchmark dataset that fully covers all types of coastal land uses. To improve the transferability of high-level features generated by deep learning to reduce the burden of creating a massive amount of labeled data, this paper proposes an integrated framework to support semantically enriched coastal land use recognition, including foundation model-powered multi-label coastal land cover classification and conversion from coastal land cover mapping into coastal land use semantics with a vector space model (VSM). The experimental results prove that the proposed method outperformed the state-of-the-art deep learning approaches in complex coastal land use recognition.

The classification of ship images has become a significant area of research within the remote sensing community due to its potential applications in maritime security, traffic monitoring, and environmental protection. Traditional monitoring methods like the Automated Identification System (AIS) and the Constant False Alarm Rate (CFAR) have their limitations, such as challenges with sea clutter and the problem of ships turning off their transponders. Additionally, classifying ship images in remote sensing is a complex task due to the spatial arrangement of geospatial objects, complex backgrounds, and the resolution limitations of sensor platforms. To address these challenges, this paper introduces a novel approach that leverages a unique dataset termed Heterogeneous Ship data and a new technique called the Spatial–Channel Attention with Bilinear Pooling Network (SCABPNet). First, we introduce the Heterogeneous Ship data, which combines Synthetic Aperture Radar (SAR) and optical satellite imagery, to leverage the complementary features of the SAR and optical modalities, thereby providing a richer and more-diverse set of features for ship classification. Second, we designed a custom layer, called the Spatial–Channel Attention with Bilinear Pooling (SCABP) layer. This layer sequentially applies the spatial attention, channel attention, and bilinear pooling techniques to enhance the feature representation by focusing on extracting informative and discriminative features from input feature maps, then classify them. Finally, we integrated the SCABP layer into a deep neural network to create a novel model named the SCABPNet model, which is used to classify images in the proposed Heterogeneous Ship data. Our experiments showed that the SCABPNet model demonstrated superior performance, surpassing the results of several state-of-the-art deep learning models. SCABPNet achieved an accuracy of 97.67% on the proposed Heterogeneous Ship dataset during testing. This performance underscores SCABPNet's capability to focus on ship-specific features while suppressing background noise and feature redundancy. We invite researchers to explore and build upon our work. [ABSTRACT FROM AUTHOR]

Electric pylons are crucial components of power infrastructure, requiring accurate detection and identification for effective monitoring of transmission lines. This paper proposes an innovative model, the EP-YOLOv8 network, which incorporates new modules: the DSLSK-SPPF and EMS-Head. The DSLSK-SPPF module is designed to capture the surrounding features of electric pylons more effectively, enhancing the model’s adaptability to the complex shapes of these structures. The EMS-Head module enhances the model’s ability to capture fine details of electric pylons while maintaining a lightweight design. The EP-YOLOv8 network optimizes traditional YOLOv8n parameters, demonstrating a significant improvement in electric pylon detection accuracy with an average mAP@0.5 value of 95.5%. The effective detection of electric pylons by the EP-YOLOv8 demonstrates its ability to overcome the inefficiencies inherent in existing optical satellite image-based models, particularly those related to the unique characteristics of electric pylons. This improvement will significantly aid in monitoring the operational status and layout of power infrastructure, providing crucial insights for infrastructure management and maintenance.

Optical remote sensing ship target detection has become an essential means of ocean supervision, coastal defense, and frontier defense. Accurate, effective, fast, and real-time remote sensing data processing is the critical technology in this field. This paper proposes a real-time detection algorithm for moving targets in low-resolution wide-area remote sensing images, which includes four steps: pre-screening, simplified HOG feature identification, sequence correlation identification, and facilitated Yolo identification. It can effectively detect and track targets in low-resolution sequence data. Firstly, iterative morphological processing was used to improve the contrast of low-resolution ship target profile edge features compared with the sea surface background. Next, the target area after adaptive segmentation was used to eliminate false alarms. As a result, the invalid background information of extensive comprehensive data was quickly eliminated. Then, support vector machine classification of S-HOG feature was carried out for suspected targets, and interference such as islands and reefs, broken clouds, and waves were eliminated according to the shape characteristics of ship targets. The method of multi-frame data association and searching for adjacent target information between frames was adopted to eliminate the interference of static targets and broken clouds with similar contours. Finally, the sequential marks were further trained and learned, and further false alarm elimination was completed based on the clipped Yolo network. Compared with the traditional Yolo Tiny V2/V3 series network, this method had higher computational speed and better detection performance. The F1 number of detection results was increased by 3%, and the calculation time was reduced by 66%. [ABSTRACT FROM AUTHOR]

