Dim Moving Multi-Target Enhancement with Strong Robustness for False Enhancement
Round 1
Reviewer 1 Report (Previous Reviewer 5)
The authors have answered my questions after three rounds of iteration and modification. The quality of the paper has been greatly improved, and it is now acceptable for publication.
Author Response
Thank you for your approval..
Reviewer 2 Report (New Reviewer)
In this paper, an enhancement method for dim moving multi-target for false enhancement is proposed to solve the circumstance of multi-target and low signal-to-noise ratio. Overall, the paper is well-organized, soundness and the experimental part is well presented. I have the following concerns.
1. A moderate editing of English language is required as it contains a considerable number of faulty formulations and improper sentences.
2. About blind pixels: which category they belong to, background or noise? The authors should clearly explain this in the text.
3. The resolution of figures is rather low and the 3-D displays are very difficult to acquire detailed information, the authors need to adjust the size and contrast to clearly present the results.
A moderate editing of English language is required as it contains a considerable number of faulty formulations and improper sentences.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.
Round 1
Reviewer 1 Report
1、 The step of removing blind pixels in the manuscript has the problem of removing targets. How does the author solve this problem?
2、 The proposed method requires determining the position of the targets firstly. Then enhancing the target and suppressing the background. After determining the location of the targets, is it still necessary to perform targets enhancement?
3、 The author used their own simulated dataset to verify the effectiveness of the algorithm. However, the dataset was too small, with only 5 sequences and only 50 images per sequence. The experimental results were not convincing.
4、 The manuscript mentioned the trajectory of the targets, but it did not clearly introduce the calculation of the target trajectory.
5、 Formula (4) has errors.
1. There are too many long sentences in the manuscript , so I recommend to improve English writing.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 2 Report
1. In line 18, 'multi targets' should be 'multi-target' or 'multiple targets'
2. Some important references are missing, e.g., Y. Li, P. Wei, L. Gao, W. Sun, H. Zhang and G. Li, "Micro-Doppler Aided Track-Before-Detect for UAV Detection," IGARSS 2019 - 2019 IEEE International Geoscience and Remote Sensing Symposium, Yokohama, Japan, 2019, pp. 9086-9089
3. The legend is best placed on the same page as the content for the Fig. 11.
4. In line 201, the explanation of symbol $\delta$ is missing.
5. How to select the best values of $\delta$ and $\tau$?
The paper is well-written.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 3 Report
The paper proposes a target-enhancement method for space-based background, which is an interesting and promising research topic. However, before acceptance, I have the following questions that need to be addressed:
-
In dim object detection, distinguishing between noise and objects is challenging. How did the authors handle this issue? Please provide a detailed explanation.
-
The authors used 3D convolution for object detection. How did they determine the kernel size for practical applications? Please clarify this.
-
The paper focuses on dim object detection, but recent hyperspectral object detection and tracking papers have shown that extra spectral information can be beneficial for discrimination. For example, in doi: 10.1109/TIP.2020.2965302 and doi: 10.1109/JSTARS.2022.3205211. It is suggested that the authors discuss the potential benefits of incorporating spectral information in their method
Minor revision required.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 4 Report
Abstract：
1. The problems to be solved are not clear. The kinds of states and ability should be also clarified.
2. ‘Then’ should be ‘Then,’
Introduction:
3. Fig.1 should not appear in the introduction. You may state the problem is experimental part.
4. Line 106, wrong use of indentation.
5. Period is missed in each caption of image.
6. The present tense should be used instead of the past tense.
7. How does the window size and image resolution influence the detection performance.
Experiments:
8. The number of frames should be increased to compare precision and other metrics.
9. The impact of image resolution should be analyzed in experiments.
The are some typos and odd presentations that should be corrected. We suggest authors improve the English expression.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Reviewer 5 Report
This paper proposes a new enhancement method for dim moving multi-target with strong robustness for false enhancement to solve the problem of the low signal-to-noise ratio (SNR) and unknown states of multi targets. The innovation of this work is suggested to figure out further. The following issues need to be improved：
(1) What is the SNR value in Figure.3? It should be addressed in this paper.
(2) How does the defocusing phenomenon caused by the moving platform be solved for the space-borne infrared system？
(3) The relative movement between the space platform and the moving target may cause infrared image defocusing phenomenon, how does this relative movement be compensated?
(4) If there are multiple targets clustered together in the scene, does this proposed method perform well?
(5) In line 147, what does 1/F noise mean? Please check.
(6) In line 183, it is said that the value is equal to 0.65. How does the value be set?
(7) This simulation is too simple. Real data experiments are suggested to be added in this paper.
(8) The author's name in the References should be consistent and conform to the journal style.
Comments for author File: 
Comments.pdf
The author's name in the References should be consistent and conform to the journal style.
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 4 Report
Authors have answered my problems and the paper now can be accepted.
Author Response
Thank you for your approval.
Reviewer 5 Report
The authors have answered most of the questions. However, some response are still need to be revised before publication. The following issues need to be improved：
(1) The relative movement between the space platform and the moving target will cause infrared image defocusing phenomenon. This is an objective and practical problem to be faced in this paper. Some relevant preprocessing methods are suggested to be supplemented in this paper.
(2) If there are multiple targets clustered together in the scene, this proposed method may perform not well. The limitations of the algorithm in this paper should be pointed out in order to facilitate further research by subsequent scholars.
(3) This simulation is too simple. Real data experiments are suggested to be added in this paper
-
Author Response
Please see the attachment.
Author Response File: Author Response.docx
