The Experts below are selected from a list of 73419 Experts worldwide ranked by ideXlab platform

Shawn Newsam - One of the best experts on this subject based on the ideXlab platform.

  • fine grained land use classification at the city scale using ground level images
    IEEE Transactions on Multimedia, 2019
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    Multimedia researchers have exploited large collections of community-contributed geo-referenced images to better understand a particular image, such as its subject matter or where it was taken, as well as to better understand a Geographic location, such as the most visited tourist spots in a city or what the local cuisine is like. The goal of this paper is to better understand location. In particular, we use geo-referenced image collections to better understand what occurs in different parts of a city at fine spatial and activity class scales. This problem is known as land use mapping in the Geographical sciences. We propose a novel framework to perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of geo-referenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the city of San Francisco, CA, USA. Individual images are classified using a novel convolutional neural network containing two streams: one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several novel strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geovisualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level that represents a strong baseline for the challenging 45-way land use classification problem, especially given the noisiness of the image data.

  • fine grained land use classification at the city scale using ground level images
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of georeferenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the City of San Francisco. Individual images are classified using a novel convolutional neural network containing two streams, one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geo-visualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level which represents a strong baseline for the challenging 45-way land use classification problem especially given the noisiness of the image data.

  • land use classification using convolutional neural networks applied to ground level images
    arXiv: Computer Vision and Pattern Recognition, 2016
    Co-Authors: Yi Zhu, Shawn Newsam
    Abstract:

    Land use mapping is a fundamental yet challenging task in Geographic science. In contrast to land cover mapping, it is generally not possible using overhead imagery. The recent, explosive growth of online geo-referenced photo collections suggests an alternate approach to Geographic Knowledge discovery. In this work, we present a general framework that uses ground-level images from Flickr for land use mapping. Our approach benefits from several novel aspects. First, we address the nosiness of the online photo collections, such as imprecise geolocation and uneven spatial distribution, by performing location and indoor/outdoor filtering, and semi- supervised dataset augmentation. Our indoor/outdoor classifier achieves state-of-the-art performance on several bench- mark datasets and approaches human-level accuracy. Second, we utilize high-level semantic image features extracted using deep learning, specifically convolutional neural net- works, which allow us to achieve upwards of 76% accuracy on a challenging eight class land use mapping problem.

Yi Zhu - One of the best experts on this subject based on the ideXlab platform.

  • fine grained land use classification at the city scale using ground level images
    IEEE Transactions on Multimedia, 2019
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    Multimedia researchers have exploited large collections of community-contributed geo-referenced images to better understand a particular image, such as its subject matter or where it was taken, as well as to better understand a Geographic location, such as the most visited tourist spots in a city or what the local cuisine is like. The goal of this paper is to better understand location. In particular, we use geo-referenced image collections to better understand what occurs in different parts of a city at fine spatial and activity class scales. This problem is known as land use mapping in the Geographical sciences. We propose a novel framework to perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of geo-referenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the city of San Francisco, CA, USA. Individual images are classified using a novel convolutional neural network containing two streams: one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several novel strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geovisualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level that represents a strong baseline for the challenging 45-way land use classification problem, especially given the noisiness of the image data.

  • fine grained land use classification at the city scale using ground level images
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of georeferenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the City of San Francisco. Individual images are classified using a novel convolutional neural network containing two streams, one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geo-visualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level which represents a strong baseline for the challenging 45-way land use classification problem especially given the noisiness of the image data.

  • land use classification using convolutional neural networks applied to ground level images
    arXiv: Computer Vision and Pattern Recognition, 2016
    Co-Authors: Yi Zhu, Shawn Newsam
    Abstract:

    Land use mapping is a fundamental yet challenging task in Geographic science. In contrast to land cover mapping, it is generally not possible using overhead imagery. The recent, explosive growth of online geo-referenced photo collections suggests an alternate approach to Geographic Knowledge discovery. In this work, we present a general framework that uses ground-level images from Flickr for land use mapping. Our approach benefits from several novel aspects. First, we address the nosiness of the online photo collections, such as imprecise geolocation and uneven spatial distribution, by performing location and indoor/outdoor filtering, and semi- supervised dataset augmentation. Our indoor/outdoor classifier achieves state-of-the-art performance on several bench- mark datasets and approaches human-level accuracy. Second, we utilize high-level semantic image features extracted using deep learning, specifically convolutional neural net- works, which allow us to achieve upwards of 76% accuracy on a challenging eight class land use mapping problem.

Xueqing Deng - One of the best experts on this subject based on the ideXlab platform.

  • fine grained land use classification at the city scale using ground level images
    IEEE Transactions on Multimedia, 2019
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    Multimedia researchers have exploited large collections of community-contributed geo-referenced images to better understand a particular image, such as its subject matter or where it was taken, as well as to better understand a Geographic location, such as the most visited tourist spots in a city or what the local cuisine is like. The goal of this paper is to better understand location. In particular, we use geo-referenced image collections to better understand what occurs in different parts of a city at fine spatial and activity class scales. This problem is known as land use mapping in the Geographical sciences. We propose a novel framework to perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of geo-referenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the city of San Francisco, CA, USA. Individual images are classified using a novel convolutional neural network containing two streams: one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several novel strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geovisualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level that represents a strong baseline for the challenging 45-way land use classification problem, especially given the noisiness of the image data.

