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.

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.

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.

A Multi Moving Target Recognition Algorithm Based on Remote Sensing Video

The Earth observation remote sensing images can display ground activities and status intuitively,which plays an important role in civil and military fields.However,the information obtained from the research only from the perspective of images is limited,so in this paper we conduct research from the perspective of video.At present,the main problems faced when using a computer to identify remote sensing images are:They are difficult to build a fixed regular model of the target due to their weak moving regularity.Additionally,the number of pixels occupied by the target is not enough for accurate detection.However,the number of moving targets is large at the same time.In this case,the main targets cannot be recognized completely.This paper studies from the perspective of Gestalt vision,transforms the problem ofmoving target detection into the problem of salient region probability,and forms a Saliency map algorithm to extract moving targets.On this basis,a convolutional neural network with global information is constructed to identify and label the target.And the experimental results show that the algorithm can extract moving targets and realize moving target recognition under many complex conditions such as target’s long-term stay and small-amplitude movement.

Automatic Extraction of Typical River Vegetation Elements Based on Low-altitude Remote Sensing Images

Based on low-altitude remote sensing images,this paper established sample set of typical river vegetation elements and proposed river vegetation extraction technical solution to adaptively extract typical vegetation elements of river basins.The main research of this paper were as follows:(1)a typical vegetation extraction sample set based on low-altitude remote sensing images was established.(2)A low-altitude remote sensing image vegetation extraction model based on the focus perception module was designed to realize the end-to-end automatic extraction of different types of vegetation areas of low-altitude remote sensing images to fully learn the spectral spatial texture information and deep semantic information of the images.(3)By comparison with the baseline method,baseline method with embedded focus perception module showed an improvement in the precision by 7.37%and mIoU by 49.49%.Through visual interpretation and quantitative calculation analysis,the typical river vegetation adaptive extraction network has effectiveness and generalization ability,consistent with the needs of practical applications of vegetation extraction.

Effective distributed convolutional neural network architecture for remote sensing images target classification with a pre-training approach

How to recognize targets with similar appearances from remote sensing images(RSIs) effectively and efficiently has become a big challenge. Recently, convolutional neural network(CNN) is preferred in the target classification due to the powerful feature representation ability and better performance. However,the training and testing of CNN mainly rely on single machine.Single machine has its natural limitation and bottleneck in processing RSIs due to limited hardware resources and huge time consuming. Besides, overfitting is a challenge for the CNN model due to the unbalance between RSIs data and the model structure.When a model is complex or the training data is relatively small,overfitting occurs and leads to a poor predictive performance. To address these problems, a distributed CNN architecture for RSIs target classification is proposed, which dramatically increases the training speed of CNN and system scalability. It improves the storage ability and processing efficiency of RSIs. Furthermore,Bayesian regularization approach is utilized in order to initialize the weights of the CNN extractor, which increases the robustness and flexibility of the CNN model. It helps prevent the overfitting and avoid the local optima caused by limited RSI training images or the inappropriate CNN structure. In addition, considering the efficiency of the Na¨?ve Bayes classifier, a distributed Na¨?ve Bayes classifier is designed to reduce the training cost. Compared with other algorithms, the proposed system and method perform the best and increase the recognition accuracy. The results show that the distributed system framework and the proposed algorithms are suitable for RSIs target classification tasks.

Alternative Fuzzy Cluster Segmentation of Remote Sensing Images Based on Adaptive Genetic Algorithm

Remote sensing image segmentation is the basis of image understanding and analysis. However,the precision and the speed of segmentation can not meet the need of image analysis,due to strong uncertainty and rich texture details of remote sensing images. We proposed a new segmentation method based on Adaptive Genetic Algorithm(AGA) and Alternative Fuzzy C-Means(AFCM) . Segmentation thresholds were identified by AGA. Then the image was segmented by AFCM. The results indicate that the precision and the speed of segmentation have been greatly increased,and the accuracy of threshold selection is much higher compared with traditional Otsu and Fuzzy C-Means(FCM) segmentation methods. The segmentation results also show that multi-thresholds segmentation has been achieved by combining AGA with AFCM.

