Weakly Supervised Network with Scribble-Supervised and Edge-Mask for Road Extraction from High-Resolution Remote Sensing Images

Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.

Correg-Yolov3:a Method for Dense Buildings Detection in High-resolution Remote Sensing Images

The exploration of building detection plays an important role in urban planning,smart city and military.Aiming at the problem of high overlapping ratio of detection frames for dense building detection in high resolution remote sensing images,we present an effective YOLOv3 framework,corner regression-based YOLOv3(Correg-YOLOv3),to localize dense building accurately.This improved YOLOv3 algorithm establishes a vertex regression mechanism and an additional loss item about building vertex offsets relative to the center point of bounding box.By extending output dimensions,the trained model is able to output the rectangular bounding boxes and the building vertices meanwhile.Finally,we evaluate the performance of the Correg-YOLOv3 on our self-produced data set and provide a comparative analysis qualitatively and quantitatively.The experimental results achieve high performance in precision(96.45%),recall rate(95.75%),F1 score(96.10%)and average precision(98.05%),which were 2.73%,5.4%,4.1%and 4.73%higher than that of YOLOv3.Therefore,our proposed algorithm effectively tackles the problem of dense building detection in high resolution images.

High-resolution Remote Sensing Image Segmentation Using Minimum Spanning Tree Tessellation and RHMRF-FCM Algorithm

It is proposed a high resolution remote sensing image segmentation method which combines static minimum spanning tree(MST)tessellation considering shape information and the RHMRF-FCM algorithm.It solves the problems in the traditional pixel-based HMRF-FCM algorithm in which poor noise resistance and low precision segmentation in a complex boundary exist.By using the MST model and shape information,the object boundary and geometrical noise can be expressed and reduced respectively.Firstly,the static MST tessellation is employed for dividing the image domain into some sub-regions corresponding to the components of homogeneous regions needed to be segmented.Secondly,based on the tessellation results,the RHMRF model is built,and regulation terms considering the KL information and the information entropy are introduced into the FCM objective function.Finally,the partial differential method and Lagrange function are employed to calculate the parameters of the fuzzy objective function for obtaining the global optimal segmentation results.To verify the robustness and effectiveness of the proposed algorithm,the experiments are carried out with WorldView-3(WV-3)high resolution image.The results from proposed method with different parameters and comparing methods(multi-resolution method and watershed segmentation method in eCognition software)are analyzed qualitatively and quantitatively.

Extraction of coastline in high-resolution remote sensing images based on the active contour model

While executing tasks such as ocean pollution monitoring,maritime rescue,geographic mapping,and automatic navigation utilizing remote sensing images,the coastline feature should be determined.Traditional methods are not satisfactory to extract coastline in high-resolution panchromatic remote sensing image.Active contour model,also called snakes,have proven useful for interactive specification of image contours,so it is used as an effective coastlines extraction technique.Firstly,coastlines are detected by water segmentation and boundary tracking,which are considered initial contours to be optimized through active contour model.As better energy functions are developed,the power assist of snakes becomes effective.New internal energy has been done to reduce problems caused by convergence to local minima,and new external energy can greatly enlarge the capture region around features of interest.After normalization processing,energies are iterated using greedy algorithm to accelerate convergence rate.The experimental results encompassed examples in images and demonstrated the capabilities and efficiencies of the improvement.

RepDDNet:a fast and accurate deforestation detection model with high-resolution remote sensing image

Forest is the largest carbon reservoir and carbon absorber on earth.Thus,mapping forest cover change accurately is of great significance to achieving the global carbon neutrality goal.Accurate forest change information could be acquired by deep learning methods using high-resolution remote sensing images.However,deforestation detection based on deep learning on a large-scale region with high-resolution images required huge computational resources.Therefore,there was an urgent need for a fast and accurate deforestation detection model.In this study,we proposed an interesting but effective re-parameterization deforestation detection model,named RepDDNet.Unlike other existing models designed for deforestation detection,the main feature of RepDDNet was its decoupling feature,which means that it allowed the multi-branch structure in the training stages to be converted into a plain structure in the inference stage,thus the computation efficiency can be significantly improved in the inference stage while maintaining the accuracy unchanged.A large-scale experiment was carried out in Ankang city with 2-meter high-resolution remote sensing images(the total area of it was over 20,000 square kilometers),and the result indicated that the model computation efficiency could be improved by nearly 30%compared with the model without re-parameterization.Additionally,compared with other lightweight models,RepDDNet also displayed a trade-off between accuracy and computation efficiency.

