Lane Crack Detection Based on Saliency
Round 1
Reviewer 1 Report
Dear Authors,
I have read your paper with attention and pleasure.
In my opinion, the manuscript titled Lane crack detection based on saliency presents original research and innovative solutions and could be interesting for readers of the MDPI Remote Sensing Journal. The article deals with very practical and important issues from the point of road users and focuses on pavement conditions monitoring.
The motivation is clear. The object of study, as well as the results, are comprehensively described providing valuable conclusions.
The paper is organised in a logical manner. The state of the art covers the main results in the field. The contributions of the report are clearly stated in the Introduction chapter.
I have no objections to recommending publishing this paper.However, due to the listed below drawbacks, my recommendation is "Reconsider after major revision". In my opinion, several aspects require clarification. Please revise and add some comments and improvements according to the following:
- whether the method can be effective for defects with a less linear shape than those analyzed, for example, point impact damage
- how the effectiveness of the analyzes will be affected by the situation in which the analyzed surface will be disturbed, variable, e.g. in places of supplementing or repairing the surface
-how to protect the inference system against false alarms caused by the presence of joints between the pavement with different parameters in places of additions and repairs
- an interesting and useful in my opinion method of crack detection based on image analysis can be found in this article:
https://doi.org/10.1016/j.measurement.2021.110336 - section 4.2.
- the detection algorithm presented in this article may also prove useful:
Balasubramaniam, Kaleeswaran / Sikdar, Shirsendu / Ziaja, Dominika / Jurek, Michał / Soman, Rohan / Malinowski, Paweł
A global-local damage localization and quantification approach in composite structures using ultrasonic guided waves and active infrared thermography
2023-02 Smart Materials and Structures , Vol. 32, No. 3
Author Response
Dear Reviewer:
Thank you for carefully reading and reviewing the manuscript. Many of your opinions and suggestions are very constructive and innovative. I will answer them one by one, and the specific answers are in the Word document. Please refer to them.
Thank you, Have a nice day!
Author Response File: Author Response.docx
Reviewer 2 Report
Please see the attachment.
Comments for author File: Comments.pdf
Moderate editing of English language required
Author Response
Dear Reviewer:
Thank you for carefully reading and reviewing the manuscript. Many of your opinions and suggestions are very constructive and innovative. I will answer them one by one, and the specific answers are in the Word document. Please refer to them.
Thank you, Have a nice day!
Author Response File: Author Response.docx
Reviewer 3 Report
(1) Please carefully review the textual description in the abstract section. It seems that there are several numbers that might be line numbers. If they are not line numbers, please explain the significance of the numbers "4, 5, 6, 8, 9" appearing in the abstract section.
(2) The novelty of the study is not clearly apparent. In the introduction section, please emphasize the contributions of your work by contextualizing them with previous research in the same domain. Please highlight at least three key points
(3) The curve in Figure 2 should be represented by the red line, not the blue line mentioned in the article.
(4) What is the rationale behind choosing YOLOv5 for coarse localization?
(5) Briefly mentioning recent developments in the YOLO family of algorithms (such as YOLOv6, v7, and v8) would provide additional context for the study. For instance, Detection and counting of banana bunches by integrating deep learning and classic image-processing algorithms; Classical image processing and YOLOv7 fusion Algorithm is already proposed for rapid automatic Camellia oleifera fruit detection.
(6) Although the author claims to have made improvements to YOLOv5, there is no presentation of relevant data to demonstrate the effectiveness of these improvements or the advancement of the algorithm.
(7) The author may put some attention to the engineering applications based on the computer vision algorithms (Visual measurement of dam concrete cracks based on U-net and improved thinning algorithm; Journal of Experimental Mechanics. Novel visual crack width measurement based on backbone double-scale features for improved detection automation; Engineering Structures).
(8) Suggestion: Compare the experimental results of the improved algorithm with the original algorithm and other existing algorithms. It is recommended to present the results in graphical form.
(9) The study should mention potential areas for further research as well as the implications and practical applications of the findings.
(10) In the summary section, please provide a brief description of the experimental results obtained using the network presented in this paper.
(11) The proposed technological innovation in the article seems insufficient and appears to be limited to technical applications. Can the algorithm proposed by the author be applied to objects other than concrete cracks, such as road cracks?
Author Response
Dear Reviewer:
Thank you for carefully reading and reviewing the manuscript. Many of your opinions and suggestions are very constructive and innovative. I will answer them one by one, and the specific answers are in the Word document. Please refer to them.
Thank you, Have a nice day!
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
Dear Authors,
thank you for reading and responding to my comments. The submitted explanations dispel all my doubts. After introducing your corrections and presenting the explanations, I have no objection to recommending the publication of the manuscript in its current form.
Author Response
Thank you very much.
Have a nice day.
Reviewer 2 Report
My comments on the initial version of the manuscript have been sufficiently addressed by the authors in this revised version. I have no further comments on the technical aspects. The manuscript may be considered for publication after a proofreading.
Author Response
Thank you very much.
Have a nice day.
Reviewer 3 Report
Recommend for Acceptance. The authors are advised to perform a thorough formatting review, addressing issues such as the incorrect numbering of reference 49 and the absence of the journal name "Journal of Experimental Mechanics".
Author Response
Thank you for your careful review. I have changed the number 49 to 39 and added "Journal of Experimental Mechanics" to the citation in reference 39.
I have thoroughly reviewed the manuscript to ensure that no similar issues have occurred.