Conference Paper

Analyzing change in spatial data by utilizing polygon models

DOI: 10.1145/1823854.1823880 Conference: Proceedings of the 1st International Conference and Exhibition on Computing for Geospatial Research & Application, COM.Geo 2010, Washington, DC, USA, June 21-23, 2010
Source: DBLP

ABSTRACT Analyzing change in spatial data is critical for many applications including developing early warning systems that monitor environmental conditions, epidemiology, crime monitoring, and automatic surveillance. In this paper, we present a framework for the detection and analysis of patterns of change; the framework analyzes change by comparing sets of polygons. A contour clustering algorithm is utilized to obtain polygon models from spatial datasets. A set of change predicates is introduced to analyze changes between different models which capture various types of changes, such as novel concepts, concept drift, and concept disappearance. We evaluate our framework in case studies that center on ozone pollution monitoring, and on diagnosing glaucoma from visual field analysis.

Download full-text

Full-text

Available from: Michael Twa, Jul 01, 2015
0 Followers
 · 
150 Views
  • Source
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: The need to collect vast amounts of geospatial data is driven by the emergence of geo-enabled Web applications and the suitability of geospatial data in general to organize information. Given that geospatial data collection and aggregation is a resource intensive task typically left to professionals, we, in this work, advocate the use of information extraction (IE) techniques to derive meaningful geospatial data from plain texts. Initially focusing on travel information, the extracted data can be visualized as routes derived from narratives. As a side effect, the processed text is annotated by this route, which can be seen as an improved geocoding effort. Experimentation shows the adequacy and accuracy of the proposed approach by comparing extracted routes to respective map data.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Reconstructing views of real-world from satellite images, surveillance videos, or street view images is now a very popular problem, due to the broad usage of image data in Geographic Information Systems and Intelligent Transportation Systems. In this paper, we propose an approach that tries to replace the differences among images that are likely to be vehicles by the counterparts that are likely to be background. This method integrates the techniques for lane detection, vehicle detection, image subtraction and weighted voting, to regenerate the "vehicle-clean" images. The proposed approach can efficiently reveal the geographic background and preserve the privacy of vehicle owners. Experiments on surveillance images from TrafficLand.com and satellite view images have been conducted to demonstrate the effectiveness of the approach.