Extensive identification of landslide boundaries using remote sensing images and deep learning method

The frequent occurrence of extreme weather events has rendered numerous landslides to a global natural disaster issue.It is crucial to rapidly and accurately determine the boundaries of landslides for geohazards evaluation and emergency response.Therefore,the Skip Connection DeepLab neural network(SCDnn),a deep learning model based on 770 optical remote sensing images of landslide,is proposed to improve the accuracy of landslide boundary detection.The SCDnn model is optimized for the over-segmentation issue which occurs in conventional deep learning models when there is a significant degree of similarity between topographical geomorphic features.SCDnn exhibits notable improvements in landslide feature extraction and semantic segmentation by combining an enhanced Atrous Spatial Pyramid Convolutional Block(ASPC)with a coding structure that reduces model complexity.The experimental results demonstrate that SCDnn can identify landslide boundaries in 119 images with MIoU values between 0.8and 0.9;while 52 images with MIoU values exceeding 0.9,which exceeds the identification accuracy of existing techniques.This work can offer a novel technique for the automatic extensive identification of landslide boundaries in remote sensing images in addition to establishing the groundwork for future inve stigations and applications in related domains.

Recognizing and monitoring infectious sources of schistosomiasis by developing deep learning models with high-resolution remote sensing images

Background China is progressing towards the goal of schistosomiasis elimination,but there are still some problems,such as difficult management of infection source and snail control.This study aimed to develop deep learning models with high-resolution remote sensing images for recognizing and monitoring livestock bovine,which is an intermediate source of Schistosoma japonicum infection,and to evaluate the effectiveness of the models for real-world application.Methods The dataset of livestock bovine’s spatial distribution was collected from the Chinese National Platform for Common Geospatial Information Services.The high-resolution remote sensing images were further divided into training data,test data,and validation data for model development.Two recognition models based on deep learning methods(ENVINet5 and Mask R-CNN)were developed with reference to the training datasets.The performance of the developed models was evaluated by the performance metrics of precision,recall,and F1-score.Results A total of 50 typical image areas were selected,1125 bovine objectives were labeled by the ENVINet5 model and 1277 bovine objectives were labeled by the Mask R-CNN model.For the ENVINet5 model,a total of 1598 records of bovine distribution were recognized.The model precision and recall were 81.9%and 80.2%,respectively.The F1 score was 0.81.For the Mask R-CNN mode,1679 records of bovine objectives were identified.The model precision and recall were 87.3%and 85.2%,respectively.The F1 score was 0.87.When applying the developed models to real-world schistosomiasis-endemic regions,there were 63 bovine objectives in the original image,53 records were extracted using the ENVINet5 model,and 57 records were extracted using the Mask R-CNN model.The successful recognition ratios were 84.1%and 90.5%for the respectively developed models.Conclusion The ENVINet5 model is very feasible when the bovine distribution is low in structure with few samples.The Mask R-CNN model has a good framework design and runs highly efficiently.The livestock recognition models developed using deep learning methods with high-resolution remote sensing images accurately recognize the spatial distribution of livestock,which could enable precise control of schistosomiasis.

VLCA: vision-language aligning model with cross-modal attention for bilingual remote sensing image captioning

In the field of satellite imagery, remote sensing image captioning(RSIC) is a hot topic with the challenge of overfitting and difficulty of image and text alignment. To address these issues, this paper proposes a vision-language aligning paradigm for RSIC to jointly represent vision and language. First, a new RSIC dataset DIOR-Captions is built for augmenting object detection in optical remote(DIOR) sensing images dataset with manually annotated Chinese and English contents. Second, a Vision-Language aligning model with Cross-modal Attention(VLCA) is presented to generate accurate and abundant bilingual descriptions for remote sensing images. Third, a crossmodal learning network is introduced to address the problem of visual-lingual alignment. Notably, VLCA is also applied to end-toend Chinese captions generation by using the pre-training language model of Chinese. The experiments are carried out with various baselines to validate VLCA on the proposed dataset. The results demonstrate that the proposed algorithm is more descriptive and informative than existing algorithms in producing captions.

