Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor
Alexander Ferworn
Round 1
Reviewer 1 Report
This is a solid paper that proposes a reasonable method for recognizing pallets in a warehouse. It is well-written and provides a way forward for those interested in this problem domain.
Author Response
Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor”.
We are very grateful for your positive comments on our research, and we will carefully refine the manuscript.
We have reviewed the full text and revised it for clarity. Any changes to the manuscript are marked with the "track changes" function, please check the manuscript for specific details of changes. These changes will not influence the content and framework of the paper.
Once again, thank you very much for your comments and suggestions.
Reviewer 2 Report
Please see the attached file
Comments for author File: 
Comments.pdf
Author Response
Dear Reviewer,
Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor”. Those comments are all valuable and very for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and had made correction which we meet with approval. We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper.
For the main corrections in the paper and responses to reviewers' comments, please see the attachment.
We appreciate for reviewers’ warm work earnestly, and hope that the corrections will meet with approval. If you have any question about this paper, please don’t hesitate to contact us.
Once again, thank you very much for your comments and suggestions.
Kind regards,
Dr. Zhao
Author Response File: Author Response.pdf
Reviewer 3 Report
1- The article needs some grammar checking
2- Refer to reference for equation 1
3- Figure 7 a, b, and c need to be more contrasted
4- You should verify your work with another previous work
5- The references 45, 47- 49 didn’t cite in the article
6- Put appendix for RGB-D Sensor specification
Author Response
Dear Reviewer,
Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor”. Those comments are all valuable and very for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and had made correction which we meet with approval. We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper.
-Response to reviewers’
- The article needs some grammar checking
Response: Thank you very much for your suggestions, we are sorry for our grammar errors on the manuscript, we’ve done a full review and revised it for more clarity and accuracy. Any changes to the manuscript are marked with the "track changes" function, please check the manuscript for specific details of changes.
- Refer to reference for equation 1
Response: We added a reference to Equation 1 in line number 205 of the manuscript.
- Figure 7 a, b, and c need to be more contrasted
Response: Figure 7 is replaced with a comparison diagram of the multi pallet recognition results with the yolov5 method. Please see the attachment and revised draft for details.
- You should verify your work with another previous work
Response: In the multi-pallet recognition experiment (Section3.2, a comparison experiment with yolov5 was added to measure the performance of the method in this paper compared with yolov5. Please see the attachment and revised draft for details.
- The references 45, 47- 49 didn’t cite in the article
Response: We cite reference 45 in line number 176, 47 in line number 261and 48,49 in line number 280 of the manuscript.
6.Put appendix for RGB-D Sensor specification
Response: We added sensor specifications to n line number 365-367 of the manuscript.
This is sensor specifications before the revision.
The sensor was a Kinect 2 (Microsoft, America)
This is sensor specifications after the revision.
The sensor was a Kinect 2 (Microsoft, America), which can obtain RGB images with a resolution of 1920 × 1080pixel and depth images with a resolution of 512 x 424. Kinect 2 detects the distance based on the time of flight, the depth detection range is 0.5-4.5m and detection accuracy is ± 4mm.The depth image size was 512 × 424. The pallet size was 1300 × 1300 × 150 mm.
We appreciate for reviewers’ warm work earnestly, and hope that the corrections will meet with approval. If you have any question about this paper, please don’t hesitate to contact us.
Once again, thank you very much for your comments and suggestions.
Kind regards,
Dr. Zhao
Author Response File: Author Response.pdf
Reviewer 4 Report
The authors proposed a real-time approach based on an improved label template matching algorithm with an RGB-D sensor to recognize and locate pallets in a warehouse environment. The work is interesting and the algorithm has the potential for implementation in an autonomous system. But the work has scope for improvement before it is recommended for publication by including more investigation of the algorithm from the computational point of view. Also, the authors suggested improving the structure of the manuscript significantly, e.g., the abstract should be rewritten without numbering or classification; the presentation of the work needs improvement in terms of the flow of the work and language correction; a lot of places (line number, 239,240, 246, 263,…) the representation of the nomenclature should be corrected; the sentence should be rechecked in line number 251. The authors are suggested to improve the presentation of the results by improving the quality of the plots and figures. Overall, the reviewer appreciates the efforts of the authors though the manuscript requires significant modifications before it can be recommended for publication.
