scholarly journals Remote Sensing Data Detection Based on Multiscale Fusion and Attention Mechanism

2021 ◽  
Vol 2021 ◽  
pp. 1-12
Author(s):  
Min Huang ◽  
Cong Cheng ◽  
Gennaro De Luca
Keyword(s):  
Remote Sensing ◽  
Multiple Scales ◽  
Remote Sensing Data ◽  
Image Data ◽  
Attention Mechanism ◽  
Context Information ◽  
Data Detection ◽  
Feature Maps ◽  
Feature Map ◽  
Main Challenge

Remote sensing images are often of low quality due to the limitations of the equipment, resulting in poor image accuracy, and it is extremely difficult to identify the target object when it is blurred or small. The main challenge is that objects in sensing images have very few pixels. Traditional convolutional networks are complicated to extract enough information through local convolution and are easily disturbed by noise points, so they are usually not ideal for classifying and diagnosing small targets. The current solution is to process the feature map information at multiple scales, but this method does not consider the supplementary effect of the context information of the feature map on the semantics. In this work, in order to enable CNNs to make full use of context information and improve its representation ability, we propose a residual attention function fusion method, which improves the representation ability of feature maps by fusing contextual feature map information of different scales, and then propose a spatial attention mechanism for global pixel point convolution response. This method compresses global pixels through convolution, weights the original feature map pixels, reduces noise interference, and improves the network’s ability to grasp global critical pixel information. In experiments, the remote sensing ship image recognition experiments on remote sensing image data sets show that the network structure can improve the performance of small-target detection. The results on cifar10 and cifar100 prove that the attention mechanism is universal and practical.

scholarly journals ℱ3-Net: Feature Fusion and Filtration Network for Object Detection in Optical Remote Sensing Images

2020 ◽  
Vol 12 (24) ◽  
pp. 4027
Author(s):  
Xinhai Ye ◽  
Fengchao Xiong ◽  
Jianfeng Lu ◽  
Jun Zhou ◽  
Yuntao Qian
Keyword(s):  
Remote Sensing ◽  
Object Detection ◽  
Multiple Scales ◽  
Feature Fusion ◽  
Dimensional Subspace ◽  
Context Information ◽  
Optical Remote Sensing ◽  
Feature Maps ◽  
Residual Structure ◽  
Cluttered Background

Object detection in remote sensing (RS) images is a challenging task due to the difficulties of small size, varied appearance, and complex background. Although a lot of methods have been developed to address this problem, many of them cannot fully exploit multilevel context information or handle cluttered background in RS images either. To this end, in this paper, we propose a feature fusion and filtration network (F3-Net) to improve object detection in RS images, which has higher capacity of combining the context information at multiple scales while suppressing the interference from the background. Specifically, F3-Net leverages a feature adaptation block with a residual structure to adjust the backbone network in an end-to-end manner, better considering the characteristics of RS images. Afterward, the network learns the context information of the object at multiple scales by hierarchically fusing the feature maps from different layers. In order to suppress the interference from cluttered background, the fused feature is then projected into a low-dimensional subspace by an additional feature filtration module. As a result, more relevant and accurate context information is extracted for further detection. Extensive experiments on DOTA, NWPU VHR-10, and UCAS AOD datasets demonstrate that the proposed detector achieves very promising detection performance.

scholarly journals Person Re-Identification Based on Attention Mechanism and Context Information Fusion

2021 ◽  
Vol 13 (3) ◽  
pp. 72
Author(s):  
Shengbo Chen ◽  
Hongchang Zhang ◽  
Zhou Lei
Keyword(s):  
Information Fusion ◽  
Irrelevant Information ◽  
Features Extraction ◽  
Attention Mechanism ◽  
Cross Entropy ◽  
Context Information ◽  
Feature Map ◽  
High Level ◽  
Surveillance Analysis ◽  
High Level Feature

