All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
I confirm that the authors have addressed all of the reviewers’ comments. As the previous reviewers were not invited to evaluate this revision, I have assessed the revised manuscript myself and am satisfied with the changes made. In my opinion, the current version meets the required standards, and the manuscript is ready for publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Mehmet Cunkas, a PeerJ Section Editor covering this Section #]
After careful consideration and revisions based on the reviewers’ comments, we confirm that all requested changes have been satisfactorily addressed. However, the manuscript would benefit from a more consistent use of voice throughout the text. Specifically, the alternation between passive and active constructions leads to an imbalance in tone and style. Establishing a uniform narrative voice—preferably aligned with standard academic conventions—would enhance clarity and coherence.
Additionally, certain paragraphs, particularly within the Method and Discussion sections, are overly lengthy and complex. The sentence structures in these sections should be revised for conciseness and readability. Simplifying the language without compromising scientific precision would greatly improve the manuscript’s accessibility.
A comprehensive revision is recommended to ensure the text adheres to a more natural, fluent, and academically appropriate style.
**Language Note:** The Academic Editor has identified that the English language must be improved. PeerJ can provide language editing services - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Alternatively, you should make your own arrangements to improve the language quality and provide details in your response letter. – PeerJ Staff
Everythingwas organized well.
Everythingwas organized well.
Everythingwas organized well.
Everythingwas organized well.
All major reviewer concerns appear to have been resolved. The remaining suggestions are minor and should be straightforward for the authors to implement. These involve clarity, completeness, and literature enrichment rather than technical rework.
no comment
no comment
no comment
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.
The respected authors have addressed all of the suggested comments correctly. However, there are some simple points that I mentioned them. Please kidnly try to modify the article according to the new series of the comments.
In the section of "Experimental Design" everything is organized well.
To prove the "Validity of the Fundings", it is much better to add a new section entiteld "Post-processing Steps".
It is better to add some newly articles (2019-2025) which implemented by applying robust algorithms. Please kindly enrich the comparison part!
Thank you for submitting your manuscript titled “Pavement defect detection algorithm SSC-YOLO for fusing multiscale spatial channels in YOLOv8". After careful evaluation, we have decided to request major revisions before further consideration. While the paper makes notable contributions through the SSC-YOLO algorithm for pavement defect detection, several key areas require improvement. The Introduction needs a more detailed discussion of existing methods' limitations and how SSC-YOLO addresses them. The methodology section is overly complex, particularly the descriptions of YOLOv8, SSD, MUP, and MFConv, which need simplification and clearer justification for the parameter-sharing detection head. The experimental design requires further detail on dataset preparation, partitioning, and validation, along with a critical analysis of performance comparisons and challenges in defect detection. Additionally, figures and tables should be improved for better clarity and readability. The conclusion needs to effectively summarize the contributions, discuss limitations, and outline future research directions. Reviewer 2 has also requested more detail on preprocessing, dataset preparation, and hyperparameters to ensure reproducibility. We look forward to reviewing your revised manuscript and thank you for your effort to improve its quality.
This paper introduces SSC-YOLO, an improved YOLOv8-based algorithm for pavement defect detection that integrates multiscale spatial channels. The proposed modifications include SSD, MUP, and a MFConv, along with a parameter-sharing detection head to improve both efficiency and accuracy. While the contributions are notable, the paper still requires significant revisions to enhance its clarity, completeness, and presentation quality.
1) Introduction and Background:
a) While the Introduction adequately highlights the importance of pavement defect detection, it lacks a deeper discussion of existing methods’ limitations and how SSC-YOLO addresses these shortcomings.
b) The literature review is comprehensive but overly technical and could benefit from a more concise narrative connecting the prior work to the proposed method.
c) There are some papers about the applications of improved YOLO models should be discussed.
2) Methodology:
a) YOLOv8 Overview: The description of YOLOv8’s structure is unnecessarily detailed and deviates from the focus of the study. Summarize this section while retaining only relevant information for context.
b) Proposed Modifications: The explanations of SSD, MUP, and MFConv are comprehensive but overly verbose and complex. Simplify the mathematical notations and diagrams to improve accessibility to a broader audience.
c) Include a clear comparison between the original YOLOv8 components and the proposed SSC-YOLO modifications.
d) Parameter-Sharing Detection Head: More justification is needed for why this strategy is effective in reducing computation costs while preserving accuracy.
3) Experiments and Results:
a) Experimental Design: Provide more details on dataset partitioning (e.g., training-validation-test split) and whether cross-validation was performed.
b) Comparative Results: While the paper shows performance comparisons with mainstream models, the discussion lacks critical analysis. Explicitly explain why SSC-YOLO outperforms or underperforms in specific metrics (e.g., AR, AP50, small object detection).
c) Highlight challenges in detecting small and medium defects and discuss why SSC-YOLO performs better or worse in certain scenarios.
d) Ablation Studies: The results of ablation experiments are promising, but the discussion needs to emphasize the specific contributions of SSD, MUP, and MFConv to the overall performance gain.
4) Figures and Tables:
a) Image Quality: The quality of diagrams and tables (e.g., Figures 3–6) is too low, making it difficult to interpret critical details. All figures need to be replaced with high-resolution versions.
b) Ensure the text in all images is legible, and colors are used effectively to distinguish components.
c) Table formatting needs improvement for readability (e.g., alignment of numerical values and column headers).
5) Conclusion and Future Work:
a) The conclusion is too brief and does not effectively summarize the key contributions and findings of the paper.
b) Discuss the limitations of SSC-YOLO, such as performance in real-world settings with varying lighting and noise conditions.
c) Provide a more robust outline of future research directions, including potential improvements and real-world deployment challenges.
In the General section, everything is organized well.
A. Please provide a detailed description of the pre-processing steps, accompanied by a
diagram illustrating the process.
B. Please describe how you prepared the dataset, including the methods used for splitting
the data into training, test, and validation sets. If random sampling was employed, specify
whether techniques like K-Fold or Monte Carlo cross-validation were utilized to enhance the
reliability of the results.
C. The interconnections between elements within the proposed model are unclear. Please provide a detailed explanation of how these elements connect and interact.
D. To enhance clarity, please provide a comprehensive table summarizing the elements employed in the model implementation, along with their characteristics and functionalities.
E. Highlight the specific optimizations or improvements introduced in this iteration of the model compared to previous versions.
F. A detailed description of the hyperparameters used in the proposed model is crucial for reproducibility. Elaborate on the chosen hyperparameter values, including any experimental settings or tuning methodologies employed.
The work seems interesting and the technical contributions are solid. I believe this paper shows great potential, and with some “Minor” revisions and addressing the comments, it will be ready for publication. I am eagerly looking forward to reviewing the revised paper. However, I hope that the findings of this paper will be useful for the audience of this journal and the investigated region.
Good Luck!
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.