Advancements in Remote Sensing Image Dehazing: Introducing URA-Net with Multi-Scale Dense Feature Fusion Clusters and Gated Jump Connection

The degradation of optical remote sensing images due to atmospheric haze poses a significant obstacle,profoundly impeding their effective utilization across various domains.Dehazing methodologies have emerged as pivotal components of image preprocessing,fostering an improvement in the quality of remote sensing imagery.This enhancement renders remote sensing data more indispensable,thereby enhancing the accuracy of target iden-tification.Conventional defogging techniques based on simplistic atmospheric degradation models have proven inadequate for mitigating non-uniform haze within remotely sensed images.In response to this challenge,a novel UNet Residual Attention Network(URA-Net)is proposed.This paradigmatic approach materializes as an end-to-end convolutional neural network distinguished by its utilization of multi-scale dense feature fusion clusters and gated jump connections.The essence of our methodology lies in local feature fusion within dense residual clusters,enabling the extraction of pertinent features from both preceding and current local data,depending on contextual demands.The intelligently orchestrated gated structures facilitate the propagation of these features to the decoder,resulting in superior outcomes in haze removal.Empirical validation through a plethora of experiments substantiates the efficacy of URA-Net,demonstrating its superior performance compared to existing methods when applied to established datasets for remote sensing image defogging.On the RICE-1 dataset,URA-Net achieves a Peak Signal-to-Noise Ratio(PSNR)of 29.07 dB,surpassing the Dark Channel Prior(DCP)by 11.17 dB,the All-in-One Network for Dehazing(AOD)by 7.82 dB,the Optimal Transmission Map and Adaptive Atmospheric Light For Dehazing(OTM-AAL)by 5.37 dB,the Unsupervised Single Image Dehazing(USID)by 8.0 dB,and the Superpixel-based Remote Sensing Image Dehazing(SRD)by 8.5 dB.Particularly noteworthy,on the SateHaze1k dataset,URA-Net attains preeminence in overall performance,yielding defogged images characterized by consistent visual quality.This underscores the contribution of the research to the advancement of remote sensing technology,providing a robust and efficient solution for alleviating the adverse effects of haze on image quality.

Feature extraction and analysis of reclaimed vegetation in ecological restoration area of abandoned mines based on hyperspectral remote sensing images

The vegetation growth status largely represents the ecosystem function and environmental quality.Hyperspectral remote sensing data can effectively eliminate the effects of surface spectral reflectance and atmospheric scattering and directly reflect the vegetation parameter information.In this study,the abandoned mining area in the Helan Mountains,China was taken as the study area.Based on hyperspectral remote sensing images of Zhuhai No.1 hyperspectral satellite,we used the pixel dichotomy model,which was constructed using the normalized difference vegetation index(NDVI),to estimate the vegetation coverage of the study area,and evaluated the vegetation growth status by five vegetation indices(NDVI,ratio vegetation index(RVI),photochemical vegetation index(PVI),red-green ratio index(RGI),and anthocyanin reflectance index 1(ARI1)).According to the results,the reclaimed vegetation growth status in the study area can be divided into four levels(unhealthy,low healthy,healthy,and very healthy).The overall vegetation growth status in the study area was generally at low healthy level,indicating that the vegetation growth status in the study area was not good due to short-time period restoration and harsh damaged environment such as high and steep rock slopes.Furthermore,the unhealthy areas were mainly located in Dawukougou where abandoned mines were concentrated,indicating that the original mining activities have had a large effect on vegetation ecology.After ecological restoration of abandoned mines,the vegetation coverage in the study area has increased to a certain extent,but the amplitude was not large.The situation of vegetation coverage in the northern part of the study area was worse than that in the southern part,due to abandoned mines mainly concentrating in the northern part of the Helan Mountains.The combination of hyperspectral remote sensing data and vegetation indices can comprehensively extract the characteristics of vegetation,accurately analyze the plant growth status,and provide technical support for vegetation health evaluation.