Person re-identification (ReID) plays a significant role in video surveillance analysis. In the real world, due to illumination, occlusion, and deformation, pedestrian features extraction is the key to person ReID. Considering the shortcomings of existing methods in pedestrian features extraction, a method based on attention mechanism and context information fusion is proposed. A lightweight attention module is introduced into ResNet50 backbone network equipped with a small number of network parameters, which enhance the significant characteristics of person and suppress irrelevant information. Aiming at the problem of person context information loss due to the over depth of the network, a context information fusion module is designed to sample the shallow feature map of pedestrians and cascade with the high-level feature map. In order to improve the robustness, the model is trained by combining the loss of margin sample mining with the loss function of cross entropy. Experiments are carried out on datasets Market1501 and DukeMTMC-reID, our method achieves rank-1 accuracy of 95.9% on the Market1501 dataset, and 90.1% on the DukeMTMC-reID dataset, outperforming the current mainstream method in case of only using global feature.

scholarly journals Improved YOLO Network for Free-Angle Remote Sensing Target Detection

2021 ◽  
Vol 13 (11) ◽  
pp. 2171
Author(s):  
Yuhao Qing ◽  
Wenyi Liu ◽  
Liuyan Feng ◽  
Wanjia Gao
Keyword(s):  
Remote Sensing ◽  
Feature Extraction ◽  
Target Detection ◽  
Multiple Scales ◽  
Classification Problem ◽  
Input Image ◽  
Detection Accuracy ◽  
Feature Maps ◽  
Regression Problem ◽  
Public Datasets

Despite significant progress in object detection tasks, remote sensing image target detection is still challenging owing to complex backgrounds, large differences in target sizes, and uneven distribution of rotating objects. In this study, we consider model accuracy, inference speed, and detection of objects at any angle. We also propose a RepVGG-YOLO network using an improved RepVGG model as the backbone feature extraction network, which performs the initial feature extraction from the input image and considers network training accuracy and inference speed. We use an improved feature pyramid network (FPN) and path aggregation network (PANet) to reprocess feature output by the backbone network. The FPN and PANet module integrates feature maps of different layers, combines context information on multiple scales, accumulates multiple features, and strengthens feature information extraction. Finally, to maximize the detection accuracy of objects of all sizes, we use four target detection scales at the network output to enhance feature extraction from small remote sensing target pixels. To solve the angle problem of any object, we improved the loss function for classification using circular smooth label technology, turning the angle regression problem into a classification problem, and increasing the detection accuracy of objects at any angle. We conducted experiments on two public datasets, DOTA and HRSC2016. Our results show the proposed method performs better than previous methods.

scholarly journals Remote Sensing Road Extraction by Road Segmentation Network

2021 ◽  
Vol 11 (11) ◽  
pp. 5050
Author(s):  
Jiahai Tan ◽  
Ming Gao ◽  
Kai Yang ◽  
Tao Duan
Keyword(s):  
Remote Sensing ◽  
Attention Mechanism ◽  
Context Information ◽  
Road Extraction ◽  
Remote Sensing Images ◽  
Long Distance ◽  
The Road ◽  
Road Segmentation ◽  
Context Characteristics

Road extraction from remote sensing images has attracted much attention in geospatial applications. However, the existing methods do not accurately identify the connectivity of the road. The identification of the road pixels may be interfered with by the abundant ground such as buildings, trees, and shadows. The objective of this paper is to enhance context and strip features of the road by designing UNet-like architecture. The overall method first enhances the context characteristics in the segmentation step and then maintains the stripe characteristics in a refinement step. The segmentation step exploits an attention mechanism to enhance the context information between the adjacent layers. To obtain the strip features of the road, the refinement step introduces the strip pooling in a refinement network to restore the long distance dependent information of the road. Extensive comparative experiments demonstrate that the proposed method outperforms other methods, achieving an overall accuracy of 98.25% on the DeepGlobe dataset, and 97.68% on the Massachusetts dataset.

scholarly journals Predicting Microhabitat Suitability for an Endangered Small Mammal Using Sentinel-2 Data

2020 ◽  
Vol 12 (3) ◽  
pp. 562 ◽  
Author(s):  
Francesco Valerio ◽  
Eduardo Ferreira ◽  
Sérgio Godinho ◽  
Ricardo Pita ◽  
António Mira ◽  
...  
Keyword(s):  
Remote Sensing ◽  
Landscape Heterogeneity ◽  
Remote Sensing Data ◽  
Predictive Distribution ◽  
Distribution Models ◽  
Explanatory Variables ◽  
Habitat Features ◽  
Main Challenge ◽  
Cabrera Vole ◽  
Sentinel 2

