Research on Grape-Planting Structure Perception Method Based on Unmanned Aerial Vehicle Multispectral Images in the Field

Round 1

Reviewer 1 Report (Previous Reviewer 1)

The author has solved all the problems I raised as required. I recommend that this article be published.

Reviewer 2 Report (Previous Reviewer 2)

The authors answered the questions point by point. Significantly improving the text and presentation of results. Therefore, my decision is to accept the publication of this paper.

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

The authors exploited different features of the multispectral images for the extraction of the grape growing area. The topic, although it may be of interest to the reader, still has the following problems. 

1. The full names of the abbreviations appear too many times in the manuscript and only need to be marked on the first occurrence (e.g. SVM, MCL, DCNN, ASPP).

2. Line 26: Does spectral information refer to reflectance?

3.  Line 27, 57: Abbreviations in the abstract need to be provided with the full spelling the first time they appear (e.g. OA and FW-IOU).

4.  Line 36, 94: The unit superscript needs to be corrected.

5. A space is required between the reference and the text.

6. The introduction section lacks a description of this study as well as its purpose.

7. The name of the software that appears in the manuscript needs to provide its basic information, such as manufacturer, location , and country (e.g. PIX4D, ENVI, ARCGIS).

8. The basic algorithms and methods in the manuscript require corresponding references, such as VIs and OIFs.

9. In 2.4.1 section, The SD in equation 1 needs to be provided with its meaning.

10. For the accuracy of area extraction, I believe that the classification accuracy should not only include the comparison of quantity, but also need to provide confusion matrix to judge the accuracy of classified pixels. Therefore, the results of equation 2 are not sufficient to indicate the true accuracy.

11. Textures used in the manuscript need to be listed in the Methods section with their definitions and full spellings.

12. The indicators in Table 6 need to be interpreted for their significance.

13. The discussion section should specify the role and rationale of the different parameters and DeepLabV3+ for the improved accuracy of grape area extraction.

 

Author Response

尊敬的审稿人：

感谢您的来信和审稿人对我们题为“基于无人机多光谱野外图像的葡萄种植结构感知方法研究”（ID：agriculture-1898943）的稿件的评论。这些评论都很有价值，对我们的论文的修改和改进都非常有帮助，对我们的研究也具有重要意义。我们仔细研究了评论，并进行了更正，希望得到批准。修订后的部分在论文中标有红色。论文中的主要更正和对审稿人评论的回应是流动的。

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear authors, the article deals with the combination of characteristics of vegetation indices and machine learning for monitoring grape growth. Initially, I congratulate you on the article, I believe it is of crucial scientific relevance, but some points need to be better presented.

My suggestions are described in the attached text!

:. important remarks

- The title does not partially match the text presented.

- The intro could be improved

- Discussion and conclusion need a good review.

Comments for author File: Comments.pdf

Author Response

Dear Reviewers:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled“Research on grape planting structure perception method based on Unmanned Aerial Vehicle multispectral image in field”(ID: agriculture-1898943). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our research. We have studied comments carefully and have made the correction which we hope meet with approval. The revised portion is marked in red in the paper. The main corrections in the paper and the responses to the reviewert’s comments are as flowing.

Author Response File: Author Response.pdf