Hyperspectral remote sensing identification of marine oil emulsions based on the fusion of spatial and spectral features

Marine oil spill emulsions are difficult to recover,and the damage to the environment is not easy to eliminate.The use of remote sensing to accurately identify oil spill emulsions is highly important for the protection of marine environments.However,the spectrum of oil emulsions changes due to different water content.Hyperspectral remote sensing and deep learning can use spectral and spatial information to identify different types of oil emulsions.Nonetheless,hyperspectral data can also cause information redundancy,reducing classification accuracy and efficiency,and even overfitting in machine learning models.To address these problems,an oil emulsion deep-learning identification model with spatial-spectral feature fusion is established,and feature bands that can distinguish between crude oil,seawater,water-in-oil emulsion(WO),and oil-in-water emulsion(OW)are filtered based on a standard deviation threshold–mutual information method.Using oil spill airborne hyperspectral data,we conducted identification experiments on oil emulsions in different background waters and under different spatial and temporal conditions,analyzed the transferability of the model,and explored the effects of feature band selection and spectral resolution on the identification of oil emulsions.The results show the following.(1)The standard deviation–mutual information feature selection method is able to effectively extract feature bands that can distinguish between WO,OW,oil slick,and seawater.The number of bands was reduced from 224 to 134 after feature selection on the Airborne Visible Infrared Imaging Spectrometer(AVIRIS)data and from 126 to 100 on the S185 data.(2)With feature selection,the overall accuracy and Kappa of the identification results for the training area are 91.80%and 0.86,respectively,improved by 2.62%and 0.04,and the overall accuracy and Kappa of the identification results for the migration area are 86.53%and 0.80,respectively,improved by 3.45%and 0.05.(3)The oil emulsion identification model has a certain degree of transferability and can effectively identify oil spill emulsions for AVIRIS data at different times and locations,with an overall accuracy of more than 80%,Kappa coefficient of more than 0.7,and F1 score of 0.75 or more for each category.(4)As the spectral resolution decreasing,the model yields different degrees of misclassification for areas with a mixed distribution of oil slick and seawater or mixed distribution of WO and OW.Based on the above experimental results,we demonstrate that the oil emulsion identification model with spatial–spectral feature fusion achieves a high accuracy rate in identifying oil emulsion using airborne hyperspectral data,and can be applied to images under different spatial and temporal conditions.Furthermore,we also elucidate the impact of factors such as spectral resolution and background water bodies on the identification process.These findings provide new reference for future endeavors in automated marine oil spill detection.

Hot spot tracking of flood remote sensing research over the past 22 years:abibliometric analysis using CiteSpace

Background,aim,and scope In the context of climate change,extreme precipitation and resulting flooding events are becoming increasingly severe.Remote sensing technologies are advantageous for monitoring such disasters due to their wide observation range,periodic revisit capabilities,and continuous spatial coverage.These tools enable real-time and quantitative assessment of flood inundation.Over the past 20 years,the field of remote sensing for floods has seen significant advancements.Understanding the evolution of research hotspots within this field can offer valuable insights for future research directions.Materials and methods This study systematically analyzes the development and hotspot evolution in the field of flood remote sensing,both domestically and internationally during 2000—2021.Data from CNKI(China National Knowledge Infrastructure)and WOS(Web of Science)databases are utilized for this analysis.Results(1)A total of 1693 articles have been published in this field,showing a stable growth trend post-2008.Significant contributors include the Chinese Academy of Sciences,Beijing Normal University,Wuhan University,the Italian National Research Council,and National Aeronautics and Space Administration.(2)High-frequency keywords from 2000 to 2021 include“remote sensing”“flood”“model”“classification”“GIS”“climate change”“area”,and“MODIS”.(3)The most prominent keywords were“GIS”(8.65),“surface water”(7.16),“remote sensing”(7.07),“machine learning”(6.52),and“sentinel-2”(5.86).(4)Thirteen cluster labels were identified through clustering,divided into three phases:2000—2009(initial exploratory stage),2010—2014(period of rapid development),and 2015—2021(steady development of remote sensing for floods and related disasters).Discussion The field exhibits strong phase-based development,with research focuses shifting over time.From 2000 to 2009,emphasis was on remote sensing image application and flood model development.From 2010 to 2014,the focus shifted to accurate interpretation of remote sensing images,multispectral image applications,and long time series detection.From 2015 to 2021,research concentrated on steady development,leveraging large datasets and advanced data processing techniques,including improvements in water body indices,big data fusion,deep learning,and drone monitoring.Early on,SAR data,known for its all-weather capability,was crucial for rapid flood hazard extraction and flood hydrological models.With the rise of high-quality optical satellites,optical remote sensing has become more prevalent,though algorithm accuracy and efficiency for water body index methods still require improvement.Conclusions Data sources and methodologies have evolved from early reliance on radar data to the current exploration of optical image fusion and multi-source data integration.Algorithms now increasingly employ deep learning,super image elements,and object-oriented methods to enhance flood identification accuracy.Recent studies focus on spatial and temporal changes in flooding,risk identification,and early warning for climate change-related flooding,including glacial melting and lake outbursts.Recommendations and perspectives To enhance monitoring accuracy and timeliness,UAV technology should be further utilized.Strengthening multi-source data fusion and assimilation is crucial,as is analyzing long-term flood disaster sequences to better understand their mechanisms.