Segmentation of Remote Sensing Images Based on U-Net Multi-Task Learning

In order to accurately segment architectural features in highresolution remote sensing images,a semantic segmentation method based on U-net network multi-task learning is proposed.First,a boundary distance map was generated based on the remote sensing image of the ground truth map of the building.The remote sensing image and its truth map were used as the input in the U-net network,followed by the addition of the building ground prediction layer at the end of the U-net network.Based on the ResNet network,a multi-task network with the boundary distance prediction layer was built.Experiments involving the ISPRS aerial remote sensing image building and feature annotation data set show that compared with the full convolutional network combined with the multi-layer perceptron method,the intersection ratio of VGG16 network,VGG16+boundary prediction,ResNet50 and the method in this paper were increased by 5.15%,6.946%,6.41%and 7.86%.The accuracy of the networks was increased to 94.71%,95.39%,95.30%and 96.10%respectively,which resulted in high-precision extraction of building features.

Object Detection in Remote Sensing Images Using Picture Fuzzy Clustering and MapReduce

In image processing, one of the most important steps is image segmentation. The objects in remote sensing images often have to be detected in order toperform next steps in image processing. Remote sensing images usually havelarge size and various spatial resolutions. Thus, detecting objects in remote sensing images is very complicated. In this paper, we develop a model to detectobjects in remote sensing images based on the combination of picture fuzzy clustering and MapReduce method (denoted as MPFC). Firstly, picture fuzzy clustering is applied to segment the input images. Then, MapReduce is used to reducethe runtime with the guarantee of quality. To convert data for MapReduce processing, two new procedures are introduced, including Map_PFC and Reduce_PFC.The formal representation and details of two these procedures are presented in thispaper. The experiments on satellite image and remote sensing image datasets aregiven to evaluate proposed model. Validity indices and time consuming are usedto compare proposed model to picture fuzzy clustering model. The values ofvalidity indices show that picture fuzzy clustering integrated to MapReduce getsbetter quality of segmentation than using picture fuzzy clustering only. Moreover,on two selected image datasets, the run time of MPFC model is much less thanthat of picture fuzzy clustering.

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.

A Remote Sensing Image Semantic Segmentation Method by Combining Deformable Convolution with Conditional Random Fields

Currently,deep convolutional neural networks have made great progress in the field of semantic segmentation.Because of the fixed convolution kernel geometry,standard convolution neural networks have been limited the ability to simulate geometric transformations.Therefore,a deformable convolution is introduced to enhance the adaptability of convolutional networks to spatial transformation.Considering that the deep convolutional neural networks cannot adequately segment the local objects at the output layer due to using the pooling layers in neural network architecture.To overcome this shortcoming,the rough prediction segmentation results of the neural network output layer will be processed by fully connected conditional random fields to improve the ability of image segmentation.The proposed method can easily be trained by end-to-end using standard backpropagation algorithms.Finally,the proposed method is tested on the ISPRS dataset.The results show that the proposed method can effectively overcome the influence of the complex structure of the segmentation object and obtain state-of-the-art accuracy on the ISPRS Vaihingen 2D semantic labeling dataset.

Smart Photogrammetric and Remote Sensing Image Processing for Very High Resolution Optical Images——Examples from the CRC-AGIP Lab at UNB

This paper introduces some of the image processing techniques developed in the Canada Research Chair in Advanced Geomatics Image Processing Laboratory (CRC-AGIP Lab) and in the Department of Geodesy and Geomatics Engineering (GGE) at the University of New Brunswick (UNB), Canada. The techniques were developed by innovatively/“smartly” utilizing the characteristics of the available very high resolution optical remote sensing images to solve important problems or create new applications in photogrammetry and remote sensing. The techniques to be introduced are: automated image fusion (UNB-PanSharp), satellite image online mapping, street view technology, moving vehicle detection using single set satellite imagery, supervised image segmentation, image matching in smooth areas, and change detection using images from different viewing angles. Because of their broad application potential, some of the techniques have made a global impact, and some have demonstrated the potential for a global impact.