Accurate mapping is a main challenge for endangered small-sized terrestrial species. Freely available spatio-temporal data at high resolution from multispectral satellite offer excellent opportunities for improving predictive distribution models of such species based on fine-scale habitat features, thus making it easier to achieve comprehensive biodiversity conservation goals. However, there are still few examples showing the utility of remote-sensing-based products in mapping microhabitat suitability for small species of conservation concern. Here, we address this issue using Sentinel-2 sensor-derived habitat variables, used in combination with more commonly used explanatory variables (e.g., topography), to predict the distribution of the endangered Cabrera vole (Microtus cabrerae) in agrosilvopastorial systems. Based on vole surveys conducted in two different seasons over a ~176,000 ha landscape in Southern Portugal, we assessed the significance of each predictor in explaining Cabrera vole occurrence using the Boruta algorithm, a novel Random forest variant for dealing with high dimensionality of explanatory variables. Overall, results showed a strong contribution of Sentinel-2-derived variables for predicting microhabitat suitability of Cabrera voles. In particular, we found that photosynthetic activity (NDI45), specific spectral signal (SWIR1), and landscape heterogeneity (Rao’s Q) were good proxies of Cabrera voles’ microhabitat, mostly during temporally greener and wetter conditions. In addition to remote-sensing-based variables, the presence of road verges was also an important driver of voles’ distribution, highlighting their potential role as refuges and/or corridors. Overall, our study supports the use of remote-sensing data to predict microhabitat suitability for endangered small-sized species in marginal areas that potentially hold most of the biodiversity found in human-dominated landscapes. We believe our approach can be widely applied to other species, for which detailed habitat mapping over large spatial extents is difficult to obtain using traditional descriptors. This would certainly contribute to improving conservation planning, thereby contributing to global conservation efforts in landscapes that are managed for multiple purposes.

scholarly journals Toward a Standardized Encoding of Remote Sensing Geo-Positioning Sensor Models

2020 ◽  
Vol 12 (9) ◽  
pp. 1530
Author(s):  
Meng Jin ◽  
Yuqi Bai ◽  
Emmanuel Devys ◽  
Liping Di
Keyword(s):  
Remote Sensing ◽  
Remote Sensing Data ◽  
Image Data ◽  
Xml Schema ◽  
Data Interoperability ◽  
Sensing Data ◽  
Sensor Model ◽  
Application Systems ◽  
Extensible Markup ◽  
Sensor Models

Geolocation information is an important feature of remote sensing image data that is captured through a variety of passive or active observation sensors, such as push-broom electro-optical sensor, synthetic aperture radar (SAR), light detection and ranging (LIDAR) and sound navigation and ranging (SONAR). As a fundamental processing step to locate an image, geo-positioning is used to determine the ground coordinates of an object from image coordinates. A variety of sensor models have been created to describe geo-positioning process. In particular, Open Geospatial Consortium (OGC) has defined the Sensor Model Language (SensorML) specification in its Sensor Web Enablement (SWE) initiative to describe sensors including the geo-positioning process. It has been realized using syntax from the extensible markup language (XML). Besides, two standards defined by the International Organization for Standardization (ISO), ISO 19130-1 and ISO 19130-2, introduced a physical sensor model, a true replacement model, and a correspondence model for the geo-positioning process. However, a standardized encoding for geo-positioning sensor models is still missing for the remote sensing community. Thus, the interoperability of remote sensing data between application systems cannot be ensured. In this paper, a standardized encoding of remote sensing geo-positioning sensor models is introduced. It is semantically based on ISO 19130-1 and ISO 19130-2, and syntactically based on OGC SensorML. It defines a cross mapping of the sensor models defined in ISO 19130-1 and ISO 19130-2 to the SensorML, and then proposes a detailed encoding method to finalize the XML schema (an XML schema here is the structure to define an XML document), which will become a profile of OGC SensorML. It seamlessly unifies the sensor models defined in ISO 19130-1, ISO 19130-2, and OGC SensorML. By enabling a standardized description of sensor models used to produce remote sensing data, this standard is very promising in promoting data interoperability, mobility, and integration in the remote sensing domain.

scholarly journals The Use of Spot-HRV Data for the Mapping of the Land Cover (applied upon East-Mono, Central Togo)