Estimation and mapping of water erosion and soil loss:Application of Gavrilovic erosion potential model(EPM)using GIS and remote sensing in the Assif el mal Watershed,Western high Atlas

Water erosion is a serious problem that leads to soil degradation,loss,and the destruction of structures.Assessing the risk of erosion and determining the affected areas has become crucial in order to understand the main factors influencing its evolution and to minimize its impacts.This study focuses on evaluating the risk of erosion in the Assif el mal watershed,which is located in the High Atlas Mountains.The Erosion Potential Model(EPM)is used to estimate soil losses depending on various parameters such as lithology,hydrology,topography,and morphometry.Geographic information systems and remote sensing techniques are employed to map areas with high erosive potential and their relationship with the distribution of factors involved.Different digital elevation models are also used in this study to highlight the impact of data quality on the accuracy of the results.The findings reveal that approximately 59%of the total area in the Assif el mal basin has low to very low potential for soil losses,while 22%is moderately affected and 19.9%is at high to very high risk.It is therefore crucial to implement soil conservation measures to mitigate and prevent erosion risks.

Spatiotemporal Evolution of Ecological Quality in Typical Karst Ecologically Fragile Areas Based on Remote Sensing Ecological Indexes

Fast and effective remote sensing monitoring is an important means for analyzing the spatio-temporal changes in ecological quality in fragile karst regions.This study focuses on Guanling Autonomous County,a national-level demonstration county for comprehensive desertification control.Based on Landsat TM/OLI remote sensing image data from 2005,2010,2015,and 2020,remote sensing ecological indices were used to analyze the spatio-temporal changes in ecological quality in Guanling Autonomous County from 2005 to 2020.The results show that:①the variance contribution rates of the first principal component for the four periods were 66.31%,71.59%,63.18%,and 75.24%,indicating that PC1 integrated most of the characteristics of the four indices,making the RSEI suitable for evaluating ecological quality in karst mountain areas;②the remote sensing ecological index grades have been increasing year by year,with an overall trend of improving ecological quality.The area of higher-grade ecological quality has increased spatially,while fragmented patches have gradually decreased,becoming more concentrated in the low-altitude areas in the northwest and east,and there is a trend of expansion towards higher-altitude areas;③the ecological environment quality in most areas has improved,with the improvement in RSEI spatio-temporal variation becoming more noticeable with increasing slope.Areas of higher-grade quality appeared in 2010,and the range of higher-grade quality expanded with increasing slope.

摄影测量与遥感领域主题演化研究——以《ISPRS Journal of Photogrammetry and Remote Sensing》期刊为例

为了便于相关领域的研究人员了解遥感学领域的整体发展状态并进行量化分析,本文以国际摄影测量与遥感学会(ISPRS)官方刊物作为研究数据,从主题挖掘和主题关联的角度出发,在计量分析的基础上,基于隐含狄利克雷分布(LDA)和word2vec的主题演化模型进行分析与研究,重点解决了摄影测量与遥感学领域主题挖掘、学科领域主题关联、学科主题演化建模和主题演化知识图谱等问题,展示了遥感学领域的主题动态演化过程。主题演化研究结果表明:1)主题强度总排名前三的主题分别是激光扫描技术、摄影测量、遥感信息提取与分类;2)随着深度学习的深入发展,遥感学领域的深度学习相关应用研究热度逐渐攀升;3)环境遥感相关方向的研究热度相对稳定,演化关系多局限于相关研究内部。

