The Experts below are selected from a list of 42114 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, 2019Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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, 2018Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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.
Jeanfrancois Mas - One of the best experts on this subject based on the ideXlab platform.
-
Mapping Land Use cover in a tropical coastal area using satellite sensor data gis and artificial neural networks
Estuarine Coastal and Shelf Science, 2004Co-Authors: Jeanfrancois MasAbstract:Abstract A common problem when classifying remotely sensed images in order to map Land Use/cover is spectral confusion: different Land Use/cover classes present similar spectral signatures and are misclassified. This paper presents a procedure for Mapping Land Use/cover combining the spectral information from a recent image and data about spatial distribution of Land Use/cover types obtained from outdated cartography and ancillary data. Two fuzzy maps, which indicate the membership of each Land Use/cover class, were generated from the ancillary and spectral data, respectively, using an artificial neural networks approach. The combination of both maps was obtained using fuzzy rules. In comparison with spectral classification, this procedure allowed a statistically significant increase of accuracy of Land Use/cover classification (from 67% to 79%). The advantages of this procedure for combining spectral and ancillary data, with regard to others previously published in the literature, are that it allows one to take into account previous Mapping efforts and to establish relationships between Land Use/cover and environmental variables specific to the mapped area.
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, 2019Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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, 2018Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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.
Marek Ryczek - One of the best experts on this subject based on the ideXlab platform.
-
estimations of nitrate nitrogen total phosphorus flux and suspended sediment concentration ssc as indicators of surface erosion processes using an ann artificial neural network based on geomorphological parameters in mountainous catchments
Ecological Indicators, 2018Co-Authors: Wiktor Halecki, Edyta Kruk, Marek RyczekAbstract:Abstract In this paper, we describe methods to establish the relationships among geomorphology (physiographic) data, topography, and physical parameters in different-sized catchments using GIS techniques. GIS software allows performing interpolation point, vector or raster analysis based on topographic parameters, simultaneously with Mapping Land Use. This technique depends on the quantity of spatial information. Our objective was to explain the most important geomorphological parameters with an emphasis on surface erosion in mountain areas. Assessment of fluvial sediment in streams is essential to evaluate surface run-off. In the present paper, Artificial Neural Networks (ANNs) were applied to show relationships among total phosphorus, nitrate nitrogen and suspended sediment concentration using architecture based on geomorphological features. Results may be applied at a catchment scale of 1 km2 to more than 50 km2. Our methods are important for investigating the Land-Use for final assembly depending on sediment-erosion appraisal. This understanding is critical for developing geomorphological models to predict the detachment of soil and transport from their mass, derived-debris material and surface run-off. Our approach will be Useful for Land management to evaluate risks of sediment transport and raindrop splash and rill erosion in mountainous catchment areas.
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, 2019Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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, 2018Co-Authors: Yi Zhu, Xueqing Deng, Shawn NewsamAbstract: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.