An Adaptive Pose Fusion Method for Indoor Map Construction

Round 1

Reviewer 1 Report

the contribution is minor, and it should be summarized in the introduction. 

Author Response

Dear reviewer:

Thank you very much for your time involved in reviewing the manuscript and your very encouraging comments on the merits. We have carefully checked and improved the English writing in the revised manuscript. I use blue font to mark the major revisions in the manuscript.

 

The paper mainly revised the following aspects:

1. Invited EditSprings to polish this paper again.
2. Modified all graphics in this paper.
3. Re-written "5.3 Map Construcion Analysis" of this manuscript.
4. Re-written the Astract of this manuscript.
5. Re-written the Cntribution of this manuscript.
6. According to the level of " Adaptive ", the title of this manuscript was revised to "An Adaptive Pose Fusion Method for Indoor Map Construction".

 

We also appreciate your clear and detailed feedback and hope that the explanation has fully addressed all of your concerns. In the remainder of this letter, we discuss each of your comments individually along with our corresponding responses.

 

To facilitate this discussion, we first retype your comments in italic font and then present our responses to the comments.

 

Thank you and best regards!

 

Yours sincerely, Jinming Zhang

Corresponding Dr. Jinming Zhang, E-mail: [email protected]

Author Response File: Author Response.pdf

Reviewer 2 Report

Dear Authors,

Please find the attached file for my comments. Please update the paper based on the comments and resubmit it. 

Best Regards 

Comments for author File: Comments.docx

Author Response

Dear reviewer:

Thank you very much for your time involved in reviewing the manuscript and your very encouraging comments on the merits. We have carefully checked and improved the English writing in the revised manuscript. I use blue font to mark the major revisions in the manuscript.

 

The paper mainly revised the following aspects:

1. Invited EditSprings to polish this paper again.
2. Modified all graphics in this paper.
3. Re-written "5.3 Map Construcion Analysis" of this manuscript.
4. Re-written the Astract of this manuscript.
5. Re-written the Cntribution of this manuscript.
6. According to the level of " Adaptive ", the title of this manuscript was revised to "An Adaptive Pose Fusion Method for Indoor Map Construction".

 

We also appreciate your clear and detailed feedback and hope that the explanation has fully addressed all of your concerns. In the remainder of this letter, we discuss each of your comments individually along with our corresponding responses.

 

To facilitate this discussion, we first retype your comments in italic font and then present our responses to the comments.

 

Thank you and best regards!

 

Yours sincerely, Jinming Zhang

Corresponding Dr. Jinming Zhang, E-mail: [email protected]

Author Response File: Author Response.pdf

Reviewer 3 Report

The vision-based robot pose estimation and mapping system have problems with the accuracy of pose estimation. The paper presents and examines a solution that tries to address these problems. The authors propose an adaptive weighted fusion method to fuse the robot's pose and use the optimized pose to construct an indoor map. This topic corresponds with a journal scope and is acceptable for publication in ISPRS International Journal of Geo-Information.

The authors put much effort into creating this paper, and the results can be important for many disciplines. However, the overall presentation requires further work to improve the clarity of the text.

Abstract – In my opinion, the current form is too detailed. Please consider rewriting this part of the article and shortening it.

The introduction should be verified. In this section, the authors claim to analyze "how to use the Extended Kalman Filter (EKF) and the Adaptive Weighted Fusion (AWF) to further improve the fusion pose accuracy of KINECT/IMU" (rows 77-78). However, in the next section, they write about the EKF and WFS method (row 82 - "The EKF method or the WFS method is adaptively selected"). The WFS method is also mentioned in section 4.3 Experimental Steps ("For the WFS method, the key is to determine the proportion of KINECT pose and IMU pose"). Could the authors comment on the reason for these differences?

Section two - "2. Related Work" is too basic and presents only general information on the presented topic. There is only a small discussion about similar, up-to-date research utilizing a fusion of visual, lidar, and inertial data to improve positioning accuracy. To date, many articles have been published on the following topics. I would recommend adding this information.

Additionally, this section lacks a description of the algorithms used in the following sections to compare pose estimation accuracy (ROVIO) and 2D mapping based on laser scanning (the Cartographer algorithm). The authors also should mention why ROVIO is a comparison method instead of another currently used visual-inertial information fusion system.

The experiment parts lack information on the technical implementation of the proposed solution. In section 4.1 ("Experimental Platform"), there are no details concerning hardware used in the experiment and specifications of computing resources. Presented results strongly depend on the performance of the components, so the authors should add into this section the parameters of the devices used to perform the tests.

The description of experimental steps is sometimes too short or incomprehensible (section 4.3 – "Experimental Steps"). This part of the manuscript should be corrected and significantly improved. In my opinion, the new figure (flow chart), which organizes and prioritizes the described steps, methods, and data, should also be considered.

In section "6. Conclusions", the authors present the experiment results. They are based on the methodology that has been proposed in the article. There is no reference to the results obtained by other authors with similar approaches. Could the authors explain this issue? Please, consider adding a comparison with results from other authors.

Some specific comments, including the addition and modification of figures and table, are listed below.

• All abbreviations should be defined the first time they appear in the text. Some abbreviations are not explained.
• English needs to be carefully checked and polished.

As for figures:

• Figure 1. The font size of the text on the figures is too small. Please increase the font size.
• Figure 2. The photo is too dark, so objects cannot be seen. The x-/y- axes labels are too small and cannot be read.
• Figure 3. The photo needs labels with sensor descriptions.
• Figure 4. The figure is too small. The photo is low quality and dark. The schematic diagram is unreadable.
• Figure 5. The colored dots and lines are illegible. Their colors are too similar to distinguish from the background. Please change the symbolization style to make the image readable.
• Figures 6, 7, 8, 9, 10 - The plots are illegible. The font size of the x-/y- axes labels and text on the figures is too small. Please increase the font size.
• Figures 12, 13. The images are of poor quality. Please consider showing next to the highlighted areas an enlarged version of these elements. The caption of figure 13 is missing a description of a and b.

Author Response

Dear reviewer:

Thank you very much for your time involved in reviewing the manuscript and your very encouraging comments on the merits. We have carefully checked and improved the English writing in the revised manuscript. I use blue font to mark the major revisions in the manuscript.

 

The paper mainly revised the following aspects:

1. Invited EditSprings to polish this paper again.
2. Modified all graphics in this paper.
3. Re-written "5.3 Map Construcion Analysis" of this manuscript.
4. Re-written the Astract of this manuscript.
5. Re-written the Cntribution of this manuscript.
6. According to the level of " Adaptive ", the title of this manuscript was revised to "An Adaptive Pose Fusion Method for Indoor Map Construction".

 

We also appreciate your clear and detailed feedback and hope that the explanation has fully addressed all of your concerns. In the remainder of this letter, we discuss each of your comments individually along with our corresponding responses.

 

To facilitate this discussion, we first retype your comments in italic font and then present our responses to the comments.

 

Thank you and best regards!

 

Yours sincerely, Jinming Zhang

Corresponding Dr. Jinming Zhang, E-mail: [email protected]

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

I recommend acception. 

Reviewer 2 Report

Dear Authors, 

Thank you for addressing all my comments and I don't have any further comments about the paper. The paper is accepted from my side. 

Best Regards

 

Reviewer 3 Report

The authors addressed all comments and suggestions from my review.