182 Hits in 5.3 sec

Enhanced Feature Representation in Detection for Optical Remote Sensing Images

Kun Fu, Zhuo Chen, Yue Zhang, Xian Sun
2019 Remote Sensing  
In recent years, deep learning has led to a remarkable breakthrough in object detection in remote sensing images.  ...  The former efficiently utilizes multi-scale features from multiple layers of the backbone network.  ...  Acknowledgments: The authors would like to thank all colleagues in the lab, who are willing to give useful opinions.  ... 
doi:10.3390/rs11182095 fatcat:jomvmjnoqvcb3gjrbwzuxlh5xy

Image Enhancement Driven by Object Characteristics and Dense Feature Reuse Network for Ship Target Detection in Remote Sensing Imagery

Ling Tian, Yu Cao, Bokun He, Yifan Zhang, Chu He, Deshi Li
2021 Remote Sensing  
As the application scenarios of remote sensing imagery (RSI) become richer, the task of ship detection from an overhead perspective is of great significance.  ...  generative adversarial network (GAN), we designed an image enhancement module driven by object characteristics, which improves the quality of the ship target in the images while augmenting the training  ...  [20] proposed a rotating dense feature pyramid network (R-DFPN), which uses the rotated anchor with improved Faster RCNN to detect small targets in remote sensing images.  ... 
doi:10.3390/rs13071327 fatcat:phazoirsb5cfbajmwnbldx25lu

Extraction of Agricultural Fields via DASFNet with Dual Attention Mechanism and Multi-scale Feature Fusion in South Xinjiang, China

Rui Lu, Nan Wang, Yanbin Zhang, Yeneng Lin, Wenqiang Wu, Zhou Shi
2022 Remote Sensing  
This paper proposed a deep neural network with a dual attention mechanism and a multi-scale feature fusion (Dual Attention and Scale Fusion Network, DASFNet) to extract the cropland from a GaoFen-2 (GF  ...  Quick and accurate identification of agricultural fields from the remote sensing images is a crucial task in digital and precision agriculture.  ...  In addition to the optical remote sensing features, meteorological and geological clues can be augmented in the cropland extraction to improve the accuracy and credibility of the remote sensing image analysis  ... 
doi:10.3390/rs14092253 fatcat:z2aqg34ztfhmljh6ejytqbxini

Landslide Extraction from High-Resolution Remote Sensing Imagery Using Fully Convolutional Spectral–Topographic Fusion Network

Wei Xia, Jun Chen, Jianbo Liu, Caihong Ma, Wei Liu
2021 Remote Sensing  
In this study, comprehensive research was carried out on the landslide features of high-resolution remote sensing images on the Mangkam dataset.  ...  In this paper, a high-resolution remote sensing image classification method based on a fully convolutional network was used to extract the landslide information, thereby realizing the accurate extraction  ...  Based on the integration of multi-scale features and contextual information in remote sensing pixel-level semantic classification, the RAE-D network structure of the RGB image feature was used in this  ... 
doi:10.3390/rs13245116 fatcat:mrppmxgicbcdrkrheyptqf2oqi

Deep network based on up and down blocks using wavelet transform and successive multi-scale spatial attention for cloud detection

Jing Zhang, Hui Wang, Yuchen Wang, Qin Zhou, Yunsong Li
2021 Remote Sensing of Environment  
In our method, a deep network is used to learn the multi-scale global features so that the high-level semantic information obtained in the process of feature learning is integrated with the low-level spatial  ...  In addition, we have also utilized dark channel prior and designed a Successive Multi-scale Spatial Attention Module by adding attention mechanisms to multi-scale feature maps in the network in order to  ...  Introduction Clouds in optical remote-sensing images are inevitable and limit the development of the imagery for ground information extraction.  ... 
doi:10.1016/j.rse.2021.112483 fatcat:ceiwzatddfb75a52k65kvcxtkq

MCCRNet: A Multi-Level Change Contextual Refinement Network for Remote Sensing Image Change Detection

Qingtian Ke, Peng Zhang
2021 ISPRS International Journal of Geo-Information  
Change detection based on bi-temporal remote sensing images has made significant progress in recent years, aiming to identify the changed and unchanged pixels between a registered pair of images.  ...  Here we propose a multi-level change contextual refinement network (MCCRNet) to strengthen the multi-level change representations of feature pairs.  ...  Conclusions In this work, we have proposed an end-to-end network named a multi-level change contextual refinement network (MCCRNet) for remote sensing image change detection.  ... 
doi:10.3390/ijgi10090591 fatcat:daca5l2hbjchbjnmeowuxy37je

A deep neural network for oil spill semantic segmentation in SAR images

Georgios Orfanidis, Konstantinos Ioannidis, Konstantinos Avgerinakis, Stefanos Vrochidis, Ioannis Kompatsiaris
2018 Zenodo  
Previous studies, including neural networks, have shown that the use of satellite Synthetic Aperture Radar (SAR) can effectively identify oil spills over sea surfaces in any environmental conditions and  ...  The deployed CNN was trained using multiple SAR images acquired from the sentinel-1 satellite provided by ESA and based on EMSA records for maritime pollution events.  ...  Despite their ability to sufficiently represent scale by trained on multi-resolution images, DCNNs' competence for object scale can still be improved to detect both large and small objects.  ... 
doi:10.5281/zenodo.3497132 fatcat:oxnuf2o5gndorhxcz4jpxz4wd4

Geospatial Contextual Attention Mechanism for Automatic and Fast Airport Detection in SAR Imagery