Remote sensing of air pollution incorporating integrated-path differential-absorption and coherent-Doppler lidar

An innovative complex lidar system deployed on an airborne rotorcraft platform for remote sensing of atmospheric pollution is proposed and demonstrated.The system incorporates integrated-path differential absorption lidar(DIAL) and coherent-doppler lidar(CDL) techniques using a dual tunable TEA CO_(2)laser in the 9—11 μm band and a 1.55 μm fiber laser.By combining the principles of differential absorption detection and pulsed coherent detection,the system enables agile and remote sensing of atmospheric pollution.Extensive static tests validate the system’s real-time detection capabilities,including the measurement of concentration-path-length product(CL),front distance,and path wind speed of air pollution plumes over long distances exceeding 4 km.Flight experiments is conducted with the helicopter.Scanning of the pollutant concentration and the wind field is carried out in an approximately 1 km slant range over scanning angle ranges from 45°to 65°,with a radial resolution of 30 m and10 s.The test results demonstrate the system’s ability to spatially map atmospheric pollution plumes and predict their motion and dispersion patterns,thereby ensuring the protection of public safety.

Estimation and verification of green tide biomass based on UAV remote sensing

Since 2007,the Yellow Sea green tide has broken out every summer,causing great harm to the environment and society.Although satellite remote sensing(RS)has been used in biomass research,there are several shortcomings,such as mixed pixels,atmospheric interference,and difficult field validation.The biomass of green tide has been lacking a high-precision estimation method.In this study,high-resolution unmanned aerial vehicle(UAV)RS was used to quantitatively map the biomass of green tides.By utilizing experimental data from previous studies,a robust relationship was established to link biomass to the red-green-blue floating algae index(RGB-FAI).Then,the lab-based model for green tide biomass from visible images taken by the UAV camera was developed and validated by field measurements.Re sults show that the accurate and cost-effective method is able to estimate the green tide biomass and its changes in given local waters of the near and far seas.The study provided an effective complement to the traditional satellite RS,as well as high-precision quantitative techniques for decision-making in disaster management.

CrossFormer Embedding DeepLabv3+ for Remote Sensing Images Semantic Segmentation

High-resolution remote sensing image segmentation is a challenging task. In urban remote sensing, the presenceof occlusions and shadows often results in blurred or invisible object boundaries, thereby increasing the difficultyof segmentation. In this paper, an improved network with a cross-region self-attention mechanism for multi-scalefeatures based onDeepLabv3+is designed to address the difficulties of small object segmentation and blurred targetedge segmentation. First,we use CrossFormer as the backbone feature extraction network to achieve the interactionbetween large- and small-scale features, and establish self-attention associations between features at both large andsmall scales to capture global contextual feature information. Next, an improved atrous spatial pyramid poolingmodule is introduced to establish multi-scale feature maps with large- and small-scale feature associations, andattention vectors are added in the channel direction to enable adaptive adjustment of multi-scale channel features.The proposed networkmodel is validated using the PotsdamandVaihingen datasets. The experimental results showthat, compared with existing techniques, the network model designed in this paper can extract and fuse multiscaleinformation, more clearly extract edge information and small-scale information, and segment boundariesmore smoothly. Experimental results on public datasets demonstrate the superiority of ourmethod compared withseveral state-of-the-art networks.

Determining the planting year of navel orange trees in mountainous and hilly areas of southern China:a remote sensing based method