Afrika Focus ◽  
1991 ◽  
Vol 7 (1) ◽  
Author(s):  
Beata Maria De Vliegher
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Land Cover ◽  
Image Interpretation ◽  
Remote Sensing Data ◽  
Image Data ◽  
Visual Image ◽  
Data Set ◽  
Land Cover Map ◽  
Colour Composite

The mapping of the land use in a tropical wet and dry area (East-Mono, Central Togo) is made using remote sensing data, recorded by the satellite SPOT. The negative, multispectral image data set has been transferred into positives by photographical means and afterwards enhanced using the diazo technique. The combination of the different diazo coloured images resulted in a false colour composite, being the basic document for the visual image interpretation. The image analysis, based upon differences in colour and texture, resulted in a photomorphic unit map. The use of a decision tree including the various image characteristics allowed the conversion of the photomorphic unit map into a land cover map. For this, six main land cover types could be differentiated resulting in 16 different classes of the final map. KEY WORDS :Remote sensing, SPOT, Multispectral view, Visual image interpre- tation, Mapping, Vegetation, Land use, Togo. 

scholarly journals DINAMIKA PERUBAHAN GARIS PANTAI DI PESISIR DESA SURODADI KECAMATAN SAYUNG DENGAN MENGGUNAKAN CITRA SATELIT (Dynamics of Coastal Line Changes in the Surodadi Village of Sayung Sub District by Using Satellite Imagery)

2018 ◽  
Vol 6 (4) ◽  
pp. 433-441
Author(s):  
Aulia Huda Riyanti ◽  
Agung Suryanto ◽  
Churun Ain
Keyword(s):  
Remote Sensing ◽  
Land Cover ◽  
Sea Water ◽  
Satellite Image ◽  
Remote Sensing Data ◽  
Image Data ◽  
Rate Of Change ◽  
Research Station ◽  
Shoreline Changes ◽  
Coastline Change

Garis pantai Desa Surodadi mengalami perubahan dari tahun ke tahun. Perubahan yang serius ini perlu untuk dilakukan pemantauan terus menerus. Penelitian ini dilakukan untuk memperoleh informasi tentang perubahan garis pantai dan kaitannya dengan tutupan lahan di pesisir Desa Surodadi Kecamatan Sayung Kabupaten Demak pada tahun 2015 dan 2016. Penelitian ini dilaksanakan pada bulan Mei sampai dengan Juni 2017. Stasiun penelitian dibagi menjadi lima stasiun berdasarkan lokasi abrasi dan akresi yang telah terjadi. Dengan proses overlay kedua data citra satelit melalui sistem informasi geografis merupakan cara cepat untuk mengetahui perubahan garis pantai yang terjadi pada pesisir Desa Surodadi. Metode penelitian ini dengan menggunakan metode deskriptif studi kasus dengan menggunakan teknologi penginderaan jauh pada pengolahan data citra SPOT 6 tahun 2015 dan tahun 2016 yang diperoleh dari Pusat Teknologi dan Data Penginderaan Jauh LAPAN Jakarta serta dilakukan survei lapangan sehingga diperoleh laju perubahan garis pantai serta tutupan lahan yang terdapat pada lokasi penelitian. Garis pantai yang terjadi dari tahun 2015 sampai tahun 2016 lebih banyak mengalami proses abrasi jika dibandingkan proses akresi. Berdasarkan hasil penelitian dapat diketahui laju perubahan panjang garis pantai sebesar 103,58 m, perubahan garis pantai yang terjadi berupa abrasi sebesar 1,197 ha dan perubahan yang berupa akresi sebesar 0,490 ha. Keterkaitan antara perubahan garis pantai dengan tutupan lahan di Desa Surodadi adalah tutupan mangrove yang ada cukup luas dan relatif rapat sehingga dapat mencegah intrusi air laut yang dapat menyebabkan perubahan garis pantai. Surodadi village coastline changes from year to year. This serious change is necessary for ongoing monitoring. This research was conducted to obtain information about coastline change and its relation to land cover in coastal village of Surodadi Sub-District of Sayung Regency of Demak in 2015 until 2016. This research was conducted from May to June 2017. The research station is divided into five stations based on the location of abrasion and Accretion that has occurred. With the second overlay process satellite image data through geographic information system is a quick way to find out the shoreline changes that occur in the coastal village of Surodadi. This research method is done by using descriptive method of case study by using remote sensing technology on SPOT image data processing of 6 year 2015 and year 2016 which obtained from Center of Technology and Remote Sensing Data of LAPAN Jakarta and conducted field survey so that obtained rate of change of coastline happened also Land cover located at the research location. Coastlines that occur from 2015 to 2016 more experienced abrasion process when compared to the accretion process. Based on the research results can be seen the rate of change of coastline length of 103.58 m, shoreline changes that occur in the form of abrasion of 1.197 ha and changes in the form of accretion of 0.490 ha. The link between coastline change and land cover in Surodadi Village is that the mangrove cover is wide enough and relatively close so it can prevent the intrusion of sea water which can cause coastline changes.