Transductive Transfer Dictionary Learning Algorithm for Remote Sensing Image Classification

To create a green and healthy living environment,people have put forward higher requirements for the refined management of ecological resources.A variety of technologies,including satellite remote sensing,Internet of Things,artificial intelligence,and big data,can build a smart environmental monitoring system.Remote sensing image classification is an important research content in ecological environmental monitoring.Remote sensing images contain rich spatial information andmulti-temporal information,but also bring challenges such as difficulty in obtaining classification labels and low classification accuracy.To solve this problem,this study develops a transductive transfer dictionary learning(TTDL)algorithm.In the TTDL,the source and target domains are transformed fromthe original sample space to a common subspace.TTDL trains a shared discriminative dictionary in this subspace,establishes associations between domains,and also obtains sparse representations of source and target domain data.To obtain an effective shared discriminative dictionary,triple-induced ordinal locality preserving term,Fisher discriminant term,and graph Laplacian regularization termare introduced into the TTDL.The triplet-induced ordinal locality preserving term on sub-space projection preserves the local structure of data in low-dimensional subspaces.The Fisher discriminant term on dictionary improves differences among different sub-dictionaries through intra-class and inter-class scatters.The graph Laplacian regularization term on sparse representation maintains the manifold structure using a semi-supervised weight graphmatrix,which can indirectly improve the discriminative performance of the dictionary.The TTDL is tested on several remote sensing image datasets and has strong discrimination classification performance.

CFM-UNet:A Joint CNN and Transformer Network via Cross Feature Modulation for Remote Sensing Images Segmentation

The semantic segmentation methods based on CNN have made great progress,but there are still some shortcomings in the application of remote sensing images segmentation,such as the small receptive field can not effectively capture global context.In order to solve this problem,this paper proposes a hybrid model based on ResNet50 and swin transformer to directly capture long-range dependence,which fuses features through Cross Feature Modulation Module(CFMM).Experimental results on two publicly available datasets,Vaihingen and Potsdam,are mIoU of 70.27%and 76.63%,respectively.Thus,CFM-UNet can maintain a high segmentation performance compared with other competitive networks.

Optimum segmentation of simple objects in high-resolution remote sensing imagery in coastal areas

The optimum segmentation of ground objects in a landscape is essential for interpretation of high-resolution remotely sensed imagery and detection of objects; and it is also a technical foundation to efficiently use spatial information in remote sensing imagery. Landscapes are complex system composed of a large number of heterogeneous components. There are many explicit homogeneous image objects that have similar spectral character and yet differ from surrounding objects in high-resolution remote sensing imagery. Thereby, a new concept of Distinctive Feature of fractal is put forward and used in deriving Distinctive Feature curve of fractal evolution in multiscale segmentation. Through distinguishing the extremum condition of Distinctive Feature curve and the inclusion relationship of fractals in multiscale representation the Scalar Order is built. This can help to determinate the optimum scale in image segmentation for simple-objects, and the potential meaningful image-object fitting the intrinsic scale of the dominant landscape object can be obtained. Based on the application in high-resolution remote sensing imagery in coastal areas, a satisfactory result was acquired.

Advances in urban information extraction from high-resolution remote sensing imagery

The study of urban area is one of the hottest research topics in the field of remote sensing. With the accumulation of high-resolution(HR) remote sensing data and emerging of new satellite sensors, HR observation of urban areas has become increasingly possible, which provides us with more elaborate urban information. However, the strong heterogeneity in the spectral and spatial domain of HR imagery brings great challenges to urban remote sensing. In recent years, numerous approaches were proposed to deal with HR image interpretation over complex urban scenes, including a series of features from low level to high level, as well as state-of-the-art methods depicting not only the urban extent, but also the intra-urban variations. In this paper, we aim to summarize the major advances in HR urban remote sensing from the aspects of feature representation and information extraction. Moreover, the future trends are discussed from the perspectives of methodology, urban structure and pattern characterization, big data challenge, and global mapping.

Privacy‐preserving remote sensing images recognition based on limited visual cryptography

With the arrival of new data acquisition platforms derived from the Internet of Things(IoT),this paper goes beyond the understanding of traditional remote sensing technologies.Deep fusion of remote sensing and computer vision has hit the industrial world and makes it possible to apply Artificial intelligence to solve problems such as automatic extraction of information and image interpretation.However,due to the complex architecture of IoT and the lack of a unified security protection mechanism,devices in remote sensing are vulnerable to privacy leaks when sharing data.It is necessary to design a security scheme suitable for computation‐limited devices in IoT,since traditional encryption methods are based on computational complexity.Visual Cryptography(VC)is a threshold scheme for images that can be decoded directly by the human visual system when superimposing encrypted images.The stacking‐to‐see feature and simple Boolean decryption operation make VC an ideal solution for privacy‐preserving recognition for large‐scale remote sensing images in IoT.In this study,the secure and efficient transmission of high‐resolution remote sensing images by meaningful VC is achieved.By diffusing the error between the encryption block and the original block to adjacent blocks,the degradation of quality in recovery images is mitigated.By fine‐tuning the pre‐trained model from large‐scale datasets,we improve the recognition performance of small encryption datasets for remote sensing images.The experimental results show that the proposed lightweight privacy‐preserving recognition framework maintains high recognition performance while enhancing security.

