Next Article in Journal
An Accurate Digital Subsidence Model for Deformation Detection of Coal Mining Areas Using a UAV-Based LiDAR
Previous Article in Journal
Underground Morphological Detection of Ground Fissures in Collapsible Loess Area Based on Three-Dimensional Laser Scanning Technology
 
 
Article
Peer-Review Record

A Fusion-Based Defogging Algorithm

Remote Sens. 2022, 14(2), 425; https://doi.org/10.3390/rs14020425
by Ting Chen 1, Mengni Liu 1, Tao Gao 1,*, Peng Cheng 2, Shaohui Mei 3 and Yonghui Li 2
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Remote Sens. 2022, 14(2), 425; https://doi.org/10.3390/rs14020425
Submission received: 7 December 2021 / Revised: 7 January 2022 / Accepted: 12 January 2022 / Published: 17 January 2022

Round 1

Reviewer 1 Report

The paper presents a really interesting algorithm to remove the fog effect on remote-sensed images.

Although the research has a great scientific soundness, it is not clearly explained.

At first, the title says "A UAV Sensing Fusion-based.." so a reader would expect at least a presentation of the study areas, where and how the images was acquired. Were they acquired by UAV? Which flight parameters were used? Which kind of camera? Instead the paper is exclusively concentrated on the algorithms.

For the same reason, I would improve the abstract, because it is not very clear the aim of your work and the real added value of the research.

I also suggest to improve the English of the paper. There are a lot of long sentences which are difficult to be read and followed, or sometimes the main sentence misses (for example in lines 33-34).

I would improve the overall structure of the paper, because in this state, it is very confusing. There are too much sub-paragraphs not well correlated. For example, paragraph 2, as it presents the algorithms used in literature, should be introduced in the state of art, and not as an isolated paragraph. In addition, in this paragraph, many terms in the equations are not clearly described, like in line 171. There is I_c(x), but it does not appear in the previous equations, or the t with the tilde above is not introduced.

I would enhance materials and methods, describing where the images were acquired, in which conditions, which altitude, which situations (I suppose they are different in order to test the proposed algorithms), so that a researcher can reproduce the experiments.

Please, improve the readability of the figures, they are blurred and too small, making it difficult to be read. If you use sub-figures, like in figure 3, please describe in the captions what they represent one by one.

The results are well described, as well as the discussion and conclusions, but also in this case, please edit the English.

Author Response

Dear Editor and Reviewers:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “A UAV Sensing Fusion-based Defogging Algorithm”. Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

Responds to the reviewer’s comments:

 

The paper presents a really interesting algorithm to remove the fog effect on remote-sensed images. Although the research has a great scientific soundness, it is not clearly explained.

 

1 Response to comment:

At first, the title says "A UAV Sensing Fusion-based.." so a reader would expect at least a presentation of the study areas, where and how the images was acquired. Were they acquired by UAV? Which flight parameters were used? Which kind of camera? Instead the paper is exclusively concentrated on the algorithms.

Response:

Special thanks to you for your good comments. Our paper aims to exclusively concentrate on defogging algorithm for UAV foggy images to acquire clear image and lay the foundation for further effective analysis . The images tested in this paper are remote sensing images of UAV with various flight parameters collected from the Internet platform. Our algorithm is an improved method based on the traditional dark channel defogging algorithm. Experimental results demonstrate that the improved algorithm achieves superior performance for the foggy images captured by UAV.

 

2 Response to comment:

For the same reason, I would improve the abstract, because it is not very clear the aim of your work and the real added value of the research.

Response:

Special thanks to you for your good comments. The aim of our algorithm is improvement of the traditional dark channel defogging algorithm, which overcome some drawbacks that the dark channel is not suitable for the large white area. We have improved the description of the abstract, and elaborated the aim and significance of the work in this paper according to the reviewer’s comments.

 

3 Response to comment:

I also suggest to improve the English of the paper. There are a lot of long sentences which are difficult to be read and followed, or sometimes the main sentence misses (for example in lines 33-34).