scholarly journals Research On The Classification Of High Resolution Image Based On Object-oriented And Class Rule

2015 ◽  
Vol XL-7/W4 ◽  
pp. 75-80 ◽  
Author(s):  
C. K. Li ◽  
W. Fang ◽  
X. J. Dong
Keyword(s):  
Remote Sensing ◽  
High Resolution ◽  
Image Classification ◽  
Object Oriented ◽  
Remote Sensing Data ◽  
Image Data ◽  
Remote Sensing Image ◽  
Classification Method ◽  
Multi Level ◽  
Image Object

With the development of remote sensing technology, the spatial resolution, spectral resolution and time resolution of remote sensing data is greatly improved. How to efficiently process and interpret the massive high resolution remote sensing image data for ground objects, which with spatial geometry and texture information, has become the focus and difficulty in the field of remote sensing research. An object oriented and rule of the classification method of remote sensing data has presents in this paper. Through the discovery and mining the rich knowledge of spectrum and spatial characteristics of high-resolution remote sensing image, establish a multi-level network image object segmentation and classification structure of remote sensing image to achieve accurate and fast ground targets classification and accuracy assessment. Based on worldview-2 image data in the Zangnan area as a study object, using the object-oriented image classification method and rules to verify the experiment which is combination of the mean variance method, the maximum area method and the accuracy comparison to analysis, selected three kinds of optimal segmentation scale and established a multi-level image object network hierarchy for image classification experiments. The results show that the objectoriented rules classification method to classify the high resolution images, enabling the high resolution image classification results similar to the visual interpretation of the results and has higher classification accuracy. The overall accuracy and Kappa coefficient of the object-oriented rules classification method were 97.38%, 0.9673; compared with object-oriented SVM method, respectively higher than 6.23%, 0.078; compared with object-oriented KNN method, respectively more than 7.96%, 0.0996. The extraction precision and user accuracy of the building compared with object-oriented SVM method, respectively higher than 18.39%, 3.98%, respectively better than the object-oriented KNN method 21.27%, 14.97%.

scholarly journals THE EFFECT OF DIFFERENT ATMOSPHERIC CORRECTIONS ON BATHYMETRY EXTRACTION USING LANDSAT 8 SATELLITE IMAGERY

2017 ◽  
Vol 12 (1) ◽  
pp. 13 ◽  
Author(s):  
Kuncoro Teguh Setiawan ◽  
Yennie Marini ◽  
Johannes Manalu ◽  
Syarif Budhiman
Keyword(s):  
Remote Sensing ◽  
Satellite Image ◽  
Atmospheric Correction ◽  
Remote Sensing Data ◽  
Image Data ◽  
Landsat 8 ◽  
Calculation Error ◽  
Sensing Technology ◽  
The Difference ◽  
Landsat Satellite

Remote sensing technology can be used to obtain information bathymetry. Bathymetric information plays an important role for fisheries, hydrographic and navigation safety. Bathymetric information derived from remote sensing data is highly dependent on the quality of satellite data use and processing. One of the processing to be done is the atmospheric correction process. The data used in this study is Landsat 8 image obtained on June 19, 2013. The purpose of this study was to determine the effect of different atmospheric correction on bathymetric information extraction from Landsat satellite image data 8. The atmospheric correction methods applied were the minimum radiant, Dark Pixels and ATCOR. Bathymetry extraction result of Landsat 8 uses a third method of atmospheric correction is difficult to distinguish which one is best. The calculation of the difference extraction results was determined from regression models and correlation coefficient value calculation error is generated.

Sign in / Sign up

Export Citation Format

Share Document