The classification of ship images has become a significant area of research within the remote sensing community due to its potential applications in maritime security, traffic monitoring, and environmental protection. Traditional monitoring methods like the Automated Identification System (AIS) and the Constant False Alarm Rate (CFAR) have their limitations, such as challenges with sea clutter and the problem of ships turning off their transponders. Additionally, classifying ship images in remote sensing is a complex task due to the spatial arrangement of geospatial objects, complex backgrounds, and the resolution limitations of sensor platforms. To address these challenges, this paper introduces a novel approach that leverages a unique dataset termed Heterogeneous Ship data and a new technique called the Spatial–Channel Attention with Bilinear Pooling Network (SCABPNet). First, we introduce the Heterogeneous Ship data, which combines Synthetic Aperture Radar (SAR) and optical satellite imagery, to leverage the complementary features of the SAR and optical modalities, thereby providing a richer and more-diverse set of features for ship classification. Second, we designed a custom layer, called the Spatial–Channel Attention with Bilinear Pooling (SCABP) layer. This layer sequentially applies the spatial attention, channel attention, and bilinear pooling techniques to enhance the feature representation by focusing on extracting informative and discriminative features from input feature maps, then classify them. Finally, we integrated the SCABP layer into a deep neural network to create a novel model named the SCABPNet model, which is used to classify images in the proposed Heterogeneous Ship data. Our experiments showed that the SCABPNet model demonstrated superior performance, surpassing the results of several state-of-the-art deep learning models. SCABPNet achieved an accuracy of 97.67% on the proposed Heterogeneous Ship dataset during testing. This performance underscores SCABPNet’s capability to focus on ship-specific features while suppressing background noise and feature redundancy. We invite researchers to explore and build upon our work.

The classification of maritime boats and ship targets using optical satellite imagery is a challenging subject. This research introduces a unique and rich ship dataset named Very High-Resolution Ships (VHRShips) from Google Earth images, which includes diverse ship types, different ship sizes, several inshore locations, and different data acquisition conditions to improve the scalability of ship detection and mapping applications. In addition, we proposed a deep learning-based multi-stage approach for ship type classification from very high resolution satellite images to evaluate the performance of the VHRShips dataset. Our "Hierarchical Design (HieD)" approach is an end-to-end structure that allows the optimization of the Detection, Localization, Recognition, and Identification (DLRI) stages, independently. We focused on sixteen parent ship classes for the DLR stages, and specifically considered eight child classes of the navy parent class at the identification stage. We used the Xception network in the DRI stages and implemented YOLOv4 for the localization stage. Individual optimization of each stage resulted in F1 scores of 99.17%, 94.20%, 84.08%, and 82.13% for detection, recognition, localization, and identification, respectively. The end-to-end implementation of our proposed approach resulted in F1 scores of 99.17%, 93.43%, 74.00%, and 57.05% for the same order. In comparison, end-to-end YOLOv4 yielded F1-scores of 99.17%, 86.59%, 68.87%, and 56.28% for DLRI, respectively. We achieved higher performance with HieD than YOLOv4 for localization, recognition, and identification stages, indicating the usability of the VHRShips dataset in different detection and classification models. In addition, the proposed method and dataset can be used as a benchmark for further studies to apply deep learning on large-scale geodata to boost GeoAI applications in the maritime domain. [ABSTRACT FROM AUTHOR]

The existing slender target detection methods based on optical satellite images are greatly affected by the satellite perspective and the solar perspective. Due to limited data sources, it is difficult to implement a fully data-driven approach. This work introduces the imaging parameters of optical satellite images, which greatly reduces the influence of the satellite perspectives and the solar perspectives, and reduces the demand for the amount of data. We improve the oriented bounding box (OBB) detector based on faster R-CNN (region convolutional neural networks) and propose an imaging parameters-considered detector (IPC-Det) which is more suitable for our task. Specifically, in the first stage, the umbra and the shadow are extracted by horizontal bounding box (HBB), respectively, and then the matching of the umbra and the shadow is realized according to the imaging parameters. In the second stage, the paired umbra and shadow features are used to complete the classification and regression, and the target is obtained by OBB. In experiments, after introducing imaging parameters, our detection accuracy is improved by 3.9% (up to 87.5%), proving that this work is a successful attempt to introduce imaging parameters for slender target detection. [ABSTRACT FROM AUTHOR]

