Special Issue "Machine Learning for High Spatial Resolution Imagery"

A special issue of ISPRS International Journal of Geo-Information (ISSN 2220-9964).

Deadline for manuscript submissions: 31 August 2021.

Special Issue Editors

Special Issue Information

The machine learning algorithm is one of the most advanced learning algorithms of Artificial Intelligence. It is a branch of data mining that focuses on the exploration of data analysis. The use of a machine learning algorithm can train the data for predictive analysis, with the outcomes resulting in more accuracy. The main objective of the machine learning algorithm is to allow the machine to learn by itself without any assistance. The output data obtained from the learning process are also considered as new input data for another process which does some statistical analysis for the prediction process, similar to data mining. The most common machine learning applications are fraud detection, predictive analysis, email filtering, medical image recognition and processing, and remote sensing applications. Machine learning has seen massive success in remote sensing image analysis and has been utilized in many diverse areas of the remote sensing field for image fusion, image segmentation, object detection, and object-based analyzing.

High-resolution images are essential for urban planning, satellite imagery, and especially during disaster rescue. Machine learning can achieve significant success in image analysis tasks, including land use classification, scene classification, and object detection. Remote sensing methods using the neural network are an emerging interest for improving the performance in preprocessing and segmentation of images. This learning algorithm based on the neural network comprises many layers that transform the input data image to the categorical output image. The machine learning algorithm acts as a supporting agent for space agencies in deploying an enormous number of satellites for earth observation. The algorithm makes learning by classifying the information from the image; this happens by extracting the edge feature first and then strengthening the effective spatial measures. It extracts the compact features which provide the semantics of input images and can achieve the challenges in high spatial resolution images from the satellite. The machine learning algorithm needs much attention in handling high dimensionality data and gives a better performance with a limited training sample.

Industrial people around the world are in the process of discovering the possibilities of machine learning to explore the extraction of high-level features representation frameworks with various techniques and methodologies, as well as to improve the accuracy during image classification. This Special Issue shall focus on inviting ideas, articles, and experimental evaluations towards development related to “Machine Learning for High Spatial Resolution Imagery” to learn, analyze, predict, and also provide more efficient classification.

Scope and Topics:

Suitable topics include but are not limited to the following:

  • ML for texture analysis to improve geo-demographic classification;
  • Geovisualization and visual analytics for high spatial resolution imagery;
  • Machine-learning-based spatial infrastructure building for agricultural and industrial landscapes using high spatial resolution imagery;
  • An overview of machine learning algorithms for location and navigation privacy for high spatial resolution monitoring;
  • ML for data mining, and decision support systems using spatial information;
  • ML for spatiotemporal database management for knowledge extraction;
  • Time series algorithms for high spatial resolution imagery;
  • Using the machine learning algorithm for classification and feature extraction of risky landscapes from urban areas;
  • Using object-oriented land use classification for aerial imagery;
  • High-performance computing algorithms for mapping of land records;
  • Parallel and distributed computation for high spatial resolution imagery;
  • Future need for intelligent spatial information infrastructure.
Dr. Gunasekaran Manogaran
Prof. Dr. Hassan Qudrat-Ullah
Prof. Dr. Qin Xin
Guest Editor

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 1400 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.

Published Papers (1 paper)

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

Research

Open AccessArticle
Weighted Ensemble Object Detection with Optimized Coefficients for Remote Sensing Images
ISPRS Int. J. Geo-Inf. 2020, 9(6), 370; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi9060370 - 04 Jun 2020
Cited by 2 | Viewed by 829
Abstract
The detection of objects in very high-resolution (VHR) remote sensing images has become increasingly popular with the enhancement of remote sensing technologies. High-resolution images from aircrafts or satellites contain highly detailed and mixed backgrounds that decrease the success of object detection in remote [...] Read more.
The detection of objects in very high-resolution (VHR) remote sensing images has become increasingly popular with the enhancement of remote sensing technologies. High-resolution images from aircrafts or satellites contain highly detailed and mixed backgrounds that decrease the success of object detection in remote sensing images. In this study, a model that performs weighted ensemble object detection using optimized coefficients is proposed. This model uses the outputs of three different object detection models trained on the same dataset. The model’s structure takes two or more object detection methods as its input and provides an output with an optimized coefficient-weighted ensemble. The Northwestern Polytechnical University Very High Resolution 10 (NWPU-VHR10) and Remote Sensing Object Detection (RSOD) datasets were used to measure the object detection success of the proposed model. Our experiments reveal that the proposed model improved the Mean Average Precision (mAP) performance by 0.78%–16.5% compared to stand-alone models and presents better mean average precision than other state-of-the-art methods (3.55% higher on the NWPU-VHR-10 dataset and 1.49% higher when using the RSOD dataset). Full article
(This article belongs to the Special Issue Machine Learning for High Spatial Resolution Imagery)
Show Figures

Figure 1

Back to TopTop