Remote Sensing Image Retrieval Algorithm for Dense Data

Round 1

Reviewer 1 Report

This paper proposes a remote sensing image retrieval algorithm for dense data (DD-RSIRA). The algorithm establishes evaluation metrics based on factors like imaging time, cloud coverage, and image coverage. The algorithm utilizes a global discrete grid to create an ensemble coverage relation between images and grids. In this paper, it is shown that the method obtains a smaller number of datasets with lower redundancy and higher data utilization, and ensures the data quality to a certain extent, which can accurately meet the requirements of regional coverage of remote sensing images. The overall organization of the article is good, but the resolution of the images is low. Very meaningful inferences cannot be made from the pictures given in the conclusion section. How these parts are developed with the applied method can be supported with more noticeable images. It is thought that more comparisons given in Table 2 would be better in terms of recognizing the quality of the article.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

In this paper, the authors proposes a remote sensing image retrieval algorithm for dense data (DD-RSIRA) to deal with the problems of traditional remote sensing image retrieval methods. In general, the work in this paper is worthy publication. However, more revisions should be performed before acceptance.

1. The comprehensive cost is shown in Eq.(5). However, the weight coefficients are not determined. The reviewer wanders to know how to choose these weight coefficients. Is there a method? The authors should discuss this in detail in their paper, as this is very important for the comprehensive cost. In the following subsection, the authors should also clarify coefficients with the same problems in Eq. (9) and Eq. (13).

2. On page 9: The authors present the optimal regional coverage of remote sensing image in the table. The first step is the setting of optimal coverage. However, this step is not clearly discussed. Since this step is very important for the iteration method. The authors should clarify this in their paper.

3. In practice, there is also underwater remote sensing image like the synthetic aperture sonar image [1][2]. The reviewer wanders to know whether the authors’ method can be used by the underwater remote sensing image. The authors should discuss this in their paper. This discussion would be helpful for readers.

[1]Yang, P., An imaging algorithm for high-resolution imaging sonar system, Multimedia Tools and Applications, 2023, Doi: 10.1007/s11042-023-16757-0

[2]X. Zhang, et al．Multireceiver SAS imagery based on monostatic conversion．IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2021，Doi: 10.1109/JSTARS.2021.3121405．

4. In Fig. 4, the authors present the flowchart of the DD-RSIRA algorithm. In the last step, the authors refer the termination conditions. The reviewer wanders to know what the termination conditions are. The authors should present this in their paper. Besides, all steps in this figure should be described in their paper. Furthermore, the authors should present the results corresponding to each step in the experimental section. With this operation, the results would be much more convincing.

5. The major difference between the authors’ method can traditional method should be further highlighted.

6. The English in this paper should be improved.

Further improvement is required.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

The proposed DD-RSIRA algorithm is a promising solution to the challenges faced by traditional remote sensing image retrieval methods. By establishing evaluation metrics based on imaging time, cloud coverage, and image coverage, the algorithm can effectively filter out irrelevant data and improve the efficiency of data retrieval. The use of a global discrete grid and a locally optimal initial solution obtained by a greedy algorithm further enhances the accuracy and effectiveness of the retrieval process.

Overall, the proposed DD-RSIRA algorithm has great potential for application in various fields such as environmental monitoring, urban planning, disaster management, and agriculture.

However, there are still some minor issues.

1.Why can your paper achieve better results than others by using the greedy algorithm? What is its principle? It is suggested to supplement a review on the greedy algorithm in section Introduction.

2. Table 1 should be modified to be more beautiful, with capital letters, units and spaces after the numbers.

3. It is recommended to add a large map of China Figure 1 to Figure 3

4. Figure 4 is suggested to increase readability, especially “Select the suboptimal subset with probability p, otherwise select the best subset.

5. "Significant" in line 492 requires a p value.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

The paper is improved