Identifying and Counting Tobacco Plants in Fragmented Terrains Based on Unmanned Aerial Vehicle Images in Beipanjiang, China
, Tian Zhang 1,2,3 and Wenhui Zhang 1,2,3
Round 1
Reviewer 1 Report
The authors aim to count the tobacco plant in fragmented terrains such as mountainous plateau areas.
The manuscript is quite interesting. My concerns are as follows:
- Title: There is a huge characteristic difference among crops. Focusing on the tobacco plant is good. UAV and RGB abbreviations are not widely known. The title should be rewritten as "Identifying and counting tobacco plants in fragmented terrains based on Unmanned Aerial Vehicle images in Beipanjiang, China"
- Abstract: What is UAV? What is ExG-ExR? Too many abbreviations without prior descriptions.
- The authors mentioned the mixed/intercropping crops nature of tobacco planting on the mountainous plateau in China. How do you distinguish between tobacco and other plants (such as grass, weed, corn, etc) from their color and spectral bands alone? Even in Figure 4, they very much look alike. Sorry, I am not convinced that just a simple low-pass filter can help the detection accurately, let alone counting the object.
- To accurately count the trees you need to create bounding boxes or bounding circles. There is no detailed explanation of how this parameter is set in the manuscript.
- Table 3 shows the enhancement process of the image. My main concern here is that the process might somehow help in counting some plant objects, however how to ensure which particular objects are tobacco plants and which are just wild plants, corns, etc?
- Figure 1 should be improved. Add the location of your study area from the map of China.
- Figure 4 is unreadable, there are a lot of Chinese characters that are unknown to international readers.
- Formulas 2-3 are unreadable.
- All formula writing is very poor. I doubt that you used a proper equation writing style.
- The English writing in this manuscript needs a huge improvement. I would recommend professional proofreading.
Author Response
On behalf of my co-authors, we thank you very much for giving us this opportunity to revise our manuscript. we appreciate editors and reviewers very much for your positive and constructive comments and suggestions on our manuscript entitled “Identifying and counting tobacco plants in fragmented terrains based on Unmanned Aerial Vehicle images in Beipanjiang, China” (ID: 1750101). Those comments are all valuable and very helpful for revising and improving our paper. We have studied the comments very carefully and tried our best to improve our manuscript. Our point-by- point response to the comments made by editors and reviewers are given below. We have also marked changes in the manuscript with red. We hope the revised manuscript will be accepted. The English style of this article, I will continue to revise.Please look at the attachment. Thank you again for your valuable comments and suggestions
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Based on the color index, this study proposed an accurate extraction method for tobacco plant information from UAV remote sensing images in mountainous plateau areas. To this end, a Phantom 4 Pro V2.0 quadrotor UAV was used to collect images of the tobacco plant growing land in the study area of Beipanjiang river town. Overall the manuscript is well written and interesting. However, the authors should address the following points before the final publication.
1. For section 1, the authors should provide the comments of the cited papers after introducing each relevant work. What readers require is, by convinced literature review, to understand the clear thinking/consideration of why the proposed approach can reach more convincing results. This is the very contribution from the authors.
2. In addition, authors should also provide a more critical literature review to indicate the drawbacks of existing approaches, then define the main stream of research direction. How did those previous studies perform?
3. Provide the structure of the manuscript at the end of section 1.
4. Increase the font size of x and y labels as well as of legends in the figures.
5. Include a section of discussion in the manuscript.
6. Add future recommendations in the manuscript.
Author Response
On behalf of my co-authors, we thank you very much for giving us this opportunity to revise our manuscript. we appreciate editors and reviewers very much for your positive and constructive comments and suggestions on our manuscript entitled “Identifying and counting tobacco plants in fragmented terrains based on Unmanned Aerial Vehicle images in Beipanjiang, China” (ID: 1750101). Those comments are all valuable and very helpful for revising and improving our paper. We have studied the comments very carefully and tried our best to improve our manuscript. Our point-by- point response to the comments made by editors and reviewers are given below. We have also marked changes in the manuscript with red. We hope the revised manuscript will be accepted.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
I appreciate the authors' effort to modify and improve the manuscript based on my previous concerns.
The manuscript has been much better.
The following are my further concerns based on the authors' revision:
- Figure 3 is never mentioned in the manuscript's description
- Figure 4: there should be a legend describing each line's color meaning
- It is good to see the differences in RGB band values among tobacco, weed, and corn plants in a visual manner. However, there should be a statistical test to clearly define that the RGB value differences are significant, especially among tobacco and weed.
Author Response
Dear Editors and Reviewers,
On behalf of my co-authors, we thank you very much for giving us this opportunity to revise our manuscript. we appreciate editors and reviewers very much for your positive and constructive comments and suggestions on our manuscript entitled “Identifying and counting tobacco plants in fragmented terrains based on Unmanned Aerial Vehicle images in Beipanjiang, China” (ID: 1750101). We have studied the comments very carefully and tried our best to improve our manuscript. Our point-by- point response to the comments made by editors and reviewers are given below. We have also marked changes in the manuscript with red. We hope the revised manuscript will be accepted.
Author Response File: Author Response.pdf
