Next Article in Journal
Exploring Spatial Patterns of Virginia Tornadoes Using Kernel Density and Space-Time Cube Analysis (1960–2019)
Previous Article in Journal
Cellular Automata Based Land-Use Change Simulation Considering Spatio-Temporal Influence Heterogeneity of Light Rail Transit Construction: A Case in Nanjing, China
 
 
Article
Peer-Review Record

Detection and Analysis of Degree of Maize Lodging Using UAV-RGB Image Multi-Feature Factors and Various Classification Methods

ISPRS Int. J. Geo-Inf. 2021, 10(5), 309; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10050309
by Zixu Wang 1,2, Chenwei Nie 2, Hongwu Wang 3, Yong Ao 4, Xiuliang Jin 2,*, Xun Yu 2,5, Yi Bai 2, Yadong Liu 2, Mingchao Shao 2,6, Minghan Cheng 2,7, Shuaibing Liu 2,8, Siyu Wang 2,9 and Nuremanguli Tuohuti 2,10
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Reviewer 4: Anonymous
ISPRS Int. J. Geo-Inf. 2021, 10(5), 309; https://0-doi-org.brum.beds.ac.uk/10.3390/ijgi10050309
Submission received: 10 March 2021 / Revised: 27 April 2021 / Accepted: 2 May 2021 / Published: 6 May 2021

Round 1

Reviewer 1 Report

I think the authors had done an excellent job to address most of my concerns. I still have some reservation on the use of ortho image, however, that should not impact on the publication of the work.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The manuscript presents a study addressing maize lodging detection by evaluating different classification approaches (pixel-based, object-based, image thresholding) and by using different features from RGB imagery acquired by and unmanned aerial vehicle.

The study itself does not pose many concerns. The main issue of the manuscript is that the authors must reorganize all the content of the manuscript and making it easier to read and comprehend.

In the Introduction Section there are some references that do not follow a correct placement and references are needed in some sentences.

Seems that the document is not correctly formatted according to the template, the main text is too condensed in the right side of the page. In the Journal template the blank part on the left side of the page is not that large. The tables also not to appear to be in accordance with the template, please correct them.

The methods (Section 2) should be explained in a more concise and fluid way, an example is the description of the different features used in the study. This makes some parts of Section 2 difficult to follow without an extra effort. Please try to reduce the number of subsections in Section 2. There are results in the materials and methods Section, and the opposite is verified in the results Section. 

Please see the remaining comments and suggestions in the attached PDF.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

 

The results are comprehensive, and you did a good job. Here are my comments:

Based on what I read, you improved the quality of the images and then use the classification methods to classify the products, while your abstract says that you pursued more tasks such as optimizing the field management strategies. So, you started the abs with your main goal and then extended it to cover a broader topic, which is not correct here. So, please first talk about the big picture and then narrow it down.

Please clarify along and across in table 3.

The UAV moves at the speed of 2m/s, which is slow, but it takes a lot of time to cover your field. What will happen to the methodology in terms of removing the tilts if we move the device faster?

Your literature is mainly about similar technologies in this field, while you need to consider papers in all areas that studied “rgb-d sensors performance measure,” as the readers are from those fields.

Did you use the GPS to match the images with locations? The accuracy should be bios for about 5 meters, while your resolution is more accurate than that. Can you clarify, please?

Don’t you think that using the SVM would work better than the random forest? Can you explain the reason for using this method?

I get lost by reaching the end of the paper, and I strongly suggest you add a flow chart in the methodology section.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

This paper focuses on the detection of maize lodging using RGB images from UAV. This is an interesting study and the manuscript is decently structured. However, due to its unnecessarily large amount of text, it is easy for the reader to get lost in the text and omit the most important features of the paper.

My main suggestion is to reduce the manuscript length by removing the narrative parts which are not tightly related to the primary focus of the research. There are numerous structural or technical minor mistakes that you probably dropped due to the large quantity of the text. The text which is related to a literature review and which you did not strictly perform should belong to the Introduction, also materials and Methods and Results overlap at some points, which you should need to make a clear distinction to. The sentences in the manuscript are generally too long (like lines 107-113), which negatively affects readability. I suggest restructuring these sentences by forming shorter ones. All figures with maps must contain the fundamental segments: a scale bar and a north arrow.

Lines 31-34: Please split this sentence into two shorter ones.

Lines 82-87: Stating that UAV can provide RGB images with higher spectral resolution compared to satellite images is highly inaccurate. Please correct this.

Line 196: Please replace “hours of sunshine” with something like “solar insolation potential”.

Figure 1: You should add a scale bar and a north arrow for all subfigures. Color scales are very confusing; in terms that a similar shade of red color indicates three different values. Subfigure B contains a lot of details that are not clearly visible. The exact division to experimental plots is unclear in terms of borders. Overall, this figure requires much improvement.

Line 267: Was it a GPS of a GNSS receiver? What was the positioning horizontal and vertical accuracy?

Subsection 2.3.: The first two paragraphs are written more like a literature review, so this should be modified. You should stick to the methods you actually applied in the research and write it that way.

