Filters








13,452 Hits in 5.6 sec

Deep Learning with Open Data for Desert Road Mapping

Christopher Stewart, Michele Lazzarini, Adrian Luna, Sergio Albani
2020 Remote Sensing  
The availability of free and open data from Earth observation programmes such as Copernicus, and from collaborative projects such as Open Street Map (OSM), enables low cost artificial intelligence (AI)  ...  The technique uses Copernicus Sentinel–1 synthetic aperture radar (SAR) satellite data as an input to a deep learning model based on the U–Net architecture for image segmentation.  ...  programme, which provides free and open access to Sentinel data; Open Street Map, for the free provision of vector data of roads, and Lucio Colaiacomo (SatCen) for the preliminary preparation of this  ... 
doi:10.3390/rs12142274 fatcat:eygftlgpcnaxfjiozwfwwwck2a

Learning On-Road Visual Control for Self-Driving Vehicles with Auxiliary Tasks [article]

Yilun Chen, Praveen Palanisamy, Priyantha Mudalige, Katharina Muelling, John M. Dolan
2018 arXiv   pre-print
Finally, we combine vehicle kinematics with a sensor fusion step.  ...  A safe and robust on-road navigation system is a crucial component of achieving fully automated vehicles.  ...  The authors would like to thank Yihao Qian and Abhinav Gupta for fruitful discussions about the project.  ... 
arXiv:1812.07760v1 fatcat:po2gfjdd4bbwja64dc4r7zqyvm

Advances in Scene Classification of Remotely Sensed High Resolution Images and the Existing Datasets

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
With the usage of different deep learning architecture and the availability of various high resolution image datasets, the field of Remote Sensing Scene Classification of high resolution (RSSCHR) images  ...  Research on Scene classification of remotely sensed images has shown a significant improvement in the recent years as it is used in various applications such as urban planning, urban mapping, management  ...  Scene Classification by combining the remote sensing images with this social media information using suitable deep learning architecture can provide us with an improved state of art performance for real  ... 
doi:10.35940/ijitee.j8841.0881019 fatcat:7dznp4cr7zfv5m25y662dskuse

Using Satellite Imagery for Good: Detecting Communities in Desert and Mapping Vaccination Activities [article]

Anza Shakeel, Mohsen Ali
2017 arXiv   pre-print
This paper describes a deep learning approach that analyzes a geo referenced satellite image and efficiently detects built structures in it.  ...  The detected built communities are then correlated with the vaccination activity that has furnished some useful statistics.  ...  Ideas like using mobile-phone-activity to geo-locate roads or directly crowdsourcing (Open Street Map, Wikimapia, etc..) the map information have been used to build and update maps.  ... 
arXiv:1705.04451v1 fatcat:5kjwb3hg6fcevb2x5aaq7bd5rq

Please, Help Me! I Am Lost in Zoom

Guillaume Touya, María-Jesús Lobo, William A. Mackaness, Ian Muehlenhaus
2021 Proceedings of the ICA  
The desert fog effect makes you feel lost for a few seconds after a zoom in or out, because the map has changed.  ...  This paper discusses the main challenges that will be addressed in this project: (1) better understand and measure the desert fog effect with maps; (2) defining and modelling the best anchors for anchor-based  ...  The material used for our spatial cognition surveys will also be released as open data to encourage future user surveys with interactive multi-scale maps.  ... 
doi:10.5194/ica-proc-4-107-2021 fatcat:nejju5glzvcovg7jmzxvelg5oe

Detecting Hardly Visible Roads in Low-Resolution Satellite Time Series Data [article]

Stefan Oehmcke, Christoffer Thrysøe, Andreas Borgstad, Marcos Antonio Vaz Salles, Martin Brandt, Fabian Gieseke
2019 arXiv   pre-print
Towards this end, this work advances data-driven approaches for the automatic identification of roads based on open satellite data.  ...  Based on this observation, we propose two deep learning frameworks that extend state-of-the-art deep learning methods by formalizing road detection as an ordinal classification task.  ...  We acknowledge support from the Danish Industry Foundation through the Industrial Data Analysis Service (IDAS).  ... 
arXiv:1912.05026v1 fatcat:iffpwvylifdidnkezrmvyhajbu

Road Extraction from High-Resolution Remote Sensing Imagery Using Deep Learning

Yongyang Xu, Zhong Xie, Yaxing Feng, Zhanlong Chen
2018 Remote Sensing  
This method also achieves a harmonic mean of precision and recall higher than other machine learning and deep learning methods.  ...  The aim of this work is to propose a novel road extraction method that can efficiently extract the road network from remote sensing imagery with local and global information.  ...  The authors also thank Mingyu Xie (University of California, Santa Barbara) for helping improve the language. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/rs10091461 fatcat:2vp4z2jsnvggrarwbf4khexb2a

ENHANCED PIXEL BASED URBAN AREA CLASSIFICATION OF SATELLITE IMAGES USING CONVOLUTIONAL NEURAL NETWORK

Noureldin Laban, Bassam Abdellatif, Hala Moushier, howida shedeed, Mohamed Tolba
2021 International Journal of Intelligent Computing and Information Sciences  
Recent years have witnessed a great development in the use of deep learning in the applied fields in general, including the improvement of remote sensing.  ...  First, select training boxes for different classes and create many pixels with variable class signatures. This makes the training process dependent on the broadband of signature for the classes.  ...  At the same time, the open-source community is being organized to build customized software libraries for deep learning networks and the expansion of participation in them on the one hand.  ... 
doi:10.21608/ijicis.2021.79070.1099 fatcat:f4eunqahzjgfjlbxdam2m4yvhm