基于改进Swin-Unet的遥感图像分割方法

针对遥感图像数据本身存在分辨率高、背景复杂和光照不均等特性导致边界分割不连续、目标错分漏分以及存在孔洞等问题,提出了一种基于改进Swin-Unet的遥感图像分割方法。在编码器末端引入空洞空间金字塔池化(Atrous Spatial Pyramid Pooling,ASPP)模块,用于捕获多尺度特征,增强网络获取不同尺度的能力,充分提取上下文信息;将解码器端的Swin Transformer Block替换为残差Swin Transformer Block,不仅保留了原始信息,又能够缓解模型出现梯度弥散现象;在跳跃连接中引入残差注意力机制,可以让模型更加关注特征图中的重要特征信息,抑制无效信息,从而提高模型分割的准确率。在自建数据集上进行实验,结果表明,改进后的网络平均交并比(mean Intersection over Union,mIoU)达到了80.55%,提高了4.13个百分点,证明改进后的网络可以有效提高遥感图像分割的精度。

MDSNet:a multiscale decoupled supervision network for semantic segmentation of remote sensing images

Recent deep-learning successes have led to a new wave of semantic segmentation in remote sensing(RS)applications.However,most approaches rarely distinguish the role of the body and edge of RS ground objects;thus,our understanding of these semantic parts has been frustrated by the lack of detailed geometry and appearance.Here we present a multiscale decoupled supervision network for RS semantic segmentation.Our proposed framework extends a densely supervised encoder-decoder network with a feature decoupling module that can decouple semantic features with different scales into distinct body and edge components.We further conduct multiscale supervision of the original and decoupled body and edge features to enhance inner consistency and spatial boundaries in remote sensing image(RSl)ground objects,enabling new segmentation designs and semantic components that can learn to perform multiscale geometry,and appearance.Our results outperform the previous algorithm and are robust to different datasets.These results demonstrate that decoupled supervision is an effective solution to semantic segmentation tasks of RS images.

基于伪全局Swin Transformer的遥感图像识别算法

如何在多目标并列的情况下,确定符合人类思维习惯的核心目标是遥感图像识别的关键之一.因此,在全局视野下,为各目标分配符合人类视觉习惯的注意力,是甄选核心目标的有效途径之一.文中结合Transformer提取全局特征的思想和Swin Transformer对图像栅格化处理可降低计算量的优点,提出基于伪全局Swin Transformer的遥感图像识别算法.构建伪全局Swin Transformer模块,将遥感图像栅格化后的各局部信息聚合为一个特征值,替代以像素为基础的全局信息,以较小计算量为代价,获取全局特征,有效提升模型对所有目标的感知能力.同时,通过以可变形卷积为基础的感受野自适应缩放模块,使感受野向核心目标偏移,提高网络对核心目标信息的关注,从而实现对遥感图像的精确识别.在RSSCN7、AID和OPTIMAL-31遥感图像数据集上的实验表明,文中算法取得较高的识别精度和参数识别效率.