The complexity of changeable marine backgrounds makes ship detection from satellite remote sensing images a challenging task. The ubiquitous interference of cloud and fog led to missed detection and false-alarms when using imagery-based optical satellite remote sensing. An off-shore ship detection method with scene classification and a saliency-tuned YOLONet is proposed to solve this problem. First, the image blocks are classified into four categories by a density peak clustering algorithm (DPC) according to their grayscale histograms, i.e., cloudless areas, thin cloud areas, scattered clouds areas, and thick cloud areas. Secondly, since the ships can be regarded as salient objects in a marine background, the spectral residue saliency detection method is used to extract prominent targets from different image blocks. Finally, the saliency tuned YOLOv4 network is designed to quickly and accurately detect ships from different marine backgrounds. We validated the proposed method using more than 2000 optical remote sensing images from the GF-1 satellite. The experimental results demonstrated that the proposed method obtained a better detection performance than other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Optical remote sensing ship target detection has become an essential means of ocean supervision, coastal defense, and frontier defense. Accurate, effective, fast, and real-time remote sensing data processing is the critical technology in this field. This paper proposes a real-time detection algorithm for moving targets in low-resolution wide-area remote sensing images, which includes four steps: pre-screening, simplified HOG feature identification, sequence correlation identification, and facilitated Yolo identification. It can effectively detect and track targets in low-resolution sequence data. Firstly, iterative morphological processing was used to improve the contrast of low-resolution ship target profile edge features compared with the sea surface background. Next, the target area after adaptive segmentation was used to eliminate false alarms. As a result, the invalid background information of extensive comprehensive data was quickly eliminated. Then, support vector machine classification of S-HOG feature was carried out for suspected targets, and interference such as islands and reefs, broken clouds, and waves were eliminated according to the shape characteristics of ship targets. The method of multi-frame data association and searching for adjacent target information between frames was adopted to eliminate the interference of static targets and broken clouds with similar contours. Finally, the sequential marks were further trained and learned, and further false alarm elimination was completed based on the clipped Yolo network. Compared with the traditional Yolo Tiny V2/V3 series network, this method had higher computational speed and better detection performance. The F1 number of detection results was increased by 3%, and the calculation time was reduced by 66%.

The classification of maritime boats and ship targets using optical satellite imagery is a challenging subject. This research introduces a unique and rich ship dataset named Very High-Resolution Ships (VHRShips) from Google Earth images, which includes diverse ship types, different ship sizes, several inshore locations, and different data acquisition conditions to improve the scalability of ship detection and mapping applications. In addition, we proposed a deep learning-based multi-stage approach for ship type classification from very high resolution satellite images to evaluate the performance of the VHRShips dataset. Our “Hierarchical Design (HieD)” approach is an end-to-end structure that allows the optimization of the Detection, Localization, Recognition, and Identification (DLRI) stages, independently. We focused on sixteen parent ship classes for the DLR stages, and specifically considered eight child classes of the navy parent class at the identification stage. We used the Xception network in the DRI stages and implemented YOLOv4 for the localization stage. Individual optimization of each stage resulted in F1 scores of 99.17%, 94.20%, 84.08%, and 82.13% for detection, recognition, localization, and identification, respectively. The end-to-end implementation of our proposed approach resulted in F1 scores of 99.17%, 93.43%, 74.00%, and 57.05% for the same order. In comparison, end-to-end YOLOv4 yielded F1-scores of 99.17%, 86.59%, 68.87%, and 56.28% for DLRI, respectively. We achieved higher performance with HieD than YOLOv4 for localization, recognition, and identification stages, indicating the usability of the VHRShips dataset in different detection and classification models. In addition, the proposed method and dataset can be used as a benchmark for further studies to apply deep learning on large-scale geodata to boost GeoAI applications in the maritime domain.

