123 Hits in 7.5 sec

Fully Convolutional Networks for Dense Semantic Labelling of High-Resolution Aerial Imagery [article]

Jamie Sherrah
2016 arXiv   pre-print
In this work, deep convolutional neural networks (CNNs) are applied to semantic labelling of high-resolution remote sensing data.  ...  The trend towards higher resolution remote sensing imagery facilitates a transition from land-use classification to object-level scene understanding.  ...  Related Work There has been a significant amount of past work on classification and segmentation of remote sensing imagery, for a recent review see [1, 10] .  ... 
arXiv:1606.02585v1 fatcat:7hqpmybmh5gtvnh6guhyx3u4ry

Automatic Discovery and Geotagging of Objects from Street View Imagery

Vladimir Krylov, Eamonn Kenny, Rozenn Dahyot
2018 Remote Sensing  
In this paper we propose to automatically detect and compute the GPS coordinates of recurring stationary objects of interest using street view imagery.  ...  To geolocate all the detected objects coherently we propose a novel custom Markov Random Field model to perform objects triangulation.  ...  and image processing for the purposes of network planning and maintenance.  ... 
doi:10.3390/rs10050661 fatcat:yrxcaadxlngobei44io3a33dem

City-Scale Road Extraction from Satellite Imagery v2: Road Speeds and Travel Times [article]

Adam Van Etten
2020 arXiv   pre-print
Automated road network extraction from remote sensing imagery remains a significant challenge despite its importance in a broad array of applications.  ...  ), which is not possible with existing remote sensing imagery based methods.  ...  Acknowledgments We thank Nick Weir, Jake Shermeyer, and Ryan Lewis for their insight, assistance, and feedback.  ... 
arXiv:1908.09715v3 fatcat:se6shcj34vbipb4hbjktv73lfu

UAS Imagery and Computer Vision for Site-Specific Weed Control in Corn [article]

Ranjan Sapkota, Paulo Flores
2022 arXiv   pre-print
In order to reduce the amount of chemicals, we used drone based high-resolution imagery and computer-vision techniwue to perform site-specific weed control in corn.  ...  Currently, weed control in a corn field is performed by a blanket application of herbicides which do not consider spatial distribution information of weeds and also uses an extensive amount of chemical  ...  This research was funded by North Dakota Corn Council (NDCC) and NDSU Agricultural Experiment Station. We thank Carrington Research Extension Center (CREC) for providing land for experimental use.  ... 
arXiv:2204.12417v2 fatcat:l7nwftf3inbqvkvgicnoyfxze4

Cluster-Based Spectral-Spatial Segmentation of Hyperspectral Imagery

Sean M. Kennedy, William Williamson, James W. Scrofani
2019 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)  
Information Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302, and to the Office of Management and Budget, Paperwork Reduction Project (0704-0188) Washington, DC  ...  the data needed, and completing and reviewing the collection of information.  ...  This situation is related to a common scene type in remotely sensed imagery: a small number of "targets" (e.g., vehicles) surrounded by a common background (e.g., pavement, or grass).  ... 
doi:10.1109/whispers.2019.8921232 dblp:conf/whispers/KennedyWS19 fatcat:j2dujaoexjdv7gmgfpwldhdxkq

High-Throughput Phenotyping of Soybean Maturity Using Time Series UAV Imagery and Convolutional Neural Networks

Rodrigo Trevisan, Osvaldo Pérez, Nathan Schmitz, Brian Diers, Nicolas Martin
2020 Remote Sensing  
Unmanned aerial vehicles (UAVs) imagery-based high-throughput phenotyping methodologies have been proposed as an alternative to the traditional visual ratings of pod senescence.  ...  However, the lack of scalable and accurate methods to extract the desired information from the images remains a significant bottleneck in breeding programs.  ...  Acknowledgments: To the Don Mario Group (GDM Seeds) for providing the images and part of the ground truth maturity data used in this work.  ... 
doi:10.3390/rs12213617 fatcat:gq3kga5w3fgyfcp3bps45wea7i

Deep Learning-Based Building Extraction from Remote Sensing Images: A Comprehensive Review

Lin Luo, Pengpeng Li, Xuesong Yan
2021 Energies  
Building extraction from remote sensing (RS) images is a fundamental task for geospatial applications, aiming to obtain morphology, location, and other information about buildings from RS images, which  ...  In recent years, deep learning (DL) technology has made remarkable progress and breakthroughs in the field of RS and also become a central and state-of-the-art method for building extraction.  ...  Introduction With the rapid development of imaging technology, high-resolution remote sensing (RS) imagery is becoming more and more readily available.  ... 
doi:10.3390/en14237982 fatcat:brv7jc3ujbbg5cjmyrjyegujgi

Assisting UAV Localization via Deep Contextual Image Matching

Muhammad Hamza Mughal, Muhammad Jawad Khokhar, Muhammad Shahzad
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
The proposed deep architecture extracts the features from the aerial imagery and localizes it in a pre-ordained, larger, and geotagged image.  ...  In this article, we aim to explore the potential of using onboard cameras and pre-stored geo-referenced imagery for Unmanned Aerial Vehicle (UAV) localization.  ...  Model Training and Optimization Data for training and optimizing the proposed model comprises of a set of template images I T and their labels y a which represent the pairs of labeled point-to-point correspondences  ... 
doi:10.1109/jstars.2021.3054832 fatcat:64uej7kmibcyxgoo3q7ppyzley

