Rapid Target Detection of Fruit Trees Using UAV Imaging and Improved Light YOLOv4 Algorithm
Round 1
Reviewer 1 Report (Previous Reviewer 3)
Authors provided a revised version of the manuscript. I have no further comments.
Author Response
Thank you very much for your kindly comments on our manuscript. There is no doubt that these comments are valuable and very helpful for revising and improving our manuscript. Thank you again for your positive and constructive comments and suggestions on our manuscript.
Author Response File: Author Response.doc
Reviewer 2 Report (Previous Reviewer 2)
The authors took the comments and made a considerable effort to improve the manuscript and the presentation of the figures.
Author Response
Thank you very much for your kindly comments on our manuscript. There is no doubt that these comments are valuable and very helpful for revising and improving our manuscript. Thank you again for your positive and constructive comments and suggestions on our manuscript.
Author Response File: Author Response.doc
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
Dear authors,
It was a pleasure to evaluate your work: Rapid target detection of fruit trees using UAVimagingand3 improved light YOLOv4 algorithm. I would like to congratulate the authors for this important research. The paper is very well written, but it missed a better expectation about the accuracy evaluation. It is unclear how the authors assessed the accuracy of detection, recognition and counting. I do not recommend the article for publication, at this moment, because the accuracy was not appropriate evaluated. Measures of concordance would be the most recommended path.
Best regards.
Reviewer 2 Report
The manuscript entitled "Rapid target detection of fruit trees using UAV imaging and improved light YOLOv4 algorithm" addresses an interesting topic: tree detection through algorithms.
Usually, detection algorithms are used in qualitative forest inventories for counting mortality in recently planted stands (e.g., quality assessments) and, more recently, for species identification in mixed-species stands and natural forests. Thus, this theme and the different methods used for this purpose are somehow stressed in the literature.
Despite that, the authors compared different models to detect fruit trees in orchards, resulting in crucial data for orchards owners and their decision-making process regarding any intervention. However, the manuscript presents several problems related to formatting and writing. Nonetheless, the logical sequence of the ideas is confusing; for example:
- Lines 162-164: this sentence appears to be a recommendation rather than a methodological description;
- Lines 364-376: This entire paragraph seems to be a methodological description;
- Discussion: in this section, the authors wrote down their observations on the results and forgot to input the literature knowledge and gaps and adequately discuss the implications of their results. My statement is reinforced when no reference to related studies or citations can be found.
- Avoid using the following terms: much, good, or at least bring any comparison for reference.
- Improve study area description.
Before adding any comment on the methodological issues, I believe that the authors and the future audience would benefit if the manuscript suffers major revision regarding its organization and writing. Therefore, please avoid extensive and exhaustive phrases and adequately introduce the challenges faced by the orchard's owners and how your study helped to overcome them.
Reviewer 3 Report
Find my comments attached.
Comments for author File: Comments.pdf