The complexity of changeable marine backgrounds makes ship detection from satellite remote sensing images a challenging task. The ubiquitous interference of cloud and fog led to missed detection and false-alarms when using imagery-based optical satellite remote sensing. An off-shore ship detection method with scene classification and a saliency-tuned YOLONet is proposed to solve this problem. First, the image blocks are classified into four categories by a density peak clustering algorithm (DPC) according to their grayscale histograms, i.e., cloudless areas, thin cloud areas, scattered clouds areas, and thick cloud areas. Secondly, since the ships can be regarded as salient objects in a marine background, the spectral residue saliency detection method is used to extract prominent targets from different image blocks. Finally, the saliency tuned YOLOv4 network is designed to quickly and accurately detect ships from different marine backgrounds. We validated the proposed method using more than 2000 optical remote sensing images from the GF-1 satellite. The experimental results demonstrated that the proposed method obtained a better detection performance than other state-of-the-art methods.

The existing slender target detection methods based on optical satellite images are greatly affected by the satellite perspective and the solar perspective. Due to limited data sources, it is difficult to implement a fully data-driven approach. This work introduces the imaging parameters of optical satellite images, which greatly reduces the influence of the satellite perspectives and the solar perspectives, and reduces the demand for the amount of data. We improve the oriented bounding box (OBB) detector based on faster R-CNN (region convolutional neural networks) and propose an imaging parameters-considered detector (IPC-Det) which is more suitable for our task. Specifically, in the first stage, the umbra and the shadow are extracted by horizontal bounding box (HBB), respectively, and then the matching of the umbra and the shadow is realized according to the imaging parameters. In the second stage, the paired umbra and shadow features are used to complete the classification and regression, and the target is obtained by OBB. In experiments, after introducing imaging parameters, our detection accuracy is improved by 3.9% (up to 87.5%), proving that this work is a successful attempt to introduce imaging parameters for slender target detection.

Object detection has made great progress. However, due to the unique imaging method of optical satellite remote sensing, the detection of slender targets is still insufficient. Specifically, the perspective of optical satellites is small, and the characteristics of slender targets are severely lost during imaging, resulting in insufficient detection task information; at the same time, the appearance of slender targets in the image is greatly affected by the satellite perspective, which is likely to cause insufficient generalization capabilities of conventional detection models. In response to these two points, we have made some improvements. First, in this paper, we introduce the shadow as auxiliary information to complement the trunk features of the target lost in imaging. Second, to reduce the impact of satellite perspective on imaging, in this paper, we use the characteristic that shadow information is not affected by satellite perspective to design STC-Det. STC-Det treats the shadow and the target as two different types of targets and uses the shadow information to assist the detection, reducing the impact of the satellite perspective on detection. Among them, in order to improve the performance of STC-Det, we propose an automatic matching method (AMM) of shadow and target and a feature fusion method (FFM). Finally, this paper proposes a new method to calculate the heatmaps of detectors, which verifies the effectiveness of the proposed network in a visual way. Experiments show that when the satellite perspective is variable, the precision of STC-Det is increased by 1.7%, and when the satellite perspective is small, the precision of STC-Det is increased by 5.2%.

The retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models.

We present a characterization, comparison and analysis of in-situ spectral reflectance of Sago and other palms (coconut, oil palm and nipa) to ascertain on which part of the electromagnetic spectrum these palms are distinguishable from each other. The analysis also aims to reveal information that will assist in selecting which band to use when mapping Sago palms using the images acquired by these sensors. The datasets used in the analysis consisted of averaged spectral reflectance curves of each palm species measured within the 345 - 1045 nm wavelength range using an Ocean Optics USB4000-VIS-NIR Miniature Fiber Optic Spectrometer. This in-situ reflectance data was also resampled to match the spectral response of the 4 bands of ALOS AVNIR-2, 3 bands of ASTER VNIR, 4 bands of Landsat 7 ETM+, 5 bands of Landsat 8, and 8 bands of Worldview-2 (WV2). Examination of the spectral reflectance curves showed that the near infra-red region, specifically at 770, 800 and 875 nm, provides the best wavelengths where Sago palms can be distinguished from other palms. The resampling of the in-situ reflectance spectra to match the spectral response of optical sensors made possible the analysis of the differences in reflectance values of Sago and other palms in different bands of the sensors. Overall, the knowledge learned from the analysis can be useful in the actual analysis of optical satellite images, specifically in determining which band to include or to exclude, or whether to use all bands of a sensor in discriminating and mapping Sago palms. [ABSTRACT FROM AUTHOR]