Fine-Grained Classification of Remote Sensing Ship Images Based on Improved VAN

The remote sensing ships’fine-grained classification technology makes it possible to identify certain ship types in remote sensing images,and it has broad application prospects in civil and military fields.However,the current model does not examine the properties of ship targets in remote sensing images with mixed multi-granularity features and a complicated backdrop.There is still an opportunity for future enhancement of the classification impact.To solve the challenges brought by the above characteristics,this paper proposes a Metaformer and Residual fusion network based on Visual Attention Network(VAN-MR)for fine-grained classification tasks.For the complex background of remote sensing images,the VAN-MR model adopts the parallel structure of large kernel attention and spatial attention to enhance the model’s feature extraction ability of interest targets and improve the classification performance of remote sensing ship targets.For the problem of multi-grained feature mixing in remote sensing images,the VAN-MR model uses a Metaformer structure and a parallel network of residual modules to extract ship features.The parallel network has different depths,considering both high-level and lowlevel semantic information.The model achieves better classification performance in remote sensing ship images with multi-granularity mixing.Finally,the model achieves 88.73%and 94.56%accuracy on the public fine-grained ship collection-23(FGSC-23)and FGSCR-42 datasets,respectively,while the parameter size is only 53.47 M,the floating point operations is 9.9 G.The experimental results show that the classification effect of VAN-MR is superior to that of traditional CNNs model and visual model with Transformer structure under the same parameter quantity.

Automated Deep Learning Driven Crop Classification on Hyperspectral Remote Sensing Images

Hyperspectral remote sensing/imaging spectroscopy is a novel approach to reaching a spectrum from all the places of a huge array of spatial places so that several spectral wavelengths are utilized for making coherent images.Hyperspectral remote sensing contains acquisition of digital images from several narrow,contiguous spectral bands throughout the visible,Thermal Infrared(TIR),Near Infrared(NIR),and Mid-Infrared(MIR)regions of the electromagnetic spectrum.In order to the application of agricultural regions,remote sensing approaches are studied and executed to their benefit of continuous and quantitativemonitoring.Particularly,hyperspectral images(HSI)are considered the precise for agriculture as they can offer chemical and physical data on vegetation.With this motivation,this article presents a novel Hurricane Optimization Algorithm with Deep Transfer Learning Driven Crop Classification(HOADTL-CC)model onHyperspectralRemote Sensing Images.The presentedHOADTL-CC model focuses on the identification and categorization of crops on hyperspectral remote sensing images.To accomplish this,the presentedHOADTL-CC model involves the design ofHOAwith capsule network(CapsNet)model for generating a set of useful feature vectors.Besides,Elman neural network(ENN)model is applied to allot proper class labels into the input HSI.Finally,glowworm swarm optimization(GSO)algorithm is exploited to fine tune the ENNparameters involved in this article.The experimental result scrutiny of the HOADTL-CC method can be tested with the help of benchmark dataset and the results are assessed under distinct aspects.Extensive comparative studies stated the enhanced performance of the HOADTL-CC model over recent approaches with maximum accuracy of 99.51%.

Hyperspectral Remote Sensing Image Classification Using Improved Metaheuristic with Deep Learning

Remote sensing image(RSI)classifier roles a vital play in earth observation technology utilizing Remote sensing(RS)data are extremely exploited from both military and civil fields.More recently,as novel DL approaches develop,techniques for RSI classifiers with DL have attained important breakthroughs,providing a new opportunity for the research and development of RSI classifiers.This study introduces an Improved Slime Mould Optimization with a graph convolutional network for the hyperspectral remote sensing image classification(ISMOGCN-HRSC)model.The ISMOGCN-HRSC model majorly concentrates on identifying and classifying distinct kinds of RSIs.In the presented ISMOGCN-HRSC model,the synergic deep learning(SDL)model is exploited to produce feature vectors.The GCN model is utilized for image classification purposes to identify the proper class labels of the RSIs.The ISMO algorithm is used to enhance the classification efficiency of the GCN method,which is derived by integrating chaotic concepts into the SMO algorithm.The experimental assessment of the ISMOGCN-HRSC method is tested using a benchmark dataset.

