Filters








32,189 Hits in 3.4 sec

Data-Driven vs. Semantic-Technology-Driven Tag-Based Video Location Estimation

Jaeyoung Choi, Gerald Friedland
2011 2011 IEEE Fifth International Conference on Semantic Computing  
The first system is a data-driven approach that uses a heuristics based on the spatial variance of tags.  ...  The second one extends this heuristics by using semantic technologies, such as extended Wordnet and a geographical gazetteer.  ...  and combination with diverse knowledge sources from the web can lead to better results than investigating only one stream of sensor input (e.g. reducing the task to an to image retrieval problem).  ... 
doi:10.1109/icsc.2011.37 dblp:conf/semco/ChoiF11 fatcat:bk233nzizrabfiaugtxavgzrpa

IM2GPS: estimating geographic information from a single image

James Hays, Alexei A. Efros
2008 2008 IEEE Conference on Computer Vision and Pattern Recognition  
In this paper, we propose a simple algorithm for estimating a distribution over geographic locations from a single image using a purely data-driven scene matching approach.  ...  Estimating geographic information from an image is an excellent, difficult high-level computer vision problem whose time has come.  ...  and Flickr for sharing their computing and image resources with the research community. All visualizations and geographic data sources are derived from NASA data.  ... 
doi:10.1109/cvpr.2008.4587784 dblp:conf/cvpr/HaysE08 fatcat:yhuzxqiwabhgjco3okov5tdn3y

A Survey on Deep Learning-Driven Remote Sensing Image Scene Understanding: Scene Classification, Scene Retrieval and Scene-Guided Object Detection

Yating Gu, Yantian Wang, Yansheng Li
2019 Applied Sciences  
RSISU includes the following sub-tasks: remote sensing image scene classification, remote sensing image scene retrieval, and scene-driven remote sensing image object detection.  ...  As a fundamental and important task in remote sensing, remote sensing image scene understanding (RSISU) has attracted tremendous research interest in recent years.  ...  As Figure 3 reveals, we transfer the task of RS image retrieval to the task of feature retrieval.  ... 
doi:10.3390/app9102110 fatcat:oj3acgbmwnhzppxvvjbsn5cfzq

Deep Convolutional Features for Image Based Retrieval and Scene Categorization [article]

Arsalan Mousavian, Jana Kosecka
2015 arXiv   pre-print
We examine several pooling strategies and demonstrate superior performance on the image retrieval task (INRIA Holidays) at the fraction of the computational cost, while using a relatively small memory  ...  We also introduce and evaluate a novel GeoPlaces5K dataset from different geographical locations in the world for image retrieval that stresses more dramatic changes in appearance and viewpoint.  ...  The work of [7] proposed a data driven method for computing the coarse geographical location of an image using simpler features like GIST and color histograms.  ... 
arXiv:1509.06033v1 fatcat:q6jj7jwbz5fotercxumrk53tsy

Mental Processing of Geographic Knowledge [chapter]

Thomas Barkowsky
2001 Lecture Notes in Computer Science  
An actual mental image representation is constructed when needed to perform a specific task. In this construction process missing information is complemented to create a determinate mental image.  ...  The internal structure and the operating of the model is elaborated using an exemplary scenario. Problems in constructing mental images from given pieces of knowledge are demonstrated and discussed.  ...  Mental images (Finke, 1989; Kosslyn, 1980 Kosslyn, , 1994 are constructed in working memory when needed using pieces of information retrieved from long-term memory.  ... 
doi:10.1007/3-540-45424-1_25 fatcat:vhad3542evhadhm3ejoa6vg4te

Deep Learning based Enhanced Triplet Nework Model for Landmark Classification in Image Retrieval

K.Shanmuga Sundari
2019 International Journal for Research in Applied Science and Engineering Technology  
This research work focuses on, whether the visual and text content could be utilized over geographical correlation for landmark retrieval.  ...  Landmark retrieval is a process of restoring a collection of images along its landmarks which is parallel to required images.  ...  Geographic referencing of images include data-driven methods and model-based methods.  ... 
doi:10.22214/ijraset.2019.8138 fatcat:a3voqhbueffdfnfh6sgdw5r3k4

Dynamic Workflow Engine of Atmospheric Big Remote Sensing Data Processing Powered by Heterogenous Platform for High Performance Computing

Sheng Zhang, Yong Xue, Xiran Zhou
2021 GI_FORUM - Journal for Geographic Information Science  
This platform simplifies the operation of complex geospatial information processing applications in the field of high-performance geographic computing and realizes the efficient processing of massive data  ...  Therefore, the whole gas big remote sensing data processing is driven by the scheduling layer. The scheduling layer includes two key modules: task launcher and task scheduler.  ... 
doi:10.1553/giscience2021_01_s112 fatcat:leyk4ux5anf2hc4ogtxm42vxwa

Designing a Volunteered Geographic Information System for Road Data Validation

Gómez-Barrón, Alcarria, Manso-Callejo
2019 Proceedings (MDPI)  
The objective of this work is to build a Volunteered Geographic Information System (VGIS) using a methodological design process.  ...  Following this process helped to design a solution based on the project's information requirements to handle a road data tagging task, while offering an experience that meets the interests and needs of  ...  The web map uses an 18-level zoom to visualize several tiles of the image on one side of the interface, along with roads information on the other.  ... 
doi:10.3390/proceedings2019019007 fatcat:gne2wt4acnfkfegtphsgg2uuyq

What makes Paris look like Paris?

