Filters








34,028 Hits in 3.9 sec

Geographic Scene Understanding of High-Spatial-Resolution Remote Sensing Images: Methodological Trends and Current Challenges

Peng Ye, Guowei Liu, Yi Huang
2022 Applied Sciences  
It has become a research hotspot to recognize the semantic information of objects, analyze the semantic relationship between objects and then understand the more abstract geographic scenes in high-spatial-resolution  ...  Then, the achievements in the processing strategies and techniques of geographic scene understanding in recent years are reviewed from three layers: visual semantics, object semantics and concept semantics  ...  Acknowledgments: The authors thank Xueying Zhang and Chunju Zhang for their critical reviews and constructive comments. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app12126000 fatcat:hgtv363m6ras5me5vnu7d6yeii

Semantic Reinforced Attention Learning for Visual Place Recognition [article]

Guohao Peng, Yufeng Yue, Jun Zhang, Zhenyu Wu, Xiaoyu Tang, Danwei Wang
2021 arXiv   pre-print
of the local weighting scheme, a semantic constrained initialization is proposed so that the local attention can be reinforced by semantic priors.  ...  To fill the gap between the two types, we propose a novel Semantic Reinforced Attention Learning Network (SRALNet), in which the inferred attention can benefit from both semantic priors and data-driven  ...  Attention-aware Image Representation After the division and refinement of local features, the k th visual word vector V k can be calculated as a spatial aggregation of the double-weighted local residuals  ... 
arXiv:2108.08443v1 fatcat:eg44qmqyprdnpocozq46ngfiui

Cross-View Matching for Vehicle Localization by Learning Geographically Local Representations

Zimin Xia, Olaf Booij, Marco Manfredi, Julian F. P. Kooij
2021 IEEE Robotics and Automation Letters  
/tudelft-iv/Visual-Localization-with-Spatial-Prior Imagenet [27] , Adam [28] is used as optimizer with a learning rate of 10 −5 on the CVACT dataset and 5 • 10 −5 on the Oxford RobotCar dataset.  ...  Cross-View Matching for Vehicle Localization by Learning Geographically Local Representations Zimin Xia , Olaf Booij, Marco Manfredi, and Julian F. P.  ... 
doi:10.1109/lra.2021.3088076 fatcat:tnmye46yhbe5xo3s6wrcgr2g4q

North in the head: spatial reference frame and map orientation

Zsolt Győző Török
2020 Abstracts of the International Cartographic Association  
Supported by ubiquitous map services, prior to visiting unfamiliar places people consult maps to familiarize themselves, and this spatial learning results in memory structures with map-oriented reference  ...  Effective map use in the field is based on orientation in two spaces: in a physical or geographical space and in a representational, graphic space.  ...  Our results are consistent with previous research (Frankenstein et al. 2012 ) that the participants had a clear sense of geographical North learned from maps, moreover, contradicting our expectations,  ... 
doi:10.5194/ica-abs-2-6-2020 fatcat:tu36fg6zq5ctblwjasf3zabmsq

GisGCN: A Visual Graph-Based Framework to Match Geographical Areas through Time

Margarita Khokhlova, Nathalie Abadie, Valérie Gouet Brunet, Liming Chen
2022 ISPRS International Journal of Geo-Information  
Geographic entities in the vertical aerial images are thought of as nodes in a graph, linked to each other by edges representing their spatial relationships.  ...  Historical visual sources are particularly useful for reconstructing the successive states of the territory in the past and for analysing its evolution.  ...  We then proposed a novel deep learning-based method to learn graph representations of geographic entities and their spatial relationships and compare them across time.  ... 
doi:10.3390/ijgi11020097 fatcat:ki42hxfyovd7lkzob7xkduknzy

Semantic-aware Visual Abstraction of Large-scale Social Media Data with Geo-Tags

Zhiguang Zhou, Xinlong Zhang, Xiaoyun Zhou, Yuhua Liu
2019 IEEE Access  
Aiming at the reduction of visual clutter of geographical visualization, a dual-objective blue noise sampling model is proposed to select a subset of social media data, by means of which both the semantic  ...  With the rapid growth of geo-tagged social media data, it has become feasible to explore topics across different areas through text mining and geographical visualization.  ...  First, a representation learning model doc2vec is applied to characterize the semantic correlation of tweets, and a t-SNE method is employed to visualize the tweets with high dimensional vectors.  ... 
doi:10.1109/access.2019.2935471 fatcat:l5e65ynrtvdkfbhblpvmln2adq

Towards precise POI localization with social media

Adrian Popescu, Aymen Shabou
2013 Proceedings of the 21st ACM international conference on Multimedia - MM '13  
Given a set of geotagged Flickr photos associated to a POI, close-up classification is used to trigger a spatial clustering process.  ...  Points of interest (POIs) are a core component of geographical databases and of location based services.  ...  Visual close and visual far classes are learned with a linear SVM which is then used to classify test images. Scores vary between 1 (close) and 0 (far).  ... 
doi:10.1145/2502081.2502151 dblp:conf/mm/PopescuS13 fatcat:ky5cywpydjdshcdbflkauxuebu