Line 338: Agisoft Photoscan or Metashape?

Line 346: Please check the abbreviation for DEM (derived?).

Line 573: Why 60:40 division? This seems like a lot of data for training.

Lines 587-589: This should not belong to the Materials and Methods section.

Lines 741-744: This should be a part of Materials and Methods.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The authors improved the manuscript according to the comments and suggestions of the reviewers. There are still minor formatting issues present in the document. However, those can be easily solved, as the placement of some tables that are divided in between pages and figures that appear before being mentioned in the main text. Therefore, after correcting those issues, the article will be ready to be considered for publication.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 4 Report

The authors performed adequate corrections based on my previous suggestions and thus improved their manuscript. I still have some minor suggestions before I can recommend this manuscript for publication:

Lines 29-33: This sentence is too long. Please split it into two shorter sentences. It might also be beneficial to first mention the more accurate results (object-oriented).

Line 39: “RGB vegetation index” is weird and inaccurate. Please remove it.

Line 192: “determined” is the more accurate term compared to “measured”.

Line 254: You already introduced the DSM abbreviation.

Figure 16: The text size in this figure is too small, which results in its poor readability. I suggest increasing the width of this figure and possibly increasing the font size.

Author Response

请参阅附件。

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.


Round 1

Reviewer 1 Report

NA

Author Response

Manuscript ID:Ijgi-1070911
Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods
Author: Zixu Wang, Chenwei Nie, Yong Ao, Xiuliang Jin, Xun Yu, Yi Bai, Yadong Liu, Mingchao Shao, Minghan Cheng, Shuaibing Liu, Siyu Wang, Nuremanguli•Tuohuti
Article 
ISPRS International Journal of Geo-Information
Cover letter 
Dear Editor and Reviewers 
First we would like to thank the reviewers for their constructive and helpful suggestions and improvements to our manuscript (ijgi-1070911, Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods). We revised the manuscript by following the suggestions of the reviewers. Our response to each suggestion or comment are given one by one in the following Pages of this letter. For details, please refer to the responses as follows (Reviewer comments are in black font, responses are in blue or red font)
With best regards, 
Zixu Wang and co-authors 

Author Response File: Author Response.docx

Reviewer 2 Report

Very unique approach to lodging classification of corn. Methods are described in detail and with excellent visuals. Use of UAV will certainly become more important in crop production as a tool for crop management and yield predictions.

Author Response

Manuscript ID:Ijgi-1070911
Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods
Author: Zixu Wang, Chenwei Nie, Yong Ao, Xiuliang Jin, Xun Yu, Yi Bai, Yadong Liu, Mingchao Shao, Minghan Cheng, Shuaibing Liu, Siyu Wang, Nuremanguli•Tuohuti
Article 
ISPRS International Journal of Geo-Information
Cover letter 
Dear Editor and Reviewers 
First we would like to thank the reviewers for their constructive and helpful suggestions and improvements to our manuscript (ijgi-1070911, Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods). We revised the manuscript by following the suggestions of the reviewers. Our response to each suggestion or comment are given one by one in the following Pages of this letter. For details, please refer to the responses as follows (Reviewer comments are in black font, responses are in blue or red font)
With best regards, 
Zixu Wang and co-authors 

Author Response File: Author Response.docx

Reviewer 3 Report

Comments for authors are listed below:

Line 27: add scientific name for maize in the brackets

Line 41: use past tense when writing

Line 45: the same comment

Line 73-74: remove all words that exist in the title and give synonyms

Line 78: [1] than goes full stop

Paragraph 77-91: provide more information regarding maize lodging

Paragraph 92-103: it is important to cite literature herein

Line 126:  Han et al. should be reference No 7?

Paragraph 181-196: this part is more like to be a material & methods part. I suggest replacing it. And at the end of the previous paragraph add one or two sentences regarding the importance of your work

Figure 1 should be also replaced because it is a part of M&M

Line 244: which fertilizer was used in the study?

Line 254-255: what is wind force 5-6 level? Can you be more precise? Is it normal to have this kind of wind every year?

Line 309: I think that is better to write in passive throughout all manuscript. Apply it everywhere you have used “WE”

Line 320: add picture source, if they are yours state it

Line 369: the same comments as in line 309

Line 381: remove “on the other hand” in the scientific way it means to switch to other hand

Line 382: the same comment

Besides all suggestions and comments, the M&M part is well written

The result section is very well written.