Remote sensing has demonstrated validity in determining the planting year of deciduous fruit trees;however,its effectiveness in ascertaining the planting year of evergreen fruit trees remains unverified.Furthermore,the sources of error associated with using remote sensing to determine the planting year of fruit trees remain unclear.This study investigates several cultivated sweet orange(Citrus sinensis)varieties,which are extensively cultivated throughout subtropical China.We analyzed Landsat time series data from 132 navel orange orchards in Gannan,covering the period from 1993 to 2021.For each orchard,Google Earth Engine was employed to extract three vegetation indices—Enhanced Vegetation Index(EVI),Normalized Difference Vegetation Index(NDVI),and Normalized Burn Ratio(NBR)—for each available date,thereby generating three distinct vegetation index time series.The planting year of navel orange trees was identified based on abrupt changes observed in these time series.The principal sources of error in determining the planting year were investigated using the Wilcoxon signed-rank test,Spearman's correlation analysis,and Kruskal-Wallis H test.Key findings include:(1)Following the planting of navel orange trees,EVI,NDVI,and NBR exhibited fluctuations and a gradual increase over time,peaking approximately 10 to 15 years later.(2)The vegetation index time series derived from Landsat imagery effectively determined the planting year of evergreen navel orange trees in orchards,even within highly fragmented landscapes.Among these indices,NDVI and NBR time series outperformed the EVI time series.Specifically,the average determination errors for EVI,NDVI,and NBR time series were 6.4,1.8,and 2.8 years,respectively.(3)Major sources of error included the methods used to construct the time series,the selection of vegetation indices,and the orchard management practices.Overall,this study provides a viable method for determining the planting year of evergreen navel orange trees in fragmented landscapes and offers insights into factors contributing to uncertainty in planting year determination.

Remote sensing of quality traits in cereal and arable production systems:A review

Cereal is an essential source of calories and protein for the global population.Accurately predicting cereal quality before harvest is highly desirable in order to optimise management for farmers,grading harvest and categorised storage for enterprises,future trading prices,and policy planning.The use of remote sensing data with extensive spatial coverage demonstrates some potential in predicting crop quality traits.Many studies have also proposed models and methods for predicting such traits based on multiplatform remote sensing data.In this paper,the key quality traits that are of interest to producers and consumers are introduced.The literature related to grain quality prediction was analyzed in detail,and a review was conducted on remote sensing platforms,commonly used methods,potential gaps,and future trends in crop quality prediction.This review recommends new research directions that go beyond the traditional methods and discusses grain quality retrieval and the associated challenges from the perspective of remote sensing data.

Quantifying glacier surging and associated lake dynamics in Amu Darya river basin using UAV and remote sensing data

Glaciers in the Pamir region are experiencing rapid melting and receding due to climate change,which has a significant implication for the Amu Darya river basin.Predominantly,surging glaciers,which undergo unpredictable advances,are potentially leading to the obstruction of high-altitude river channels and also glacial lake outburst floods.decrease of-703.5±30.0 m.There is a substantial increase in the number(from 19 to 75)and area(from 4889.7±0.6 m2 to 15345.5±0.6 m2)of RGS lakes along with supra-glacier ponds based on a comparison of ArcGIS base map in 2011 and high-resolution UAV data in 2023.For M glacier,number of lakes increased from 4 to 22 but the lake area declined from 10715.2±0.6 to 365.6±0.6 m2.It was noted that the largest lake in 2011 with an area of 10406.4±0.6 m2 at the southeastern portion of the glacier was not observed in 2023 due to outburst.Both the glaciers have substantially impacted the river flow(Abdukahor river)by obstructing a significant proportion of river channel in recent years and might cause outburst floods.These findings enhance the understanding of glacier dynamics and their impacts on the surrounding areas,emphasizing the urgent need for continued monitoring and appropriate management strategies,with a specific focus on surging glaciers and the associated risks.

Using ontology and rules to retrieve the semantics of disaster remote sensing data

Remote sensing data plays an important role in natural disaster management.However,with the increase of the variety and quantity of remote sensors,the problem of“knowledge barriers”arises when data users in disaster field retrieve remote sensing data.To improve this problem,this paper proposes an ontology and rule based retrieval(ORR)method to retrieve disaster remote sensing data,and this method introduces ontology technology to express earthquake disaster and remote sensing knowledge,on this basis,and realizes the task suitability reasoning of earthquake disaster remote sensing data,mining the semantic relationship between remote sensing metadata and disasters.The prototype system is built according to the ORR method,which is compared with the traditional method,using the ORR method to retrieve disaster remote sensing data can reduce the knowledge requirements of data users in the retrieval process and improve data retrieval efficiency.

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.

