Depth Estimation from a Hierarchical Baseline Stereo with a Developed Light Field Camera
Round 1
Reviewer 1 Report
Comments and Suggestions for Authors
Please proofread the English language in the paper.
Abstract
Please re-write the abstract to consider the next points:
The word “treating” is general, please replace it by more specific word.
Please avoid using (I, we, our and us), use the passive voice. Please check the paper.
Please quantify the result accuracy.
Please detail more the suggested approach
Introduction
Recoving depth information for real-world scenes and objects are desirable for many applicationsè please provide some examples.
“multi-view stereo (MVS)” should be written “Multi-View Stereo (MVS)” Please check all abbreviations in the paper.
Please cite references about lidar such as:
Gharineiat, Z., Tarsha Kurdi, F., Campbell, G. 2022. Review of automatic processing of topography and surface feature identification LiDAR data using machine learning techniques. Remote Sens. 2022, 14 (19), 4685, https://doi.org/10.3390/rs14194685.
Solares-Canal, A., Alonso, L., Picos, J. et al. Automatic tree detection and attribute characterization using portable terrestrial lidar. Trees 37, 963–979 (2023). https://doi.org/10.1007/s00468-023-02399-0
Line 42: please replace “traditional” with “rule-based”.
Please define all used abbreviations, e.g., DSLR, please check all used abbreviations in the paper.
Please explain the goal of the camera system and the difference between it and traditional one, applications and advantages.
The Proposed Approach
Please add detailed flowchart the explain the input, output, and step by step the suggested approach.
Figure 1:
please define all parameters presented in Figure 1b.
please add numbers for each picture in Figure 1d and describe them in the caption.
In Figure 1b, some parameters are determined clearly using arrows such as Z, a, and b. Others or not clear because you didn’t use arrows such as f, d, and A, you can zoom Figure 1b and determine all parameters clearly.
Figure 2 should be after its citation not before (please check all figures and tables).
What is “k-ring neighboring macro-pixels”?
Please define the “specific local features”.
Equation I is not cited.
Please cite a reference for the used gradian filter.
Vmp is the feature vector?
Why figure 2a does consist of two images?
If you develop any equation, please explain how you develop it, if not, please add reference(s) (please check all equations in the paper).
Please explain how do you determine all used threshold values such as Ɛ
Please check all parameters used in equations, all should be defined after the equation directly.
Please add figures to show the result of application of each procedure.
Section 3 and subsection 3.2 have the same title (should be fixed). Moreover, Subsection 3.1 are not harmonise with Section 3. I think that Subsection 3.1 should be an independent section.
I am not sure if Figure 3 is necessary.
In Table 1, please explain under the table what do you mean by “-“ and “
”.
Replace the title of the last section by “Conclusion”. Then, extend this section to discuss the limitations of the suggested approach.
Comments on the Quality of English Language
Extensive editing of the English language required.
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for Authors
The article describes a baselines stereo matching method using a light field camera.
The method is based on hierarchical refinement from macro-pixel-wise coarse matching to pixel-wise fine matching.
I doubt the novelty of the suggested method about the following argues.
1.
The first contribution of the proposed method is stated as :
A macro-pixel map is built by treating each micro-lens as one macro-pixel.
It is arguable that it will extremely reduces the resolution of the output depth map, which will be the critical disadvantage of this method.
2.
The second and third contributions of the proposed method are stated as : Both coarse and fine matching are performed through WTA with ZNCC. Hierarchical baselines stereo matching is applied.
The matching approach using WTA with ZNCC is widespread and not novel. Also the hierarchical matching is commonly used.
The authors should survey find several most similar previous works and describe distinct differences between them.
Also, quantitive comparison from experimental results should be provided.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for Authors
[Major Comments]
l This manuscript appears to express interest in the subject matter. However, the authors fall short in providing objective research results, leading to a lack of precision in detailing the level of enhancement achieved. The reliance on images may present a subjective interpretation, as opinions on the level of detail improvement can vary. Objective research facts are crucially needed to address this limitation.
l The paper's structure does not conform to scholarly standards; it is recommended that the authors refer to other journal papers published in Applied Sciences for guidance.
l The assertion that the authors developed an enhanced capturing system is questionable, as the modifications made merely involve changing the interface from Camlink to USB 3.0, based on the commercial product Raytrix R29. This study lacks novelty.
l The discussion section is inadequate, lacking the depth expected of scholarly discourse. It reads more like a series of concluding statements rather than offering insightful discussions.
l A formal conclusion is necessary to provide a comprehensive summary.
l The literature review is incomplete. The authors need to provide clear research gaps between the existing studies and this paper.
l Abstract is weak.
Please, re-write an abstract based on the following questions.
1. What is the general domain/problem covered in the paper?
2. What is the specific research question addressed?
3. What means and methods were used to answer this question?
4. What is the answer?
5. Why is this answer important and for whom?
6. How does the answer inspire future research and development?
[Minor Comments]
l Line 15: Define TOF.
l Line 15: Use lowercase for expressing "laser scanner."
l Lines 14-17: Include a reference for support.
l Lines 34-36: Cite relevant references.
l Line 59: Avoid using "we" in the context of a journal paper for increased objectivity.
Comments on the Quality of English Language
English should be improved.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
Comments and Suggestions for Authors
The paper looks so much better. I think that it is ready to be published.
Comments on the Quality of English Language
Minor editing of the English language is required.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 2 Report
Comments and Suggestions for Authors
The manuscript has been moderately revised according to the reviewer's suggestions and comments.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
Comments and Suggestions for Authors
Thank you for your hard work.
It looks now okay to publish it.
Comments on the Quality of English Language
Just in case, please check English.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
