Special Issue "Geographic Object-Based Image Analysis: State-Of-the-Art and Emerging Research Trends"

Special Issue Editors

Dr. Amr Abd-Elrahman
E-Mail Website
Guest Editor
Gulf Coast Research and Education Center, Wimauma, United States
University of Florida, Plant City, FL 33563, USA
Tel. +1-813-757-2283
Interests: object-based image analysis; machine learning; deep learning; hyperspectral and multispectral image analysis; lidar data analysis
Dr. Zoltan Szantoi
E-Mail Website
Guest Editor
European Commission Joint Research Centre, Copernicus Global Land Service, Italy
Tel. +39 (0332) 789-111
Interests: object-based image analysis; machine learning; hyperspectral and multispectral image analysis; land cover mapping; change detection; big data analysis
Special Issues and Collections in MDPI journals
Dr. Tao Liu
E-Mail Website
Guest Editor
Geographic Data Science Research Group, Oak Ridge National Laboratory (ORNL), USA
Interests: deep learning; landcover mapping; change detection; small unmanned aerial system (SUAS)

Special Issue Information

Dear Colleagues,

Geographic object-based image analysis (GEOBIA) has evolved over the past couple of decades motivated by the increased availability of higher spatial resolution imagery, computing power, analysis algorithms, and application needs. Years ago, some researchers described GEOBIA as a new paradigm in remote sensing image analysis. Today, we have experienced the use of GEOBIA in a wide range of applications using spectral and nonspectral (e.g., Lidar) datasets. An increasing number of commercial software packages are currently implementing GEOBIA algorithms capable of handling large datasets through optimized algorithms and parallel/cloud computations in a production environment. Traditional GEOBIA research involves developing new image segmentation algorithms, optimization segmentation parameters, feature extraction methods, and classification algorithms, as well as experimenting with accuracy assessment methods. The use of deep learning networks in GEOBIA and the recent introduction of deep learning algorithms capable of segmenting and classifying imagery as an emerging subject that integrates several crucial GEOBIA operations in convolutional network frameworks are also welcomed in this Special Issue.

The objective of this Special Issue is to present GEOBIA applications that incorporate recent developments for segmentation, classification, feature extraction, or segmentation parameter selection algorithms. It is our view that this Special Issue provides a timely and valuable opportunity for geo-information community researchers to rethink and advance the GEOBIA workflow by reaping the benefits of recent technology developments, especially in the deep learning area. In this context, we would like to invite our colleagues to submit their GEOBIA studies, in, but not limited to, the following topics:

  • Image segmentation and segmentation parameter optimization algorithms;
  • Integration of deep learning algorithms in GEOBIA workflow;
  • Applications of deep learning semantic segmentation algorithm in the geospatial analysis field;
  • Sampling strategies to train or evaluate deep learning classifiers;
  • GEOBIA usage in urban and natural land cover/use mapping and change detection applications;
  • Algorithms for GEOBIA of Big Data;
  • GEOBIA applications in large scale production emphasizing Big Data and cloud computing;
  • GEOBIA classification assessment metrics and methods.

Dr. Amr Abd-Elrahman
Dr. Zoltan Szantoi
Dr. Tao Liu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. ISPRS International Journal of Geo-Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1000 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.


  • geographic object-based image analysis (GEOBIA)
  • OBIA segmentation
  • artificial intelligence
  • OBIA classification
  • deep learning
  • big data

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:


Open AccessArticle
An Improved Hybrid Segmentation Method for Remote Sensing Images
ISPRS Int. J. Geo-Inf. 2019, 8(12), 543; https://doi.org/10.3390/ijgi8120543 - 28 Nov 2019
Image segmentation technology, which can be used to completely partition a remote sensing image into non-overlapping regions in the image space, plays an indispensable role in high-resolution remote sensing image classification. Recently, the segmentation methods that combine segmenting with merging have attracted researchers’ [...] Read more.
Image segmentation technology, which can be used to completely partition a remote sensing image into non-overlapping regions in the image space, plays an indispensable role in high-resolution remote sensing image classification. Recently, the segmentation methods that combine segmenting with merging have attracted researchers’ attention. However, the existing methods ignore the fact that the same parameters must be applied to every segmented geo-object, and fail to consider the homogeneity between adjacent geo-objects. This paper develops an improved remote sensing image segmentation method to overcome this limitation. The proposed method is a hybrid method (split-and-merge). First, a watershed algorithm based on pre-processing is used to split the image to form initial segments. Second, the fast lambda-schedule algorithm based on a common boundary length penalty is used to merge the initial segments to obtain the final segmentation. For this experiment, we used GF-1 images with three spatial resolutions: 2 m, 8 m and 16 m. Six different test areas were chosen from the GF-1 images to demonstrate the effectiveness of the improved method, and the objective function (F (v, I)), intrasegment variance (v) and Moran’s index were used to evaluate the segmentation accuracy. The validation results indicated that the improved segmentation method produced satisfactory segmentation results for GF-1 images (average F (v, I) = 0.1064, v = 0.0428 and I = 0.17). Full article
Back to TopTop