基于改进YOLOv3-Tiny的遥感舰船小目标检测方法

遥感图像中各类舰船小目标检测存在检测难度大、检测精确度低等问题,因此提出一种基于改进YOLOv3-Tiny的遥感舰船小目标检测方法。先对训练数据进行Mosaic数据增强,丰富小尺度样本数据集,解决遥感图像小目标检测泛化能力低的问题,再在特征提取网络中加入混合域注意力机制CBAM,强化小目标的特征提取,提高对遥感舰船小目标的检测能力。实验结果表明,改进后的方法能够更加准确、快速地对遥感舰船小目标进行检测,显著提高了检测的准确率和召回率。

Watershed-based Image Segmentation with Region Merging and Edge Detection

The clustering technique is used to examine each pixel in the image which assigned to one of the clusters depending on the minimum distance to obtain primary classified image into different intensity regions. A watershed transformation technique is then employes. This includes: gradient of the classified image, dividing the image into markers, checking the Marker Image to see if it has zero points (watershed lines). The watershed lines are then deleted in the Marker Image created by watershed algorithm. A Region Adjacency Graph (RAG) and Region Adjacency Boundary (RAB) are created between two regions from Marker Image. Finally region merging is done according to region average intensity and two edge strengths (T1, T2). The approach of the authors is tested on remote sensing and brain MR medical images. The final segmentation result is one closed boundary per actual region in the image.

基于空洞Inception注意力U-Net的遥感图像目标分割方法

针对遥感图像中目标类型多、目标尺寸小、目标大小差异较大、图像视场大、环境和背景复杂等特点导致其分割困难的问题,提出一种注意力空洞多尺度U-Net(ADMSU-Net)的遥感图像中目标分割方法。ADMSU-Net由收缩子网、扩展子网、空洞残差卷积连接和空间注意连接组成,在收缩和扩展子网中引入空洞多尺度Inception模块,在不增加计算成本的情况下学习多尺度高级特征,在跳跃连接中加入空间注意机制,提取特征之间的空间相关性,提高模型的分割性能。在包含多尺度目标的遥感图像数据集EORSSD上的实验结果表明,该方法是有效可行的,分割准确率为93%以上。

Transformer-Based Cloud Detection Method for High-Resolution Remote Sensing Imagery

Cloud detection from satellite and drone imagery is crucial for applications such as weather forecasting and environmentalmonitoring.Addressing the limitations of conventional convolutional neural networks,we propose an innovative transformer-based method.This method leverages transformers,which are adept at processing data sequences,to enhance cloud detection accuracy.Additionally,we introduce a Cyclic Refinement Architecture that improves the resolution and quality of feature extraction,thereby aiding in the retention of critical details often lost during cloud detection.Our extensive experimental validation shows that our approach significantly outperforms established models,excelling in high-resolution feature extraction and precise cloud segmentation.By integrating Positional Visual Transformers(PVT)with this architecture,our method advances high-resolution feature delineation and segmentation accuracy.Ultimately,our research offers a novel perspective for surmounting traditional challenges in cloud detection and contributes to the advancement of precise and dependable image analysis across various domains.

基于改进YOLOv5的遥感图像目标检测

目前目标检测技术虽然已经趋于成熟,但是对遥感图像的检测仍存在不少挑战。针对遥感图像的背景复杂、目标尺度差异大、目标方向任意等特点造成目标检测精度低下的问题,提出一种基于改进YOLOv5的遥感图像目标检测算法。首先,构建一种联合注意力的多尺度特征增强网络,充分融合高低层特征,使特征层具有语义信息的同时包含丰富的细节信息,并在融合过程中利用设计的特征聚焦模块帮助模型选择关键特征,抑制无关信息。其次,使用感受野模块(RFB)对融合后的特征图进行更新,扩大特征图的感受野,减少特征信息损失。最后,对目标增加旋转角度,并采用圆形平滑标签将回归问题转化成分类问题,提高遥感目标定位的准确性。在用于航拍图像目标检测的大规模数据集(DOTA)上的实验结果表明,与YOLOv5算法相比,所提算法的交并比(Io U)为0.5和0.5~0.95时的平均精度均值(m AP@0.5和m AP@0.5∶0.95)分别提高了7.3和3.3个百分点,能够明显提高复杂背景下遥感图像目标的检测精度,并改善对遥感目标的漏检和误检情况。