Evaluation of the Self-Organizing Map Classifier for Building Detection from Lidar Data and Multispectral Aerial Images

Journal of Spatial Science, Vol. 54, No. 2

M.  Salah, J. Trinder, A. Shaker

“Integration of aerial images and lidar data compensate for the individual weaknesses of each data set when used alone, thus providing more accurate classification of terrain cover, such as buildings, roads and green areas, and advancing the potential for automation of large scale digital mapping and GIS database compilation. This paper presents work on the development of automatic feature extraction from multispectral aerial images and lidar data. A total of 22 feature attributes have been generated from the aerial image and the lidar data which contribute to the detection of the features. The attributes include those derived from the Grey Level Co-occurrence Matrix (GLCM), Normalized Difference Vegetation Indices (NDVI), and standard deviation of elevations and slope. A Self-Organizing Map (SOM) was used for fusing the aerial image, lidar data and the generated attributes for building detection. The classified images were then processed through a series of image processing techniques to separate the detected buildings. Results show that the proposed method can extract buildings accurately. Compared with a building reference map, 95.5 percent of the buildings were detected with a completeness and correctness of 83 percent and 80 percent respectively for buildings around 100m2 in area; these measures increased to 96 percent and 99 percent respectively for buildings around 1100m2 in area. Further, the contributions of lidar and the individual attributes to the quality of the classification results were evaluated.”

An Improved Approach for DSM Generation from High-Resolution Satellite Imagery

Journal of Spatial Science, Vol. 54, No. 2

C. Zhang, C. S. Fraser

“This paper develops an improved approach to digital surface model (DSM) generation from high-resolution satellite imagery (HRSI).  The approach centres upon an image matching strategy that integrates feature point, grid point and edge matching algorithms within a coarse-to-fine hierarchical process. The starting point is a knowledge of precise sensor orientation, achieved in this case through bias-compensated rational polynomial coefficients (RPCs), and the DSM is sequentially constructed through a combination of the matching results for feature and grid points, and edges at different image pyramid levels. The approach is designed to produce precise, reliable and very dense DSMs which preserve information on surface discontinuities. Following a brief introduction to sensor orientation modelling, the integrated image matching algorithms and DSM generation stages are described. The proposed approach is then experimentally tested through the generation of a DSM covering the Hobart area from a stereo pair of IKONOS Geo images. The accuracy of the resulting surface model is assessed using both ground checkpoints and a lidar DSM, with the results indicating that for favourable imagery and land cover, a heighting accuracy of 2 – 4 pixels can be readily achieved. This result validates the feasibility of the developed approach for DSM production from HRSI.”

Mike Steiner Named 2009 Outstanding Earth Science Teacher by National Association of Geoscience Teachers

…from The Chetek Alert

“Mike Steiner, a science teacher in Chetek, was named a 2009 Outstanding Earth Science Teacher by National Association of Geoscience Teachers.

“Steiner started a water quality testing program and, with the help of a social studies teacher, expanded the effort to involve students in GPS and GIS mapping and landscape analysis.”

Post-doctoral Research Associate, Faculty of Physical Sciences, Geographical & Earth Sciences, University of Glasgow

“We seek a post-doctoral researcher with experience in limnological biogeochemical research to join the Department of Geographical and Earth Sciences’ Earth Surface Dynamics research group. This position is working with Dr. Susan Waldron, Prof. Michael Bird (University of St. Andrews) and Amazonica colleagues, in applying field, laboratory and GIS modelling methods to quantify carbon effluxes from freshwater systems in the Amazon basin.

“Due to the nature of this project and its location please read the job description fully to make sure it is appropriate for you.

“This post has funding until 11.01.2013

“Further information or informal enquiries can be made to Dr. Susan Waldron (Susan.Waldron@ges.gla.ac.uk), Department of Geographical and Earth Sciences, University of Glasgow, G12 8QQ.

“Apply online at www.glasgow.ac.uk/jobs

“If you are unable to apply online please contact us on 0141 330 3898 for an application pack.

“Closing Date: 29 January 2010”

Summer Institute on Geographic Information Science: Interfacing Social and Environmental Modeling

13 to 19 June 2010

Facilitators: Gilberto Camara, Henk Scholten

The week will be organized around two main topics:

  1. Development of nature-society models using cellular automata and agents
  2. Mobile GIS and natural disasters modelling and response coordination

Topic (1) will be based on the current work at INPE. It will start with a discussion on how to do social and environmental modelling using cellular automata. Then, participants will develop simple models using the open source TerraME software (www.terrame.org). This will lead to an informed discussion on how such models can be enhanced using agent-based modelling. Topic (2) will be addressed with a mix of talks and hands-on work, based on leading edge industry developments using mobile technologies to interface environmental and social models.

“Eyes in the Sky II” Helps Grade 9 to 12 Science Teachers Become Proficient in Using NASA Data and Geospatial Analysis Tools

Eyes in the Sky II is a long-term professional development program that prepares high school science teachers to use NASA data and visualizations along with other geospatial information technologies. Throughout the program, teachers and students investigate both global and local environmental issues. The program includes four parts:

  1. A 12-week online Web course, consisting of three 4-week modules
  2. A 7-day face-to-face summer workshop held onsite at a NASA research center
  3. One year of classroom implementation, ending with a virtual student showcase
  4. An ambassador program for providing professional development for other teachers in participants’ schools or districts.

Grade 9 to 12 science teachers will benefit from this program. Through participating, teachers will:

  • Become proficient using NASA data and geospatial analysis tools
  • Receive a $1000 stipend for completing the online course and the 7-day summer workshop
  • Receive an additional $1000 stipend as compensation for delivering professional development as an Eyes in the Sky II Ambassador
  • Equip their students with geospatial technology skills that are in increasing demand in the workplace
  • Obtain optional graduate credit through Northern Arizona University.

For more information about the Eyes in the Sky II program, including the online application visit http://serc.carleton.edu/eyesinthesky2/index.html. Applications are due by January 15, 2010. We expect this will be a popular program. As there are a limited number of openings available, first consideration will be given to early applicants. If you have further questions, please contact Carla McAuliffe (Carla_McAuliffe@xxxxxxxx) or Erin Bardar (Erin_Bardar@xxxxxxxx).

Scientists Map Speed of Climate Change

…from LabSpaces.net

“From beetles to barnacles, pikas to pine warblers, many species are already on the move in response to shifting climate regimes. But how fast will they—and their habitats—have to move to keep pace with global climate change over the next century? In a new study, a team of scientists including Dr. Healy Hamilton from the California Academy of Sciences have calculated that on average, ecosystems will need to shift about 0.42 kilometers per year (about a quarter mile per year) to keep pace with changing temperatures across the globe. Mountainous habitats will be able to move more slowly, since a modest move up or down slope can result in a large change in temperature. However, flatter ecosystems, such as flooded grasslands, mangroves, and deserts, will need to move much more rapidly to stay in their comfort zone—sometimes more than a kilometer per year. The team, which also included scientists from the Carnegie Institute of Science, Climate Central, and U.C. Berkeley, will publish their results in the December 24 issue of Nature. ”