Call for Papers: New Trends in UAV Remote Sensing: A Deep Learning Approach

Unmanned aerial vehicles (UAVs) are increasingly understood to be valuable equipment that may help facilitate humans in various operations, including control and testing, remote monitoring, mountain rescue, discovery, logistics, and transport. Thanks to recent technology advancements, practical applications for such missions in both civilian and defense contexts have seen significant development. Currently, unmanned aerial vehicles are employed to capture a range of remote sensing data. Smart remote sensing enables ultra-resolution collections in constrained or inaccessible areas, making it a viable replacement or addition to spacecraft or aircraft sensors. Because of their potential, low-cost, and dynamic data collection compared to those other acquisitions and processing methods, UAVs are progressively emerging as unique and expensive equipment to execute various environmental planning and surveying operations. Deep Learning (DL) is an Artificial Neural technique that employs several hidden units and additional permutations to improve and provide learning sequences that are superior to those provided by a Conventional Neural network. The images produced by UAV sensors have a higher image quality; when compared to circling and potentially other airborne sensor technologies, landscape mapping with UAV systems offers some advantages.

 Due to less atmospheric interference, the ability to operate at low elevations, and, most crucially, low operating expenses, this collection technique is used on commercial and scientific expeditions. On the other hand, a visual examination of many different items could be time-consuming, biased, and inaccurate. Numerous applications in the field of vehicle detection photography have benefited from deep learning approaches. Researchers investigated the possible application of shallower knowledge or traditional statistical techniques to support laborious human activities and improve standard measurements as the applicability of such networking develops across numerous wireless sensing sectors. Precision farming has greatly benefited from modern research that combines UAV-enabled images with DL methods. Such systems focus on image and semantic segmentation for tasks like collecting plants, identifying plantations' borders, identifying planting sites, and other difficulties. Crops and invasive organisms, such as herbicides, are divided using phenotypic sensing, growth and productivity, and other methods. These programs offer a wide variety of mapping possibilities, largely because most tasks will still be carried out by hand utilizing human visual analysis. Many UAV concepts developed in a forestry analysis may be used in urban settings, opening up a vast area for future research to assess Deep Learning-enabled modeling in this context. Such applications must consider diverse scientific consequences because urban areas present distinct challenges for tree monitoring.

This special issue examines the current advancements in deep learning for remote sensing by unmanned aerial vehicles, along with their difficulties and immediate advantages. This contribution supports researchers' innovative solutions and academic publications that address the issues above for effective remote sensing systems.

The Special Issue is open for contributions related to but not limited to the following topics:

-                 Machine Learning Techniques for Advanced Remote Sensing Applications

-                 Impacts and Effects of Vehicle Sensors in UAV Imagery

-                 Deep learning-enabled Image Recognition Applications

-                 Convolutional Neural Network for UAV Imagery Methodologies

-                 Computer Vision-enabled UAV Remote Sensor Applications

-                 Intelligent Techniques for Advanced Global Positioning Systems

-                 Unmanned Aerial Vehicles in Precision Agriculture Application

-                 Multi-agent Reinforcement Learning for Remote Sensing System

-                 Spatial analysis and visualization on 5G network-assisted UAV

-                 The Complete Vision of Geographic Information Systems

-                 Utilizing Computer-aided design for Next-Generation UAVs

-                 DL-assisted Remote Sensing to Locate and Recognize Weeds in Agricultural Area

-                 Advanced 3D Visualization by Unmanned Aerial Vehicles


Manuscripts can be submitted under the following link: http://www.editorialmanager.com/jgsa/default.aspx

The topical collection (special issue) will be closed on May 1, 2023

You can find the Instructions for Authors here. Please direct any questions regarding the Special Issue to one of the guest editors:

Abdu Saif, Department of Electrical Engineering,

University of Malaya,

Kuala Lumpur, Malaysia.

Email: abduh.saif2017@siswa.um.edu.myabduh.saif.signaltech@gmail.com


Saeed Hamood Alsamhi, Software Research Institute, Athlone Institute of Technology

Technical University of the Shannon: Midlands Midwest, Athlone, Westmeath, Ireland.

Faculty of Engineering, IBB University, Ibb 70270, Yemen.
Email: salsamhi@ait.ie


Ahmed M Al-samman, Norwegian University of Science and Technology

Department of Manufacturing and Civil Engineering

Gjovik, Norway, 2815
Email: ahmedma@stud.ntnu.no

Working on a manuscript?

Avoid the most common mistakes and prepare your manuscript for journal editors.

Learn more