Author Response
Dear Reviewer,
Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “Recognition and Location Algorithm for Pallets in Warehouses Using RGB-D Sensor”. Those comments are all valuable and very for revising and improving our paper, as well as the important guiding significance to our researches. We have studied comments carefully and had made correction which we meet with approval. We tried our best to improve the manuscript and made some changes in the manuscript. These changes will not influence the content and framework of the paper.
Kind regards,
Dr. Zhao
The main corrections in the paper and the responds to the reviewers’ comments are as follow:
-Response to reviewers
- Respond to the problems in the presentation of the article
Thank you very much for your suggestions, we are sorry for our language errors on the manuscript, we have reviewed the full text and revised it for clarity. Any changes to the manuscript are marked with the "track changes" function, please check the manuscript for specific details of changes.
- Response to the suggest about plots and figures question in the article
Thank you for your friendly suggestions, and we apologize for the low-resolution images that made reading them hard. We have replaced and improved the images in the manuscript to ensure that they are clearly visible and informative. Also included are the following revisions.
1) Adding a schematic diagram of the spatial relationship between the sensor and the pallet for explaining the mathematics of Equation 5.
2) Combining images and text to explain in more details the variables of Equation. (5)-(8)
3) Annotations for the variables have been added in Figures 4 and 5, and more detailed explanations of the variables are provided in the text to help understand the processing of the algorithm.
4）We have added labels and annotations in Figures 8 and 9 to make the information in the figures clearer.
Any changes to the manuscript are marked with the "track changes" function, please check the manuscript for specific details of changes.
- Response to the suggest about the structure of the manuscript
Thanks to your constructive comments, we have made significant changes to the text and figures in order to present the proposed algorithm more clarity. The revisions include: a more detailed description of the steps of the algorithm, and a comparison with the yolov5 algorithm. Please check the manuscript for specific details of changes.
In this study, proposed algorithm was adapted to situations with multiple pallets and with differently shaped pallets. A labeled template matching algorithm developed to achieve small-sample, low-computation pallet identification and localization in a semi-structured environment using the priori information.
Through the static and dynamic experiment, the correlation between the results of recognition errors of this paper's method and the algorithm parameters is measured, which provides an important reference for debugging the algorithm according to practical scenarios.
The simplicity of operation should enhance the flexibility of autonomous forklifts and expand the applicability of autonomous forklifts in complex environmental conditions.
We sincerely hope that you will review and comment on our articles again, thank you! If you have any question about this paper, please don’t hesitate to contact us.
Once again, thank you very much for your comments and suggestions.
Round 2
Reviewer 2 Report
Please see the attached file.
Comments for author File: Comments.pdf
Author Response
Dear Reviewer,
Thank you for your decision and constructive comments on my manuscript. We have carefully considered the suggestion of reviewer and make some changes. We have tried our best to improve and made some changes in the manuscript. These changes will not influence the content and framework of the paper.
For the main corrections in the paper and responses to reviewers' comments, please see the attachment.
We appreciate for reviewers’ warm work earnestly, and hope that the corrections will meet with approval. If you have any question about this paper, please don’t hesitate to contact us.
Once again, thank you very much for your comments and suggestions.
Kind regards,
Dr. Zhao
Author Response File: Author Response.pdf
Reviewer 3 Report
Author Response
Dear Reviewer,
We are very grateful to the reviewer for the approval of our revisions and positive comments on the article.
Once again, thank you very much for your comments and suggestions.
Kind regards,
Dr. Zhao
Reviewer 4 Report
The comments have been incorporated properly, hence, the modified manuscript can be acceptable for publication.
Author Response
Dear Reviewer,
We are very grateful to the reviewer for the approval of our revisions and positive comments on the article.
Once again, thank you very much for your comments and suggestions.
Kind regards,