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros
2012 ACM Transactions on Graphics  
elements at different geo-spatial scales, and geographically-informed image retrieval.  ...  In addition, we face a hard search problem: given all possible patches in all images, which of them are both frequently occurring and geographically informative?  ...  This work is a part of a larger effort with Dan Huttenlocher and David Crandall, on modeling geo-informative visual attributes. We thank Google for letting us publish the Street View images.  ... 
doi:10.1145/2185520.2335452 fatcat:vtoxulxwqrcdtjxtijbgddrdhm

What makes Paris look like Paris?

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros
2012 ACM Transactions on Graphics  
elements at different geo-spatial scales, and geographically-informed image retrieval.  ...  In addition, we face a hard search problem: given all possible patches in all images, which of them are both frequently occurring and geographically informative?  ...  This work is a part of a larger effort with Dan Huttenlocher and David Crandall, on modeling geo-informative visual attributes. We thank Google for letting us publish the Street View images.  ... 
doi:10.1145/2185520.2185597 fatcat:vo67dw6kjjdcrnw3u6acaumtfe

What makes Paris look like Paris?

Carl Doersch, Saurabh Singh, Abhinav Gupta, Josef Sivic, Alexei A. Efros
2015 Communications of the ACM  
elements at different geo-spatial scales, and geographically-informed image retrieval.  ...  In addition, we face a hard search problem: given all possible patches in all images, which of them are both frequently occurring and geographically informative?  ...  This work is a part of a larger effort with Dan Huttenlocher and David Crandall, on modeling geo-informative visual attributes. We thank Google for letting us publish the Street View images.  ... 
doi:10.1145/2830541 fatcat:6h4ynxh72vez7iazwui5usvnay

A TASK-DRIVEN DISASTER DATA LINK APPROACH

L. Y. Qiu, Q. Zhu, J. Y. Gu, Z. Q. Du
2015 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The method breaks through traditional static management of disaster data and establishes a base for intelligent retrieval and active push of disaster information.  ...  The case study presented in this paper illustrates the use of the method with a flood emergency relief task.  ...  For example, the post-disaster raster image is used as a background to show information of disaster area as rich as possible, the images of ZY-3 satellite was often chosen in this application, then the  ... 
doi:10.5194/isprsarchives-xl-3-w3-179-2015 fatcat:ohvmnw2refgopbjhtti4cfqrva

Food recognition and recipe analysis: integrating visual content, context and external knowledge [article]

Luis Herranz, Weiqing Min, Shuqiang Jiang
2018 arXiv   pre-print
of food-related information.  ...  our individual and social life, combined with recent technological advances, has motivated a growing interest in applications that help to better monitor dietary habits as well as the exploration and retrieval  ...  Although some datasets can be used to evaluate multiple tasks, we will roughly distinguish between three groups, according to the main task: general food recognition, recipe analysis/retrieval, and restaurantbased  ... 
arXiv:1801.07239v1 fatcat:kbcpto5iznhkddvdklwxxbtehm

Ontology-based topological representation of remote-sensing images

Rafael Oliva-Santos, Francisco Maciá-Pérez, Eduardo Garea-Llano
2013 International Journal of Remote Sensing  
This representation has been validated by a case study of semantic retrieval based on the Normalised Vegetation Index (NDVI), taking into account the topological relations between NDVI regions in images  ...  Our aim is to provide an explicit definition in ontologies of the topological relations between objects in the image using the Quadtree data structure for spatial indexing.  ...  image regions for information retrieval.  ... 
doi:10.1080/01431161.2013.858847 fatcat:o55zwnbalzfz7ch6knunnueu5q

Geographic Information Retrieval

Ross Purves, Christopher Jones
2011 SIGSPATIAL Special  
The scope includes, but is not limited to, geographic information systems.  ...  The SIGSPATIAL Special is the newsletter of the Association for Computing Machinery (ACM) Special Interest Group on Spatial Information (SIGSPATIAL).  ...  The dimensions of context and its role in mobile information retrieval. David Mountain Department of Information Science, City University London, UK D.M.Mountain@city.ac.uk  ... 
doi:10.1145/2047296.2047297 fatcat:npmfk7kdhrailfrgyyaszkj6wi
« Previous Showing results 1 — 15 out of 32,189 results