UAV-Assisted Wide Area Multi-Camera Space Alignment Based on Spatiotemporal Feature Map

Round 1

Reviewer 1 Report

Dear Authors,

The manuscript is clear, and well-written in most parts. The manuscript has sufficient originality, and undertaken problem is of practical nature. Although the results presented in the manuscript seem promising and overall approach is contributing in the body of the literature significantly, I encourage the authors to please consider the attached file suggestions to improvise the presented work more prior to its consideration. Thanks

Comments for author File: Comments.pdf

Author Response

Dear reviewer,
Thanks for your valuable comments and hard work, your advises are very helpful for our research. 
We have answered your comments one by one. All the revised parts are shown by blue font in the revision, and the details are located in the attachment.  
Thanks again for your kindly suggestion, and we do hope that the revision is acceptable.
Best regards.
Jing Li 
==================================================
Associate Professor, Ph.D. 
Intelligent Signal Processing and Pattern Recognition Laboratory
School of Telecommunications Engineering 
Xidian University 
Xi'an, 710071, China 
Email: [email protected] 
==================================================

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper presents a cross-view feature description algorithm (named as spatio-temporal feature map) to overcome the gap between assisted UAV and ground cameras. Also proposed a new traffic monitoring database collected in both simulation and real environment. The experiments demonstrate that the proposed spatio-temporal feature map is accurate and effective for cross-view matching. The manuscript is well organized and written well.

.

1. Page 12, what are the parameters are to generate data base from the simulation (AirSim)?. A table describing the parameters used in simulation and real scene environment will be helpful.
2. Equations (2), and (3) are confusing, when each row from the sampling time… and what this sentence means, “m n-dimensional row vectors r is converted…”. The appropriate references to the equations are needed.
3. The conclusion section needs to be improved with more details of findings, and future prospectives. 

Author Response

Dear reviewer,
Thanks for your valuable comments and hard work, your advises are very helpful for our research. 
We have answered your comments one by one. All the revised parts are shown by blue font in the revision, and the details are located in the attachment.  
Thanks again for your kindly suggestion, and we do hope that the revision is acceptable.
Best regards.
Jing Li 
===================================================
Associate Professor, Ph.D. 
Intelligent Signal Processing and Pattern Recognition Laboratory
School of Telecommunications Engineering 
Xidian University 
Xi'an, 710071, China 
Email: [email protected] 
===================================================

Author Response File: Author Response.pdf

Reviewer 3 Report

The topic of this work is interesting and in general it is well written and organized although some improvements could be done. The main reviewer concerns are summarized as follow,

 

• The reviewer would prefer that the contribution part be placed after the related work. This is easier to understand the contribution regarding the SoA.

 

• In the introduction is mentioned “This problem, in a sense, is similar to multi-stations cooperative wireless communication [x].” The reviewer suggest to add one reference regarding wireless multi BS cooperation, e.g. D. Castanheira, et al, “Set Optimization for Efficient Interference Alignment in Heterogeneous Networks,” IEEE Trans. on Wireless Communications, 2014.

 

• It is hard to follow Fig.2, since there are a lot of things. Please see if it is possible to improve it.

 

• The reviewer suggest to add a paragraph with the notation followed in the paper.

 

• The math formulation of section 3.2 is a little bit simple. Please see if it is possible to add some more details.

 

• Is it possible compare the results with other approaches proposed in the literature? This would enrich your work.

Author Response

Dear reviewer,
Thanks for your valuable comments and hard work, your advises are very helpful for our research. 
We have answered your comments one by one. All the revised parts are shown by blue font in the revision, and the details are located in the attachment.  
Thanks again for your kindly suggestion, and we do hope that the revision is acceptable.
Best regards.
Jing Li 
===================================================
Associate Professor, Ph.D. 
Intelligent Signal Processing and Pattern Recognition Laboratory
School of Telecommunications Engineering 
Xidian University 
Xi'an, 710071, China 
Email: [email protected] 
===================================================

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Dear Authors, the paper is well organized and clear now. My all concerns have been carefully addressed by the authors. In my opinion, the paper is ready for publication in the present form. I acknowledge and congratulate the authors for their significant efforts and time they spent on the thorough revision of the Manuscript. Excellent work!!!.

Reviewer 3 Report

The authors have satisfactory addressed most of the reviewer’s concerns. This new version is much more clear. Therefore the reviewer has no further comments.