Next Article in Journal
Transfer of Orbital Angular Momentum of Light Using Autler-Townes Splitting
Previous Article in Journal
Circulating Tumor Cell Models Mimicking Metastasizing Cells In Vitro: Discrimination of Colorectal Cancer Cells and White Blood Cells Using Digital Holographic Cytometry
 
 
Article
Peer-Review Record

An Unknown Hidden Target Localization Method Based on Data Decoupling in Complex Scattering Media

Photonics 2022, 9(12), 956; https://doi.org/10.3390/photonics9120956
by Chen Wang 1,†, Jiayan Zhuang 2,†, Sichao Ye 2,*, Wei Liu 3, Yaoyao Yuan 4, Hongman Zhang 4 and Jiangjian Xiao 2
Reviewer 1: Anonymous
Reviewer 2:
Reviewer 3: Anonymous
Photonics 2022, 9(12), 956; https://doi.org/10.3390/photonics9120956
Submission received: 7 November 2022 / Revised: 24 November 2022 / Accepted: 25 November 2022 / Published: 9 December 2022

Round 1

Reviewer 1 Report

The authors designed a target localization network incorporating an attention mechanism to estimate the positions of targets in speckle images. Their method was demonstrated with an optical experiment. The theory is solid, and well supported by the experimental results. The paper was well written. I suggest the publication of this manuscript with some minor revisions.

The authors claimed that earlier works required a large number of datasets. It would be better to give an explicit comparison between this work and earlier works by showing the relevant numbers in a table.

The objects in this work were black and white, while gray-scale objects are closer to reality. Could the authors discuss the performance of their method for gray-scale objects? How would the accuracy change? Do they need more training datasets?

Should the integration variable in Eq. 6 be x_i?

Correct the grammar in line 80.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors proposed a deep learning based method to precisely locate complex targets in scattered environments. Experiments were conducted to verify the accuracy of the proposed method. The article has sufficient novelty and can be accepted for publication. However, the authors should address the following queries:

1.     The authors can add more information about the training process such as training epochs, training loss and testing loss.

2.     The authors should proofread the article as there are a few typographical errors.

 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

In this manuscript, the authors designed a single-stage target localization network based on the robust feature-resolution capability of neural networks by incorporating global attention mechanisms. In my opinion, this manuscript is interesting to the readers of Photonics. The topic is very important in this field. This work is novel and original. The authors have solid background in this field. Therefore, the referee recommends it to be directly accepted for publication.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop