Next Article in Journal
Modelling Electricity Consumption in Cambodia Based on Remote Sensing Night-Light Images
Next Article in Special Issue
A GIS-Based Approach for Primary Substations Siting and Timing Based on Voronoi Diagram and Particle Swarm Optimization Method
Previous Article in Journal
Design of Model-Based and Model-Free Robust Control Strategies for Lower Limb Rehabilitation Exoskeletons
Previous Article in Special Issue
Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Applied Sciences
Volume 12
Issue 8
10.3390/app12083972
Review Report
applsci-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

Remote Sensing Scene Data Generation Using Element Geometric Transformation and GAN-Based Texture Synthesis

Appl. Sci. 2022, 12(8), 3972; https://doi.org/10.3390/app12083972
by Zhaoyang Liu 1, Renxiang Guan 1, Jingyu Hu 1, Weitao Chen 1,2 and Xianju Li 1,2,*
Reviewer 1:
Graziella Del Duca
Reviewer 2: Anonymous
Appl. Sci. 2022, 12(8), 3972; https://doi.org/10.3390/app12083972
Submission received: 25 February 2022 / Revised: 7 April 2022 / Accepted: 11 April 2022 / Published: 14 April 2022
(This article belongs to the Special Issue GeoAI: Integration of Artificial Intelligence, Machine Learning and Deep Learning with GIS)

Round 1

Reviewer 1 Report

While is clearly explained, in the proposed article, that the classification of high-resolution remote sensing scene data is the basis of land resource management, natural resource management, urban planning, etc.,  the applicability of the RSSI generated by a synthetic  process is not specified.

Ethical awareness for artificial intelligence should be discussed in the proposed article. Once specified the possible fields of application, please, address the possible ethical issues that the usage of synthetic instances of data (that can pass for real data to the human eye and to the machine itself) could generate in real life.

Typo

Line 257: Berkeley not in bibliography

Line 341: also repeated twice

Line 346-350:  All the introduction text in the "Discussion" section is taken from the Template provided by the editors. Please, remove/replace it.

Suggestions:

Figure 3. Classes description too small (river, meadwod, island, forest, lake)

 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The work exposes a method of generating scene data using GAN to augment the data sets needed for remote image classification algorithms. The objectives and the proposed method are very clearly indicated. It is recommended to explain more consistently the results and the advantages that are achieved. There are no improvements in the accuracy of the classification, as is the case in the references provided by the authors.
Line 253 should be corrected as the equation changes the format.
On line 416 the name of the dataset used should be in uppercase as in the rest of the document.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Misunderstanding at Point 6: Figure 3. Classes description too small (river, meadow, island, forest, lake): please note the reviewer meant that the font size of the text (river, meadow, island, forest, lake) on the images in Figure 3 is too small and unreadable. Please increase font size.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Back to TopTop