An Intelligent Detection Method for Optical Remote Sensing Images Based on Improved YOLOv7

To address the issue of imbalanced detection performance and detection speed in current mainstream object detection algorithms for optical remote sensing images,this paper proposes a multi-scale object detection model for remote sensing images on complex backgrounds,called DI-YOLO,based on You Only Look Once v7-tiny(YOLOv7-tiny).Firstly,to enhance the model’s ability to capture irregular-shaped objects and deformation features,as well as to extract high-level semantic information,deformable convolutions are used to replace standard convolutions in the original model.Secondly,a Content Coordination Attention Feature Pyramid Network(CCA-FPN)structure is designed to replace the Neck part of the original model,which can further perceive relationships between different pixels,reduce feature loss in remote sensing images,and improve the overall model’s ability to detect multi-scale objects.Thirdly,an Implicitly Efficient Decoupled Head(IEDH)is proposed to increase the model’s flexibility,making it more adaptable to complex detection tasks in various scenarios.Finally,the Smoothed Intersection over Union(SIoU)loss function replaces the Complete Intersection over Union(CIoU)loss function in the original model,resulting in more accurate prediction of bounding boxes and continuous model optimization.Experimental results on the High-Resolution Remote Sensing Detection(HRRSD)dataset demonstrate that the proposed DI-YOLO model outperforms mainstream target detection algorithms in terms of mean Average Precision(mAP)for optical remote sensing image detection.Furthermore,it achieves Frames Per Second(FPS)of 138.9,meeting fast and accurate detection requirements.

Optimizing Spatial Relationships in GCN to Improve the Classification Accuracy of Remote Sensing Images

Semantic segmentation of remote sensing images is one of the core tasks of remote sensing image interpretation.With the continuous develop-ment of artificial intelligence technology,the use of deep learning methods for interpreting remote-sensing images has matured.Existing neural networks disregard the spatial relationship between two targets in remote sensing images.Semantic segmentation models that combine convolutional neural networks(CNNs)and graph convolutional neural networks(GCNs)cause a lack of feature boundaries,which leads to the unsatisfactory segmentation of various target feature boundaries.In this paper,we propose a new semantic segmentation model for remote sensing images(called DGCN hereinafter),which combines deep semantic segmentation networks(DSSN)and GCNs.In the GCN module,a loss function for boundary information is employed to optimize the learning of spatial relationship features between the target features and their relationships.A hierarchical fusion method is utilized for feature fusion and classification to optimize the spatial relationship informa-tion in the original feature information.Extensive experiments on ISPRS 2D and DeepGlobe semantic segmentation datasets show that compared with the existing semantic segmentation models of remote sensing images,the DGCN significantly optimizes the segmentation effect of feature boundaries,effectively reduces the noise in the segmentation results and improves the segmentation accuracy,which demonstrates the advancements of our model.

Removal of Stripes in Remote Sensing Images Based on Statistics Combined with Image Enhancement

A method to remove stripes from remote sensing images is proposed based on statistics and a new image enhancement method.The overall processing steps for improving the quality of remote sensing images are introduced to provide a general baseline.Due to the differences in satellite sensors when producing images,subtle but inherent stripes can appear at the stitching positions between the sensors.These stitchingstripes cannot be eliminated by conventional relative radiometric calibration.The inherent stitching stripes cause difficulties in downstream tasks such as the segmentation,classification and interpretation of remote sensing images.Therefore,a method to remove the stripes based on statistics and a new image enhancement approach are proposed in this paper.First,the inconsistency in grayscales around stripes is eliminated with the statistical method.Second,the pixels within stripes are weighted and averaged based on updated pixel values to enhance the uniformity of the overall image radiation quality.Finally,the details of the images are highlighted by a new image enhancement method,which makes the whole image clearer.Comprehensive experiments are performed,and the results indicate that the proposed method outperforms the baseline approach in terms of visual quality and radiation correction accuracy.

Image Fusion Based on NSCT and Sparse Representation for Remote Sensing Data

The practice of integrating images from two or more sensors collected from the same area or object is known as image fusion.The goal is to extract more spatial and spectral information from the resulting fused image than from the component images.The images must be fused to improve the spatial and spectral quality of both panchromatic and multispectral images.This study provides a novel picture fusion technique that employs L0 smoothening Filter,Non-subsampled Contour let Transform(NSCT)and Sparse Representation(SR)followed by the Max absolute rule(MAR).The fusion approach is as follows:first,the multispectral and panchromatic images are divided into lower and higher frequency components using the L0 smoothing filter.Then comes the fusion process,which uses an approach that combines NSCT and SR to fuse low frequency components.Similarly,the Max-absolute fusion rule is used to merge high frequency components.Finally,the final image is obtained through the disintegration of fused low and high frequency data.In terms of correlation coefficient,Entropy,spatial frequency,and fusion mutual information,our method outperforms other methods in terms of image quality enhancement and visual evaluation.