Response:

Special thanks to you for your good comments. We are very sorry that the paper uses a lot of long and obscure sentences, which are not easy for readers to understand, and there are some omissions of main sentences. We have invited a proficient native speaker to help check the paper carefully and corrected the grammatical problems in this paper. Some corrections are listed as follows:

 

4 Response to comment:

I would improve the overall structure of the paper, because in this state, it is very confusing. There are too much sub-paragraphs not well correlated. For example, paragraph 2, as it presents the algorithms used in literature, should be introduced in the state of art, and not as an isolated paragraph.

Response:

Special thanks to you for your good comments. We are very sorry that some sub-paragraphs not well correlated. The chapters are reorganized according to the algorithm flow. We have adjusted the overall structure of the paper, improving the second chapter as related work of the paper, and strengthening the relevance of the paragraphs.

 

5 Response to comment:

In addition, in this paragraph, many terms in the equations are not clearly described, like in line 171. There is I_c(x), but it does not appear in the previous equations, or the t with the tilde above is not introduced.

Response:

Special thanks to you for your good comments. We are very sorry that we neglected the description of some terms in some formulas. We have added the description of missing terms.

 

6 Response to comment:

I would enhance materials and methods, describing where the images were acquired, in which conditions, which altitude, which situations (I suppose they are different in order to test the proposed algorithms), so that a researcher can reproduce the experiments.

Response:

Special thanks to you for your good comments. The experimental images in this paper are all foggy images collected on the Internet platform, under different weather conditions and different flight parameters, which guarantee the effectiveness of experiments. Moreover, if subsequent researchers are interested in our algorithm, we will provide relevant codes and experimental materials for researchers to reproduce the experiment.

 

7 Response to comment:

Please, improve the readability of the figures, they are blurred and too small, making it difficult to be read. If you use sub-figures, like in figure 3, please describe in the captions what they represent one by one.

Response:

Special thanks to you for your good comments. We are very sorry for blurred figures. We have adjusted the images and corrected the caption of figures to make sure the readability.

8 Response to comment:

The results are well described, as well as the discussion and conclusions, but also in this case, please edit the English.

Response:

Special thanks to you for your good comments. We have improved the discussion and conclusions . In addition, we have improved the English writing.

We tried our best to improve the manuscript and made some changes in the manuscript. And here we did not list all the changes in revised paper.

We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

Once again, thank you very much for your comments and suggestions.

 

 

Author Response File: Author Response.docx

Reviewer 2 Report

The paper presents author's contribution to defog algorithms. The main contribution is in the application of mixed dark channel.

From the paper is not clear how the inner coefficients (like p, q, m, n etc.) were established. Is it constant or calculated for each case?
What was a dataset to test an algorithm performance? Is it available on-line?  From here the tables 1-4 were calculated just for images 12-15?

Is proposed algorithm valid for all types of fog known from aerounatics? Fog, "brume", and haze. 

The paper contains many typhograpic mistakes like missing space between words and formulas. The quality of some images needs to be improved. Some comments in figures are difficult to read.

 

Author Response

Dear Editor and Reviewers:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “A UAV Sensing Fusion-based Defogging Algorithm”. Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

Responds to the reviewer’s comments:

 

The paper presents author's contribution to defog algorithms. The main contribution is in the application of mixed dark channel.

 

1 Response to comment:

From the paper is not clear how the inner coefficients (like p, q, m, n etc.) were established. Is it constant or calculated for each case?

Response:

Special thanks to you for your good comments. The coefficients including p, q, m and n are adjusting constants, among which m and n are parameters for adjusting atmospheric light values, p and q are adjusting parameters in the compensation model. Since atmospheric light is often overvalued when it is obtained through dark channels, resulting in distortion of the restored image. We introduce adjusting constants m and n for appropriate adjustment, and finally determine the values of m and n through a large number of comparison experiments and optimal evaluation indexes. Since the restored image is difficult to achieve visual effects suitable for human eyes, we introduce the compensation model for color restoration, and determine the values of p and q through comparison experiments under different parameters.

2 Response to comment:

What was a dataset to test an algorithm performance? Is it available on-line?  From here the tables 1-4 were calculated just for images 12-15?