After a large-scale disaster, many damaged buildings are demolished and treated as disaster waste. Though the weight of disaster waste was estimated two months after the 2016 earthquake in Kumamoto, Japan, the estimated weight was significantly different from the result when the disaster waste disposal was completed in March 2018. The amount of disaster waste generated is able to be estimated by an equation by multiplying the total number of severely damaged and partially damaged buildings by the coefficient of generated weight per building. We suppose that the amount of disaster waste would be affected by the conditions of demolished buildings, namely, the areas and typologies of building structures, but this has not yet been clarified. Therefore, in this study, we aimed to use geographic information system (GIS) map data to create a time series GIS map dataset with labels of demolished and remaining buildings in Mashiki town for the two-year period prior to the completion of the disaster waste disposal. We used OpenStreetMap (OSM) data as the base data and time series SPOT images observed in the two years following the Kumamoto earthquake to label all demolished and remaining buildings in the GIS map dataset. To effectively label the approximately 16,000 buildings in Mashiki town, we calculated an indicator that shows the possibility of the buildings to be classified as the remaining and demolished buildings from a change of brightness in SPOT images. We classified 5701 demolished buildings from 16,106 buildings, as of March 2018, by visual interpretation of the SPOT and Pleiades images with reference to this indicator. We verified that the number of demolished buildings was almost the same as the number reported by Mashiki municipality. Moreover, we assessed the accuracy of our proposed method: The F-measure was higher than 0.9 using the training dataset, which was verified by a field survey and visual interpretation, and included the labels of the 55 demolished and 55 remaining buildings. We also assessed the accuracy of the proposed method by applying it to all the labels in the OSM dataset, but the F-measure was 0.579. If we applied test data including balanced labels of the other 100 demolished and 100 remaining buildings, which were other than the training data, the F-measure was 0.790 calculated from the SPOT image of 25 March 2018. Our proposed method performed better for the balanced classification but not for imbalanced classification. We studied the examples of image characteristics of correct and incorrect estimation by thresholding the indicator.

In this paper, we present a novel method for ship detection in optical satellite image based on the ReedXiaoli (RX) method and the principal component analysis network (PCAnet). The proposed method consists of the following three steps. First, the spatially adjacent pixels in optical image are arranged into a vector, transforming the optical image into a 3D cube image. By taking this process, the contextual information of the spatially adjacent pixels can be integrated to magnify the discrimination between ship and background. Second, the RX anomaly detection method is adopted to preliminarily extract ship candidates from the produced 3D cube image. Finally, real ships are further confirmed among ship candidates by applying the PCAnet and the support vector machine (SVM). Specifically, the PCAnet is a simple deep learning network which is exploited to perform feature extraction, and the SVM is applied to achieve feature pooling and decision making. Experimental results demonstrate that our approach is effective in discriminating between ships and false alarms, and has a good ship detection performance. [ABSTRACT FROM AUTHOR]

Georeferencing is a mandatory issue at many applications where the satellite images are used. Georeferencing is based on a transformation between images and objects coordinate systems, and parametric, semi parametric and non-parametric mathematical models are preferred for this issue. A semi-parametric model, i.e. sensor-based RFM (Rational Functional Model) suggested by the OGC (Open Geospatial Consortium) is subjected in this paper. Some theoretical background about the general equation, the estimation of coefficients, the distortions carried and their removing, the simplification of RFMs thanks to the special characteristics of coefficients and also the various adjustment models will be presented at first. Then, the georeferencing accuracies of a mono IKONOS panchromatic image covering Zonguldak test field having an undulating and mountainous topography will be presented using 22 GCPs via a computation package called GeoFigcon derived in Matlab environment by the author. If a bias compensation is applied, the accuracies are when 1st degree RFM is preferred.