:{unav)

Ioanna Vekiri
2012 Educational Psychology Review  
The article reviews studies that explain the role of graphical displays in learning and synthesizes relevant findings into principles for effective graphical design.  ...  Learners' characteristics, such as prior subject-matter knowledge, visuospatial ability, and strategies, influence graphic processing and interact with graphical design to mediate its effects.  ...  Pintrich for his guidance during the writing of this review, and Priti Shah, Daniel Robinson, Annemarie S. Palincsar, Carl Berger and two anonymous reviewers for their comments.  ... 
doi:10.1023/a:1016064429161 fatcat:b6nzetp32vavroknyogdciuvru

Wide-Area Image Geolocalization with Aerial Reference Imagery

Scott Workman, Richard Souvenir, Nathan Jacobs
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
We use state-of-the-art feature representations for ground-level images and introduce a cross-view training approach for learning a joint semantic feature representation for aerial images.  ...  We also show, qualitatively, that the proposed feature representations are discriminative at both local and continental spatial scales.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
doi:10.1109/iccv.2015.451 dblp:conf/iccv/WorkmanSJ15 fatcat:mbxc3menl5gstn45lqw6xupgjq

Wide-Area Image Geolocalization with Aerial Reference Imagery [article]

Scott Workman, Richard Souvenir, Nathan Jacobs
2015 arXiv   pre-print
We use state-of-the-art feature representations for ground-level images and introduce a cross-view training approach for learning a joint semantic feature representation for aerial images.  ...  We also show, qualitatively, that the proposed feature representations are discriminative at both local and continental spatial scales.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright annotation thereon.  ... 
arXiv:1510.03743v1 fatcat:twi64udpa5bxrhg4zfhhk6tv34

Geovisualizing space and time in a science-art exhibit

Javier A. Arce-Nazario
2019 Abstracts of the International Cartographic Association  
</p><p> Like these other public geographic exhibits, <i>geo/visual/isla</i> extensively used an early cartographic representation of time, which was chosen for its simplicity and familiarity.  ...  Spatial orientation between images was reinforced by choosing images with prominent, essentially consistent landscape features such as a coastline.  ...  Like these other public geographic exhibits, geo/visual/isla extensively used an early cartographic representation of time, which was chosen for its simplicity and familiarity.  ... 
doi:10.5194/ica-abs-1-14-2019 fatcat:yx575hygdrhela4c7wat5e72ce

Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization

Yujiao Shi, Liu Liu, Xin Yu, Hongdong Li
2019 Neural Information Processing Systems  
To improve the robustness of feature representation, we introduce a feature aggregation strategy via learning multiple spatial embeddings.  ...  Thus, we propose a two-step approach to exploit this prior.  ...  We thank all anonymous reviewers for their constructive comments.  ... 
dblp:conf/nips/Shi0YL19 fatcat:ha3iyzpqtbaejmtlg7npchb3ya

Thinking about Spatial Computing

Andrea Ballatore, Werner Kuhn
2015 Conference On Spatial Information Theory  
Thus, we propose a lightning talk on core concepts of spatial information as a form of spatial thinking to support learning GIS.  ...  Specifically, we recommend developing and applying a set of spatial lenses through which learners of Geographic Information Systems (GIS) get to see geographic space and choose spatial computations.  ...  Acknowledgments This ongoing research is made possible through funding from the University of California Santa Barbara for its Center for Spatial Studies.  ... 
dblp:conf/cosit/BallatoreK15 fatcat:ewmam2eekjh3xezceptnq72lca

Design, Implementation, and Evaluation of GIS-Based Learning Materials in an Introductory Geoscience Course

Michelle K. Hall-Wallace, Carla M. McAuliffe
2002 Journal of Geoscience education  
Learning with Geographic Information Systems (GIS) rather than about GIS has great potential for improving students' skills in problem solving, analysis, and spatial visualization.  ...  Through field-testing, we improved the materials design to address student difficulties with learning to use a GIS, identifying basic geographic locations and features, and interpreting topography and  ...  The power of a GIS is in the tools it provides for rapid analysis and visualization of large geographic data sets.  ... 
doi:10.5408/1089-9995-50.1.5 fatcat:ftbmonfzyvewxnd6ehzfk4hp54

Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD

Hyo Jin Kim, Enrique Dunn, Jan-Michael Frahm
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
In particular, we discover features that are useful for recognizing a place in a data-driven manner, and use this knowledge to predict useful features in a query image prior to the geo-localization process  ...  Also, for both learning to predict features and retrieving geo-tagged images from the database, we propose per-bundle vector of locally aggregated descriptors (PBVLAD), where each maximally stable region  ...  The authors would also like to thank Alex Berg and Amir Zamir for helpful discussions.  ... 
doi:10.1109/iccv.2015.139 dblp:conf/iccv/KimDF15 fatcat:f74k7gpmqvfb3k6f74ch5jg5he
« Previous Showing results 1 — 15 out of 34,028 results