Large-Scale Counting and Localization of Pineapple Inflorescence Through Deep Density-Estimation

Jennifer Hobbs, Prajwal Prakash, Robert Paull, Harutyun Hovhannisyan, Bernard Markowicz, Greg Rose
2021 Frontiers in Plant Science  
Since pineapple is hand-harvested, the ability to harvest all of the fruit of a field in a single pass is critical to reduce field losses, costs, and waste, and to maximize efficiency.  ...  Our work uses a deep learning-based density estimation approach to count the number of flowering pineapple plants in a field with a test MAE of 11.5 and MAPD of 6.37%.  ...  The expert drone piloting skills and professionalism of Mike Elliott at Drone Services Hawaii was critical for the success of this project.  ... 
doi:10.3389/fpls.2020.599705 pmid:33584745 pmcid:PMC7876329 fatcat:af65kqmjprbuhpev4vsgm4sqy4

UATNet: U-Shape Attention-Based Transformer Net for Meteorological Satellite Cloud Recognition

Zhanjie Wang, Jianghua Zhao, Ran Zhang, Zheng Li, Qinghui Lin, Xuezhi Wang
2021 Remote Sensing  
Our model efficiently integrates the spatial and multi-channel information of clouds.  ...  Hence, it is difficult to effectively extract the structural shape, area size, contour shape, hue, shadow and texture of clouds through traditional deep learning methods.  ...  Remote Sens. Lett. 2014, 12, 666–670. 27. Shi, M.; Xie, F.; Zi, Y.; Yin, J. Cloud detection of remote sensing images by deep learning.  ... 
doi:10.3390/rs14010104 fatcat:mv2uoxlrebgpffocebkiznaj3m

Fusarium Wilt of Radish Detection using RGB and Near Infrared Images from Unmanned Aerial Vehicles

L. Minh Dang, Hanxiang Wang, Yanfen Li, Kyungbok Min, Jin Tae Kwak, O. New Lee, Hanyong Park, Hyeonjoon Moon
2020 Remote Sensing  
of a superpixel segmentation method to segment captured radish field images into separated segments; (3) a customized deep learning-based radish identification framework for the extracted segmented images  ...  In addition to Red-Green-Blue (RGB) images, the development of near-infrared (NIR) sensors has enabled a more effective way to monitor the diseases and evaluate plant health based on multispectral imagery  ...  and (3) the dataset includes both RGB images, which are applied to regular wilt identification, and NIR images, which can be used in remote sensing analysis.  ... 
doi:10.3390/rs12172863 fatcat:rfrbk2gixzfybahallyhuxumnm

Attention Mechanism and Depthwise Separable Convolution Aided 3DCNN for Hyperspectral Remote Sensing Image Classification

Wenmei Li, Huaihuai Chen, Qing Liu, Haiyan Liu, Yu Wang, Guan Gui
2022 Remote Sensing  
Hyperspectral Remote Rensing Image (HRSI) classification based on Convolution Neural Network (CNN) has become one of the hot topics in the field of remote sensing.  ...  However, the high dimensional information and limited training samples are prone to the Hughes phenomenon for hyperspectral remote sensing images.  ...  Acknowledgments: We would like to thank the anonymous reviewers and the editor-in-chief for their comments to improve the paper. Thanks also to the data sharer.  ... 
doi:10.3390/rs14092215 fatcat:kc3okdha6rhipkfewovzwqawpq

Integrating EfficientNet into an HAFNet Structure for Building Mapping in High-Resolution Optical Earth Observation Data

Luca Ferrari, Fabio Dell'Acqua, Peng Zhang, Peijun Du
2021 Remote Sensing  
Deep learning (DL) is increasingly used in multi-modal data fusion and urban object extraction.  ...  However, DL-based multi-modal fusion networks may under-perform due to insufficient learning of "joint features" from multiple sources and oversimplified approaches to fusing multi-modal features.  ...  final segmented output.  ... 
doi:10.3390/rs13214361 fatcat:r6zqjkwzhvdirfbjfiavm4oycq

Neural Network-Based Urban Change Monitoring with Deep-Temporal Multispectral and SAR Remote Sensing Data

Georg Zitzlsberger, Michal Podhorányi, Václav Svatoň, Milan Lazecký, Jan Martinovič
2021 Remote Sensing  
We propose a fully automated method that uses a large amount of available remote sensing observations for a selected period without the need to manually select samples.  ...  To combine the benefit of both remote sensing types, the network models are ensembles of optical- and SAR-specialized sub-networks.  ...  Deep learning is able to fulfill the needs of remote sensing image processing, such as classification or segmentation [6] .  ... 
doi:10.3390/rs13153000 fatcat:swpgzzodxjhhfeg5lmncy2ylzm

High-Resolution Aerial Image Labeling With Convolutional Neural Networks

Emmanuel Maggiori, Yuliya Tarabalka, Guillaume Charpiat, Pierre Alliez
2017 IEEE Transactions on Geoscience and Remote Sensing  
., the problem of assigning a semantic label to an entire input image.  ...  We observe that even though they provide competitive results, these CNNs often underexploit properties of semantic labeling that could lead to more effective and efficient architectures.  ...  An individual neuron takes a vector of inputs x = x 1 . . . x n and performs a simple operation to produce an output a.  ... 
doi:10.1109/tgrs.2017.2740362 fatcat:mka6svy3afdklfv54l5rsxicva
« Previous Showing results 1 — 15 out of 123 results