Next Article in Journal
Compact High-Directivity Contra-Directional Coupler
Previous Article in Journal
A 320 μW Multi-Band Receiver with N-Path Switched-Capacitor Networks
 
 
Article
Peer-Review Record

A Classification Method for Airborne Full-Waveform LiDAR Systems Based on a Gramian Angular Field and Convolution Neural Networks

Electronics 2022, 11(24), 4114; https://doi.org/10.3390/electronics11244114
by Bin Hu 1,2,3, Yiqiang Zhao 1,2,*, Jiaji He 1,2,*, Qiang Liu 1,2 and Rui Chen 1,2
Reviewer 1:
Reviewer 2: Anonymous
Reviewer 3:
Reviewer 4:
Electronics 2022, 11(24), 4114; https://doi.org/10.3390/electronics11244114
Submission received: 8 November 2022 / Revised: 30 November 2022 / Accepted: 8 December 2022 / Published: 9 December 2022
(This article belongs to the Section Computer Science & Engineering)

Round 1

Reviewer 1 Report

The proposed study is interesting. However, there are some concerns which must be addressed. The comments are as follows:

1. Please incorporate the value of the precision and the f1 score achieved using proposed method.

2. Incorporate manuscript organization at the end of Section 1.

3. The literature review is very limited. Consider adding some more studies so that the readers can get an in-depth view related to machine learning and deep learning algorithms applied in LiDAR study.

4. Modalities of Bathymetry and Urban full wave form is illustrated well. However, it is important to incorporate a complete flowchart / pseudocode of the proposed CNN model.

5. Please elaborate on the train and test model. Are heat map images being used as the inputs?

6. Results are described well. Conclusion is ok.

7. Please give a thorough language check.

 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and observations on the paper can be found in the attached file.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

 

 Authors have presented a Classification Method for Airborne LiDAR Full Waveform using CNN

1. It is better to add some theoretical analysis to the experimental results to clarify the reasons why the proposed method is better.

2. Too long a sentence affects comprehension. The structure, format, and grammar of the paper need to be improved.

3. Explain the dataset in detail & how many images are taken for experiments. Do authors check the impact of preprocessing ?

4. What if the authors use some other classifiers of deep learning, then the results might be better. However, if they have already applied other classifiers please state the reasons for selecting this classifier.

5.Analysis & comparison is not strong, authors are required to compare their results in latest state of the art.

6. Some figure's quality is not up to the mark & that requires author's attention.

7. Abstract should be more comprehensive.

8. Make sure all Figures should be cited in the article.

 

9. More recent state of the art should be discussed and better to include a Table to show so far progress in this area & need of this research will have a better impact on the readers.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 4 Report

1. Add efficiency analysis in terms of No. of parameters and consumed time and memory.

2. Add case study analysis.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have well addressed the corrections.

Reviewer 3 Report

Accepted in present form.

Thanks for the improvements.

 

Back to TopTop