Response:

Special thanks to you for your good comments. We are very sorry for our negligence of vague description. The images are collected from the internet. The details of data collection and setting refer to the literature: “Ma K, Liu W, Wang Z. Perceptual evaluation of single image dehazing algorithms[C]//2015 IEEE International Conference on Image Processing (ICIP). IEEE, 2015: 3600-3604.” The test dataset is not available on-line now. However, we will upload the dataset and relevant codes to website in the future. If subsequent researchers are interested in our algorithm, we are pleasure to provide corresponding experimental data sets and experimental codes. Table1-4 corresponds to Figure 12-15 respectively, listing the evaluation parameter values of five defogging algorithms in four groups of comparative experiments.

 

3 Response to comment:

Is proposed algorithm valid for all types of fog known from aerounatics? Fog, "brume", and haze. 

Response:

Special thanks to you for your good comments. Our algorithm is effective for aerial images under foggy days taken by UAV and frequent fog in remote sensing images. In this paper, the name of fog is unified and changed to “fog”.

 

4 Response to comment:

The paper contains many typhograpic mistakes like missing space between words and formulas. The quality of some images needs to be improved. Some comments in figures are difficult to read.

Response:

Special thanks to you for your good comments. We are very sorry for the typhograpic mistakes in this article. We have corrected all the typhograpic mistakes and modified the caption of all images.

 

We tried our best to improve the manuscript and made some changes in the manuscript. And here we did not list all the changes in revised paper.

We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

Once again, thank you very much for your comments and suggestions.

 

 

Author Response File: Author Response.docx

Reviewer 3 Report

This paper is excellent. It is well presented, all methods are clearly and scientifically described, results and comparison with other approaches are given, references are recent and relevant.

Author Response

Dear  Reviewers:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “A UAV Sensing Fusion-based Defogging Algorithm”. Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

Responds to the reviewer’s comments:

 

This paper is excellent. It is well presented, all methods are clearly and scientifically described, results and comparison with other approaches are given, references are recent and relevant.

 

We tried our best to improve the manuscript and made some changes in the manuscript. And here we did not list all the changes in revised paper.

We appreciate for Editors/Reviewers’ warm work earnestly, and hope that the correction will meet with approval.

Once again, thank you very much for your comments and suggestions.

 

 

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Dear authors, the paper has improved both from the English point of view and to the image, structure and explanation quality.

Although the conclusions was not so different from the previous version of the manuscript, the rest of the paper is now well written and clearer, so it is almost ready to be published.

Just a last remark:

I understand that you took the images from Internet platform, but I would specify at least how you chose the various images. Which kind considerations have you made to choose the different scenarios? Are there logic reasons that guided you to these choices? I would specify that in few lines in the paper.

Moreover, the manuscript has a template different from the journal template. Why?

However, congratulation for the interesting work.

 

Author Response

Dear Editor and Reviewers:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “A novel UAV Sensing Image Defogging Method”. Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and have made correction which we hope meet with approval. The main corrections in the paper and the responds to the reviewer’s comments are as flowing:

Responds to the reviewer’s comments:

1 Response to comment:

I understand that you took the images from Internet platform, but I would specify at least how you chose the various images. Which kind considerations have you made to choose the different scenarios? Are there logic reasons that guided you to these choices? I would specify that in few lines in the paper.

Response:

Special thanks to you for your good comments. We are very sorry that we did not clearly explain the specific content of the experimental data set. We selected 50 remote sensing images in common scenes, such as coastal towns, ports, fields, villages, mountain roads, etc., and these remote sensing images contain fog of different degrees. We restored 50 foggy images with five defogging algorithms respectively, and formed 50 data sets containing one original foggy image and five restored images for comparison experiments. We have added the description of data set in the experiment section.

2 Response to comment:

Moreover, the manuscript has a template different from the journal template. Why?

Response:

Special thanks to you for your good comments. We are very sorry that we did not modify according to the template provided by your magazine. We have corrected the format of the article.

Author Response File: Author Response.docx

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.


Back to TopTop