  • fine grained land use classification at the city scale using ground level images
    arXiv: Computer Vision and Pattern Recognition, 2018
    Co-Authors: Yi Zhu, Xueqing Deng, Shawn Newsam
    Abstract:

    We perform fine-grained land use mapping at the city scale using ground-level images. Mapping land use is considerably more difficult than mapping land cover and is generally not possible using overhead imagery as it requires close-up views and seeing inside buildings. We postulate that the growing collections of georeferenced, ground-level images suggest an alternate approach to this Geographic Knowledge discovery problem. We develop a general framework that uses Flickr images to map 45 different land-use classes for the City of San Francisco. Individual images are classified using a novel convolutional neural network containing two streams, one for recognizing objects and another for recognizing scenes. This network is trained in an end-to-end manner directly on the labeled training images. We propose several strategies to overcome the noisiness of our user-generated data including search-based training set augmentation and online adaptive training. We derive a ground truth map of San Francisco in order to evaluate our method. We demonstrate the effectiveness of our approach through geo-visualization and quantitative analysis. Our framework achieves over 29% recall at the individual land parcel level which represents a strong baseline for the challenging 45-way land use classification problem especially given the noisiness of the image data.

Harvey J Miller - One of the best experts on this subject based on the ideXlab platform.

  • Geographic information science ii mesogeography social physics giscience and the quest for Geographic Knowledge
    Progress in Human Geography, 2018
    Co-Authors: Harvey J Miller
    Abstract:

    The 20th century witnessed the rise of social physics: the application of models and techniques developed for physical processes to social phenomena. Social physics left an enduring legacy in human...

  • Geographic data mining and Knowledge discovery
    Geographic Information Science, 2001
    Co-Authors: Harvey J Miller, Jiawei Han
    Abstract:

    Introduction Harvey J. Miller and Jiawei Han Spatiotemporal Data Mining Paradigms and Methodologies John F. Roddick and Brian G. Lees Fundamentals of Spatial Data Warehousing for Geographic Knowledge Discovery Yvan Bedard and Jiawei Han Analysis of Spatial Data with Map Cubes: Highway Traffic Data Chang-Tien Lu, Arnold P. Boedihardjo, and Shashi Shekhar NEW! Data Quality Issues and Geographic Knowledge Discovery Marc Gervais, Yvan Bedard, Marie-Andree Levesque, Eveline Bernier, and Rodolphe Devillers Spatial Classification and Prediction Models for Geospatial Data Mining Shashi Shekhar, Ranga Raju Vatsavai, and Sanjay Chawla An Overview of Clustering Methods in Geographic Data Analysis Jiawei Han, Jae-Gil Lee, and Micheline Kamber NEW! Computing Medoids in Large Spatial Datasets Kyriakos Mouratidis, Dimitris Papadias, Spiros Papadimitriou NEW! Looking for a Relationship? Try GWR A. Stewart Fotheringham, Martin Charlton, and Urska Demsar Leveraging the Power of Spatial Data Mining to Enhance the Applicability of GIS Technology Donato Malerba, Antonietta Lanza, and Annalisa Appice Visual Exploration and Explanation in Geography: Analysis with Light Mark Gahegan NEW! Multivariate Spatial Clustering and Geovisualization Diansheng Guo NEW! Toward Knowledge Discovery about Geographic Dynamics in Spatiotemporal Databases} May Yuan NEW! The Role of a Multitier Ontological Framework in Reasoning to Discover Meaningful Patterns of Sustainable Mobility Monica Wachowicz, Jose Macedo, Chiara Renso, and Arend Ligtenberg NEW! Periodic Pattern Discovery from Trajectories of Moving Objects Huiping Cao, Nikos Mamoulis, and David W. Cheung NEW! Decentralized Spatial Data Mining for Geosensor Networks Patrick Laube and Matt Duckham NEW! Beyond Exploratory Visualization of Space-Time Paths Menno-Jan Kraak and Otto Huisman

Billy Tusker Haworth - One of the best experts on this subject based on the ideXlab platform.

  • implications of volunteered Geographic information for disaster management and giscience a more complex world of volunteered geography
    Annals of the American Association of Geographers, 2018
    Co-Authors: Billy Tusker Haworth
    Abstract:

    Volunteered Geographic information (VGI) refers to changing practices in recent years associated with technological advancements that provide increasing opportunities for private citizens to produce Geographic information. VGI activities range from public contributions to online crowdsourced mapping projects to location-related posts on social media sites. These changing practices have important implications for citizens, traditional authoritative systems of Geographic Knowledge production, and the disciplines of geography and GIScience. One field affected by VGI is disaster management, with numerous studies reporting on the opportunities associated with increased citizen data and involvement in crisis response. There are also significant limitations to the application of VGI, however, notably related to scale, the digital divide, trust, uneven power relations, and adaptability of existing authoritative systems, such as formal emergency management. In this article, these issues and more are critically dis...