Untethered Micro/Nanorobots for Remote Sensing:Toward Intelligent Platform

Untethered micro/nanorobots that can wirelessly control their motion and deformation state have gained enormous interest in remote sensing applications due to their unique motion characteristics in various media and diverse functionalities.Researchers are developing micro/nanorobots as innovative tools to improve sensing performance and miniaturize sensing systems,enabling in situ detection of substances that traditional sensing methods struggle to achieve.Over the past decade of development,significant research progress has been made in designing sensing strategies based on micro/nanorobots,employing various coordinated control and sensing approaches.This review summarizes the latest developments on micro/nanorobots for remote sensing applications by utilizing the self-generated signals of the robots,robot behavior,microrobotic manipulation,and robot-environment interactions.Providing recent studies and relevant applications in remote sensing,we also discuss the challenges and future perspectives facing micro/nanorobots-based intelligent sensing platforms to achieve sensing in complex environments,translating lab research achievements into widespread real applications.

ConvNeXt-UperNet-Based Deep Learning Model for Road Extraction from High-Resolution Remote Sensing Images

When existing deep learning models are used for road extraction tasks from high-resolution images,they are easily affected by noise factors such as tree and building occlusion and complex backgrounds,resulting in incomplete road extraction and low accuracy.We propose the introduction of spatial and channel attention modules to the convolutional neural network ConvNeXt.Then,ConvNeXt is used as the backbone network,which cooperates with the perceptual analysis network UPerNet,retains the detection head of the semantic segmentation,and builds a new model ConvNeXt-UPerNet to suppress noise interference.Training on the open-source DeepGlobe and CHN6-CUG datasets and introducing the DiceLoss on the basis of CrossEntropyLoss solves the problem of positive and negative sample imbalance.Experimental results show that the new network model can achieve the following performance on the DeepGlobe dataset:79.40%for precision(Pre),97.93% for accuracy(Acc),69.28% for intersection over union(IoU),and 83.56% for mean intersection over union(MIoU).On the CHN6-CUG dataset,the model achieves the respective values of 78.17%for Pre,97.63%for Acc,65.4% for IoU,and 81.46% for MIoU.Compared with other network models,the fused ConvNeXt-UPerNet model can extract road information better when faced with the influence of noise contained in high-resolution remote sensing images.It also achieves multiscale image feature information with unified perception,ultimately improving the generalization ability of deep learning technology in extracting complex roads from high-resolution remote sensing images.

Modeling urban redevelopment:A novel approach using time-series remote sensing data and machine learning

Accurate mapping and timely monitoring of urban redevelopment are pivotal for urban studies and decisionmakers to foster sustainable urban development.Traditional mapping methods heavily depend on field surveys and subjective questionnaires,yielding less objective,reliable,and timely data.Recent advancements in Geographic Information Systems(GIS)and remote-sensing technologies have improved the identification and mapping of urban redevelopment through quantitative analysis using satellite-based observations.Nonetheless,challenges persist,particularly concerning accuracy and significant temporal delays.This study introduces a novel approach to modeling urban redevelopment,leveraging machine learning algorithms and remote-sensing data.This methodology can facilitate the accurate and timely identification of urban redevelopment activities.The study’s machine learning model can analyze time-series remote-sensing data to identify spatio-temporal and spectral patterns related to urban redevelopment.The model is thoroughly evaluated,and the results indicate that it can accurately capture the time-series patterns of urban redevelopment.This research’s findings are useful for evaluating urban demographic and economic changes,informing policymaking and urban planning,and contributing to sustainable urban development.The model can also serve as a foundation for future research on early-stage urban redevelopment detection and evaluation of the causes and impacts of urban redevelopment.

Probability-Enhanced Anchor-Free Detector for Remote-Sensing Object Detection

Anchor-free object-detection methods achieve a significant advancement in field of computer vision,particularly in the realm of real-time inferences.However,in remote sensing object detection,anchor-free methods often lack of capability in separating the foreground and background.This paper proposes an anchor-free method named probability-enhanced anchor-free detector(ProEnDet)for remote sensing object detection.First,a weighted bidirectional feature pyramid is used for feature extraction.Second,we introduce probability enhancement to strengthen the classification of the object’s foreground and background.The detector uses the logarithm likelihood as the final score to improve the classification of the foreground and background of the object.ProEnDet is verified using the DIOR and NWPU-VHR-10 datasets.The experiment achieved mean average precisions of 61.4 and 69.0 on the DIOR dataset and NWPU-VHR-10 dataset,respectively.ProEnDet achieves a speed of 32.4 FPS on the DIOR dataset,which satisfies the real-time requirements for remote-sensing object detection.

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.