Drones in the Desert: Augmenting HMA and Socio-Economic Activities in Chad

John Fardoulis, Xavier Depreytere, Emmanuel Sauvage, Pierre Gallien
2019 Zenodo  
It is meant to be a guide for the landmine and explosives of war clearance sector, plus an introduction for researchers and donors.  ...  An emphasis is placed on the value of data outputs, particularly how aerial data can help augment; manual demining, non technical survey, mechanical demining, pre-deployment planning and quality assurance  ...  Special thanks are in order to the people of the HCND for their support and for making pretesting a reality.  ... 
doi:10.5281/zenodo.4020982 fatcat:4fjrkyvlfzgjhhwi3oi6wojoyq

Local Climate Zone Mapping Using Multi-Source Free Available Datasets on Google Earth Engine Platform

Lingfei Shi, Feng Ling
2021 Land  
With the help of the GEE, this study provides the potential to generate more accurate LCZ mapping on a large scale, which is significant for urban development.  ...  More and more effort has been focused on improving LCZ mapping accuracy. It has become a prevalent trend to take advantage of multi-source images in LCZ mapping.  ...  Most importantly, POI and social media check-in data also are open access for the public. The open and free datasets provide more possibilities for LCZ mapping in other cities.  ... 
doi:10.3390/land10050454 doaj:988ba38e7b9f48baa4380a73f464ade4 fatcat:bw5kpix2wrc7rcpwhebp46drl4

Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications

Matthias Müller, Vincent Casser, Jean Lahoud, Neil Smith, Bernard Ghanem
2018 International Journal of Computer Vision  
The simulator fully integrates both several state-of-the-art tracking algorithms with a benchmark evaluation tool and a deep neural network (DNN) architecture for training vehicles to drive autonomously  ...  We demonstrate the versatility of the simulator with two case studies: autonomous UAV-based tracking of moving objects and autonomous driving using supervised learning.  ...  Moreover, since our developed simulator and its seamless interface to deep learning platforms are generic in nature and open-source, we expect that this combination will open up unique opportunities for  ... 
doi:10.1007/s11263-018-1073-7 fatcat:go2kohdljzfmfemp5z536p2qhy

Automated School Location Mapping at Scale from Satellite Imagery Based on Deep Learning

Iyke Maduako, Zhuang-Fang Yi, Naroa Zurutuza, Shilpa Arora, Christopher Fabian, Do-Hyung Kim
2022 Remote Sensing  
Computer vision for large scale building detection can be very challenging in many environments and settings even with recent advances in deep learning technologies.  ...  modern deep learning techniques.  ...  Maxar's highresolution satellite imagery used for this work were provided by the United States Government under NextView end user license.  ... 
doi:10.3390/rs14040897 fatcat:ktmtwzzfwvbs7okhmh6t2vqtrq

An Integrated CNN Model for Reconstructing and Predicting Land Use/Cover Change: A Case Study of the Baicheng Area, Northeast China

Yubo Zhang, Jiuchun Yang, Dongyan Wang, Jing Wang, Lingxue Yu, Fengqin Yan, Liping Chang, Shuwen Zhang
2021 Remote Sensing  
This model applies the deep learning method, which far exceeds the performance of traditional machine learning methods, and uses CNN to extract spatial features and provide greater proximity information  ...  In particular, models that can obtain long-term land use data with high precision are of great value in research on global environmental change and climate impact, as land use data are important model  ...  Deep learning in neural networks has strong learning ability, the increase in data volume has an obvious effect in terms of improved accuracy, and the characteristics of cumbersome feature engineering  ... 
doi:10.3390/rs13234846 fatcat:dgayaa3aurgjveofdajqve7n2y

FaceLift: a transparent deep learning framework to beautify urban scenes

Sagar Joglekar, Daniele Quercia, Miriam Redi, Luca Maria Aiello, Tobias Kauer, Nishanth Sastry
2020 Royal Society Open Science  
Unfortunately, deep learning techniques have not been designed with that challenge in mind.  ...  Yet they fall short when it comes to generating actionable insights for urban design.  ...  Deep learning systems need considerable amounts of training data.  ... 
doi:10.1098/rsos.190987 pmid:32218934 pmcid:PMC7029915 fatcat:haxw4yxp2jc3hdk7jh2igilrr4

Road Extraction from a High Spatial Resolution Remote Sensing Image Based on Multi-task Key Point Constraints

Xungen Li, Zhan Zhang, Shuaishuai Lv, Mian Pan, Qi Ma, Haibin Yu
2021 IEEE Access  
Compared with the traditional method, the road extraction method based on deep learning has huge strengths.  ...  dataset are not diversified and abundant, some sites are extracted from open map data on Google Map, including Tokyo in Japan, Washington in America, Xinjiang in China, London in Britain, etc.  ... 
doi:10.1109/access.2021.3094536 fatcat:2hvhbdknqfhypgddv7wfqm2a5m
« Previous Showing results 1 — 15 out of 13,452 results