EYOLOv3: An Efficient Real-Time Detection Model for Floating Object on River

Round 1

Reviewer 1 Report

(1)The abstract is too long. Please shorten/condense it.

(2)Please check the manuscript carefully to remove the typos, improve the language and format.

E.g.

-”The” is on the surface of Table 3.

...

(3)Why not use YOLOv5 or higher version of YOLO?

(4)The review of the related works and comparison experiments can be more sufficient. Please carefully read, cite and compare (if applicable) the following papers.

Multi-scale fusion and online hard example mining for the improvement of deep learning:

-Mask Refined R-CNN: A network for refining object details in instance segmentation

-Object detection based on multi-layer convolution feature fusion and online hard example mining

Novel NSM technology:

-Syncretic-NMS: A merging non-maximum suppression algorithm for instance segmentation

If the authors cannot employ these methods or compare their method with these methods, at least they could introduce/mention these novel technologies in Sections 1 and 2 to improve the quality of the survey, or explain them as the possible future works.

(5)Table 4 does not contain all the important parameters. The authors should provide all the parameters directly in Fig. 2 or in an additional table.

(6)In my opinion, clustering is time-consuming. How about the speed of K-means++?

(7)Please provide the x-label and y-label in Fig. 5.

(8)Please provide and label the reference indices of the compared methods in the figures and tables, and then the readers can judge whether the compared methods are SOTA.

(9)Please use bold font to label the best results in all tables.

(10)In Table 6, since the authors use many technologies to improve YOLOv3, why do EYOLO3 and YOLOV3 have the same FPS?

Author Response

Dear Reviewer,

Thank you very much for your constructive comments and suggestions on our manuscript entitled “EYOLOv3: An Efficient Real-time Detection Model for Floating Object On River” (applsci-2142915). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. According to the associate editor and reviewers’ comments, we have made extensive modifications to our manuscript and supplemented extra data to make our results convincing. We have tried our best to polish the language. In this revised manuscript, we using the “Track Changes” indicating changes. The point-by-point response to the comments are provided in the Word file.

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

Yours sincerely.

<Lili Zhang>et al.

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments for author File: Comments.pdf

Author Response

Dear Reviewer,

Thank you very much for your constructive comments and suggestions on our manuscript entitled “EYOLOv3: An Efficient Real-time Detection Model for Floating Object On River” (applsci-2142915). Those comments are all valuable and very helpful for revising and improving our paper, as well as the important guiding significance to our researches. According to the associate editor and reviewers’ comments, we have made extensive modifications to our manuscript and supplemented extra data to make our results convincing. We have tried our best to polish the language. In this revised manuscript, we using the “Track Changes” indicating changes. The point-by-point response to the comments are provided in the Word file.

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

Yours sincerely.

<Lili Zhang>et al.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Accept.

Author Response

Response to Reviewer 1 Comments

Thank you very much for accepting our manuscript entitled “EYOLOv3: An Efficient Real-time Detection Model for Floating Object on River” (applsci-2142915). We have carefully checked the English language and style, and corrected spelling errors in the revised manuscript. In this revised manuscript, we using the “Track Changes” indicating changes.

Once again, Thank you very much for your review.

Reviewer 2 Report

Minor corrections

Line 106, “Edlgelet” should be “Edgelet”.

Line 158, “…but is still not efficient…” should be “…but is still not effective…”.

Line 569, “Dan et al.” should be “Munteanu et al.”.

Comments for author File: Comments.docx

Author Response

Dear Reviewer,

Thank you very much for your comments and suggestions on our manuscript entitled “EYOLOv3: An Efficient Real-time Detection Model for Floating Object on River” (applsci-2142915). In this revised manuscript, we using the “Track Changes” indicating changes. The point-by-point response to the comments are provided in the Word file. Please see the attachment.

Once again, thank you very much for your review.

Yours sincerely.

<Lili Zhang>et al.

Author Response File: Author Response.docx