GPS and satellite images are used for determining displacements resulting from natural disasters such as earthquake and landslide. Satellite images, which are fast, effective and economic tools for revealing surface deformations and mass movements in such regions have commonly been used. A method was developed for determining horizontal displacements and mass movements resulting from large earthquakes, glacier flow, landslides, and sand dune migrations. This method, which is named as Co-Registration of Optically Sensed Images and Correlation (COSI-Corr), makes it possible to measure horizontal ground deformation from optical images in earthquake, glacier, landslide, and sand dune regions. In particular, its sub-pixel capabilities allow for accurate mapping of surface ruptures and measurement of co-seismic offsets. Although it has been commonly applied to earthquake, sand dune and glacier regions today, it has not been used sufficiently in landslide regions. Landslides, which have frequently been encountered in the world, cause loss of live and asset. It is highly important to reveal displacements and mass movements resulting from landslides. This study focuses on studies performed for landslide by COSI-Corr method and obtained results in the study area selected on the North Anatolian Fault Zone.

Road information has a fundamental role in modern society. Road extraction from optical satellite images is an economic and efficient way to obtain and update a transportation database. This paper presents an integrated method to extract urban main-road centerlines from satellite optical images. The proposed method has four main steps. First, general adaptive neighborhood is introduced to implement spectral-spatial classification to segment the images into two categories: road and nonroad groups. Second, road groups and homogeneous property, measured by local Geary's C, are fused to improve road-group accuracy. Third, road shape features are used to extract reliable road segments. Finally, local linear kernel smoothing regression is performed to extract smooth road centerlines. Road networks are then generated using tensor voting. The proposed method is tested and subsequently validated using a large set of multispectral high-resolution images. A comparison with several existing methods shows that the proposed method is more suitable for urban main-road centerline extraction. [ABSTRACT FROM PUBLISHER]

Georeferencing is a mandatory issue at many applications where the satellite images are used. Georeferencing is based on a transformation between images and objects coordinate systems, and parametric, semi parametric and non-parametric mathematical models are preferred for this issue. A semi-parametric model, i.e. sensor-based RFM (Rational Functional Model) suggested by the OGC (Open Geospatial Consortium) is subjected in this paper. Some theoretical background about the general equation, the estimation of coefficients, the distortions carried and their removing, the simplification of RFMs thanks to the special characteristics of coefficients and also the various adjustment models will be presented at first. Then, the georeferencing accuracies of a mono IKONOS panchromatic image covering Zonguldak test field having an undulating and mountainous topography will be presented using 22 GCPs via a computation package called GeoFigcon derived in Matlab environment by the author. If a bias compensation is applied, the accuracies are mx = ±0.4 pixel, my = ±0.5 pixel when 1st degree RFM is preferred. [ABSTRACT FROM AUTHOR]

GPS and satellite images are used for determining displacements resulting from natural disasters such as earthquake and landslide. Satellite images, which are fast, effective and economic tools for revealing surface deformations and mass movements in such regions have commonly been used. A method was developed for determining horizontal displacements and mass movements resulting from large earthquakes, glacier flow, landslides, and sand dune migrations. This method, which is named as Co- Registration of Optically Sensed Images and Correlation (COSI-Corr), makes it possible to measure horizontal ground deformation from optical images in earthquake, glacier, landslide, and sand dune regions. In particular, its sub-pixel capabilities allow for accurate mapping of surface ruptures and measurement of co-seismic offsets. Although it has been commonly applied to earthquake, sand dune and glacier regions today, it has not been used sufficiently in landslide regions. Landslides, which have frequently been encountered in the world, cause loss of live and asset. It is highly important to reveal displacements and mass movements resulting from landslides. This study focuses on studies performed for landslide by COSI-Corr method and obtained results in the study area selected on the North Anatolian Fault Zone. [ABSTRACT FROM AUTHOR]