Table in the line 775: for overall accuracy only one decimal point is quite enough for presenting results

The discussion part is not written well. There is a lack of important references to connect authors work with previous published papers. There are only 6 references, and this part is more like a results part. It must be rewritten

Table 6: put the abbreviation in the table for: average value; coefficient of variation and in the legend provide explanations for all abbreviations used

Author Response

Manuscript ID:Ijgi-1070911
Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods
Author: Zixu Wang, Chenwei Nie, Yong Ao, Xiuliang Jin, Xun Yu, Yi Bai, Yadong Liu, Mingchao Shao, Minghan Cheng, Shuaibing Liu, Siyu Wang, Nuremanguli•Tuohuti
Article 
ISPRS International Journal of Geo-Information
Cover letter 
Dear Editor and Reviewers 
First we would like to thank the reviewers for their constructive and helpful suggestions and improvements to our manuscript (ijgi-1070911, Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods). We revised the manuscript by following the suggestions of the reviewers. Our response to each suggestion or comment are given one by one in the following Pages of this letter. For details, please refer to the responses as follows (Reviewer comments are in black font, responses are in blue or red font)
With best regards, 
Zixu Wang and co-authors 

Author Response File: Author Response.docx

Reviewer 4 Report

Dear authors, the paper presents an interesting application of UAV and remote sensing to an agricultural problem. While the paper has its merits regarding the extensions of the information used in the approach, complementing previous work existing in the literature, I think that some changes are needed in order to reach the publishing stage.

First, the part of the relation between cultivar type, density and nitrogen, and the risk of lodging should be extracted and published separately. There are some papers (like https://0-plantmethods-biomedcentral-com.brum.beds.ac.uk/articles/10.1186/s13007-019-0481-1#:~:text=Maize%20stalk%20lodging%20is%20defined,costs%20to%20harvest%20%5B8%5D.) that show that the canopy is important in lodging intensity. There could be also questions regarding the wind event and the local topography influence on the lodging, so I would not push on this. I would rather leave the paper to bring the novelty to the classification. In this regard, there is a need to conclude on the position of the results in the literature, but not as a simple description of what was done in the past, but to show how the present approach compares and is better to the literature.

Second, I would not say monitoring, but detection or classification, since is a single event, and monitoring means multiples event a long term data.

Punctual observations:

Lines 336-337 - actually you georeferenced the point cloud; please see a paper outlining the steps required to process UAV images for SfM in order to rewrite the SfM part of your paper; 

Lines 339-340 - specify in which CRS the GCPs were acquired and in which CRS the images were processed since the same dataset can have only one CRS, and not two as you say there.

In Fig. 5 there is a c "flying", please resolve it.

Fig. 8 appears to be cut

Fig. 9 a histogram is statistic

You should use codes for non-lodging, severe and light lodging: NL, LL, SL. It will simplify the understanding of the sentences and bring some polish to graphs from the figures.

Overall, the text needs careful review, because there are a lot of citation problems, with the citation appearing after the sentence point or after comas, when it should be before.

 

Author Response

Manuscript ID:Ijgi-1070911
Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods
Author: Zixu Wang, Chenwei Nie, Yong Ao, Xiuliang Jin, Xun Yu, Yi Bai, Yadong Liu, Mingchao Shao, Minghan Cheng, Shuaibing Liu, Siyu Wang, Nuremanguli•Tuohuti
Article 
ISPRS International Journal of Geo-Information
Cover letter 
Dear Editor and Reviewers 
First we would like to thank the reviewers for their constructive and helpful suggestions and improvements to our manuscript (ijgi-1070911, Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods). We revised the manuscript by following the suggestions of the reviewers. Our response to each suggestion or comment are given one by one in the following Pages of this letter. For details, please refer to the responses as follows (Reviewer comments are in black font, responses are in blue or red font)
With best regards, 
Zixu Wang and co-authors 

Author Response File: Author Response.docx

Reviewer 5 Report

Please see the attached file to more details

Comments for author File: Comments.pdf

Author Response

Manuscript ID:Ijgi-1070911
Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods
Author: Zixu Wang, Chenwei Nie, Yong Ao, Xiuliang Jin, Xun Yu, Yi Bai, Yadong Liu, Mingchao Shao, Minghan Cheng, Shuaibing Liu, Siyu Wang, Nuremanguli•Tuohuti
Article 
ISPRS International Journal of Geo-Information
Cover letter 
Dear Editor and Reviewers 
First we would like to thank the reviewers for their constructive and helpful suggestions and improvements to our manuscript (ijgi-1070911, Title: Monitoring degree of lodging of maize using UAV-RGB image multi-feature factors and various classification methods). We revised the manuscript by following the suggestions of the reviewers. Our response to each suggestion or comment are given one by one in the following Pages of this letter. For details, please refer to the responses as follows (Reviewer comments are in black font, responses are in blue or red font)
With best regards, 
Zixu Wang and co-authors 

Author Response File: Author Response.docx

Round 2

Reviewer 3 Report

N/A

Reviewer 4 Report

I saw that the article was edited and I saw the responses to my observations. I maintain my observations regarding (i) the part with causative factors of lodging related to the experiments (which I think is not related to this work - for example, is not included in the title so it's spurious), (ii) the methodology parts need to be well covered since it seems that the paper does not introduce new methods (so the methods should be briefly described and citations need to be included for further references), (iii) English needs to be carefully reviewed.

Reviewer 5 Report

Hello Authors, I don't think you have taken my comments seriously. My concerns in the last round were not addressed adequately. I did not find many changes, and in fact, some of the changes were worse than before. 

Back to TopTop