Siyu Tan, Lifu Chen, Zhouhao Pan, Jin Xing, Zhenhong Li, Zhihui Yuan
2020 IEEE Access  
The structure of improved ResNet_101 (b)Multi-scale Squeeze Pyramid Multi-scale Squeeze Pyramid (MSP) is a new proposed network module in the paper.  ...  Existing research of airport detection is mostly based on optical remote sensing images [5] [6] .  ...  In conclusion, GCAM is proposed in this paper to implement runway areas detection of the airport, which can fully extract geospatial features and edge features to achieve fast and automatic detection of  ... 
doi:10.1109/access.2020.3024546 fatcat:gbj4ihg44fct7hdfha5gimp3hu

Height estimation from single aerial images using a deep ordinal regression network [article]

Xiang Li, Mingyang Wang, Yi Fang
2020 arXiv   pre-print
To enable multi-scale feature extraction, we further incorporate an Atrous Spatial Pyramid Pooling (ASPP) module to extract features from multiple dilated convolution layers.  ...  Understanding the 3D geometric structure of the Earth's surface has been an active research topic in photogrammetry and remote sensing community for decades, serving as an essential building block for  ...  To further enable multi-scale feature learning, we apply an Atrous Spatial Pyramid Pooling (ASPP) module to combine features at different scales and keep the same resolutions for them.  ... 
arXiv:2006.02801v1 fatcat:5ilruweznrhatct5kqgoa4w6vm

Geospatial Object Detection in Remote Sensing Imagery Based on Multiscale Single-Shot Detector with Activated Semantics

Shiqi Chen, Ronghui Zhan, Jun Zhang
2018 Remote Sensing  
Multi-scale Convolutional Neural Networks (MS-CNN) [31] and Feature Pyramid Networks (FPN) [32] adopts the multi-scale feature pyramid form and fuse the output detection in the end.  ...  Geospatial object detection from high spatial resolution (HSR) remote sensing imagery is a heated and challenging problem in the field of automatic image interpretation.  ...  Remote Sens. 2018, 10, 820  ... 
doi:10.3390/rs10060820 fatcat:32n6fpvqx5fyvoh3viizllp76q

Multiscale Object Detection in Remote Sensing Images Combined with Multi-Receptive-Field Features and Relation-Connected Attention

Jiahang Liu, Donghao Yang, Fei Hu
2022 Remote Sensing  
In recent years, with the development of deep convolutional neural networks, object detection in remote sensing images has made great improvements.  ...  To solve these problems, a novel object detection algorithm based on multi-receptive-field features and relation-connected attention is proposed for remote sensing images to achieve more accurate detection  ...  Optical remote sensing images play a vital part in object detection, which is a valuable supplement to object detection in SAR images.  ... 
doi:10.3390/rs14020427 fatcat:5lsplczy7ndrxlcpnac7gfgthy

ADT-Det: Adaptive Dynamic Refined Single-Stage Transformer Detector for Arbitrary-Oriented Object Detection in Satellite Optical Imagery

Yongbin Zheng, Peng Sun, Zongtan Zhou, Wanying Xu, Qiang Ren
2021 Remote Sensing  
The detection of arbitrary-oriented and multi-scale objects in satellite optical imagery is an important task in remote sensing and computer vision.  ...  Firstly, we propose a feature pyramid transformer (FPT) to enhance feature extraction of the rotated object detection framework through a feature interaction mechanism.  ...  In many DCNN-based object detection frameworks, FPN is a basic component used to extract multi-level features for detecting objects at different scales.  ... 
doi:10.3390/rs13132623 fatcat:vvp6w75nwvbjrn5cyzcrkgy65i

Fine Building Segmentation in High-Resolution SAR Images via Selective Pyramid Dilated Network

Hao Jing, Xian Sun, Zhirui Wang, Kaiqiang Chen, Wenhui Diao, Kun Fu
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The fully convolutional network and other variants are widely transferred to the SAR studies because of their high precision in optical images.  ...  In this paper, a unified framework called selective spatial pyramid dilated (SSPD) network is proposed for the fine building segmentation in SAR images.  ...  ACKNOWLEDGMENT The authors would like to thank all colleagues in the lab for generously providing their raw data and helping to annotate the images.  ... 
doi:10.1109/jstars.2021.3076085 fatcat:3gzb3c2jbfaxnfnzayoteofmcq

A Slimmer Network with Polymorphic and Group Attention Modules for More Efficient Object Detection in Aerial Images

Wei Guo, Weihong Li, Zhenghao Li, Weiguo Gong, Jinkai Cui, Xinran Wang
2020 Remote Sensing  
Firstly, we design a polymorphic module (PM) for simultaneously learning the multi-scale and multi-shape object features, so as to better detect the hugely different objects in aerial images.  ...  multi-scale and multi-shape object characteristics in aerial images, which may lead to some missing or false detections; (2) high precision detection generally requires a large and complex network structure  ...  Remote Sens. 2020, 12, 3750  ... 
doi:10.3390/rs12223750 fatcat:3fek2povbzhzdc3myxvjk3qb6u

Extracting Raft Aquaculture Areas from Remote Sensing Images via an Improved U-Net with a PSE Structure

Binge Cui, Dong Fei, Guanghui Shao, Yan Lu, Jialan Chu
2019 Remote Sensing  
The fully convolutional network (FCN) based methods have made great progress in the field of remote sensing in recent years.  ...  However, due to the complexity of the marine aquaculture environment, the boundaries of the raft aquaculture areas in remote sensing images are often blurred, which will result in 'adhesion' phenomenon  ...  Conclusions In this paper, based on the FCN model, we proposed an improved U-Net with a PSE structure (UPS-Net) for raft aquaculture areas extraction from high resolution optical remote sensing images.  ... 
doi:10.3390/rs11172053 fatcat:mj2bsnwkorcddis4e7qd5oevba
« Previous Showing results 1 — 15 out of 182 results