Object detection has made great progress. However, due to the unique imaging method of optical satellite remote sensing, the detection of slender targets is still insufficient. Specifically, the perspective of optical satellites is small, and the characteristics of slender targets are severely lost during imaging, resulting in insufficient detection task information; at the same time, the appearance of slender targets in the image is greatly affected by the satellite perspective, which is likely to cause insufficient generalization capabilities of conventional detection models. In response to these two points, we have made some improvements. First, in this paper, we introduce the shadow as auxiliary information to complement the trunk features of the target lost in imaging. Second, to reduce the impact of satellite perspective on imaging, in this paper, we use the characteristic that shadow information is not affected by satellite perspective to design STC-Det. STC-Det treats the shadow and the target as two different types of targets and uses the shadow information to assist the detection, reducing the impact of the satellite perspective on detection. Among them, in order to improve the performance of STC-Det, we propose an automatic matching method (AMM) of shadow and target and a feature fusion method (FFM). Finally, this paper proposes a new method to calculate the heatmaps of detectors, which verifies the effectiveness of the proposed network in a visual way. Experiments show that when the satellite perspective is variable, the precision of STC-Det is increased by 1.7%, and when the satellite perspective is small, the precision of STC-Det is increased by 5.2%. [ABSTRACT FROM AUTHOR]

The retrieval of chlorophyll-a (Chl-a) concentrations relies on empirical or analytical analyses, which generally experience difficulties from the diversity of inland waters in statistical analyses and the complexity of radiative transfer equations in analytical analyses, respectively. Previous studies proposed the utilization of artificial neural networks (ANNs) to alleviate these problems. However, ANNs do not consider the problem of insufficient in situ samples during model training, and they do not fully utilize the spatial and spectral information of remote sensing images in neural networks. In this study, a two-stage training is introduced to address the problem regarding sample insufficiency. The neural network is pretrained using the samples derived from an existing Chl-a concentration model in the first stage, and the pretrained model is refined with in situ samples in the second stage. A novel convolutional neural network for Chl-a concentration retrieval called WaterNet is proposed which utilizes both spectral and spatial information of remote sensing images. In addition, an end-to-end structure that integrates feature extraction, band expansion, and Chl-a estimation into the neural network leads to an efficient and effective Chl-a concentration retrieval. In experiments, Sentinel-3 images with the same acquisition days of in situ measurements over Laguna Lake in the Philippines were used to train and evaluate WaterNet. The quantitative analyses show that the two-stage training is more likely than the one-stage training to reach the global optimum in the optimization, and WaterNet with two-stage training outperforms, in terms of estimation accuracy, related ANN-based and band-combination-based Chl-a concentration models. [ABSTRACT FROM AUTHOR]

After a large-scale disaster, many damaged buildings are demolished and treated as disaster waste. Though the weight of disaster waste was estimated two months after the 2016 earthquake in Kumamoto, Japan, the estimated weight was significantly different from the result when the disaster waste disposal was completed in March 2018. The amount of disaster waste generated is able to be estimated by an equation by multiplying the total number of severely damaged and partially damaged buildings by the coefficient of generated weight per building. We suppose that the amount of disaster waste would be affected by the conditions of demolished buildings, namely, the areas and typologies of building structures, but this has not yet been clarified. Therefore, in this study, we aimed to use geographic information system (GIS) map data to create a time series GIS map dataset with labels of demolished and remaining buildings in Mashiki town for the two-year period prior to the completion of the disaster waste disposal. We used OpenStreetMap (OSM) data as the base data and time series SPOT images observed in the two years following the Kumamoto earthquake to label all demolished and remaining buildings in the GIS map dataset. To effectively label the approximately 16,000 buildings in Mashiki town, we calculated an indicator that shows the possibility of the buildings to be classified as the remaining and demolished buildings from a change of brightness in SPOT images. We classified 5701 demolished buildings from 16,106 buildings, as of March 2018, by visual interpretation of the SPOT and Pleiades images with reference to this indicator. We verified that the number of demolished buildings was almost the same as the number reported by Mashiki municipality. Moreover, we assessed the accuracy of our proposed method: The F-measure was higher than 0.9 using the training dataset, which was verified by a field survey and visual interpretation, and included the labels of the 55 demolished and 55 remaining buildings. We also assessed the accuracy of the proposed method by applying it to all the labels in the OSM dataset, but the F-measure was 0.579. If we applied test data including balanced labels of the other 100 demolished and 100 remaining buildings, which were other than the training data, the F-measure was 0.790 calculated from the SPOT image of 25 March 2018. Our proposed method performed better for the balanced classification but not for imbalanced classification. We studied the examples of image characteristics of correct and incorrect estimation by thresholding the indicator. [ABSTRACT FROM AUTHOR]