Image Segmentation for Environmental Monitoring

Edited by
July 2020
198 pages
  • ISBN978-3-03936-477-0 (Hardback)
  • ISBN978-3-03936-478-7 (PDF)

This book is a reprint of the Special Issue Image Segmentation for Environmental Monitoring that was published in

Environmental & Earth Sciences

OBIA, based on image segmentation and as an important remote sensing monitoring technology, has been widely used in forestry, vegetation, wetland, urban, crop, conservation, ecology, and agriculture areas. Although OBIA has considerably progressed in the past 20 years, OBIA still much room for further development, regardless of the technological aspect of OBIA or the prospective expansion field of applications. Therefore, this book was organized to further encourage OBIA technology development and expand OBIA applications. This book collects a total of eight papers, which compile the current state-of-the-art research and technology in the area of image segmentation, and highlight prominent current application directions. Therefore, this book not only contains innovative methods, but also covers the innovation of application-driven OBIA technology. The eight papers in this highlight both the popular applications (urban, vegetation, ecology) and several subjects that require additional research attention (landslide, arid-land).

  • Hardback
License and Copyright
© 2020 by the authors; CC BY-NC-ND license
unsupervised segmentation parameter optimization; GRASS GIS; image classification; land cover; urban areas; big data; image over-segmentation; distance dependent Chinese restaurant process; nonparametric Bayesian clustering model; superpixels; multiscale segmentation; scale parameter; cross-scale optimization; segmentation refinement; urban green cover; GEOBIA; biodiversity; LIDAR; orthophoto; segmentation; classification; biotope distribution model; image segmentation; remote sensing; land cover; iterative elimination; RSGISLib; ND; END; ECOC; MRS; Extended object-guided morphological profiles; Multiclass classification; Arid-land vegetation mapping; Sentinel-2A MSIL1C; Central Asia; image classification; ensemble; mean-shift; entropy; uncertainty map; landslides information extraction; unmanned aerial vehicle imagery; convolutional neural network; transfer learning; object-oriented image analysis; GEOBIA; object-based image analysis; high-spatial-resolution; image segmentation parameter optimization