A Sector-Matching Probability Hypothesis Density Filter for Radar Multiple Target Tracking

Round 1

Reviewer 1 Report

The work is well presented. Following things should be improved. 1. Significance of figures should be explained. Only mentioned like 'these are shown in figure x' like that is not enough. 

2. I find some conflicting results in computation time vs time because it should be generally increasing but in some case it is varying quite randomly. why? It should be explained properly.

3. References should be uniformly presented.

Author Response

The co-authors and I would like to thank you for the time and effort spent in reviewing the manuscript. We have corrected some typos/grammatical errors throughout and revised the manuscript according to the reviewer's suggestion. Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

This paper deals with an interesting practical issue in tracking: the mismatch between the measurement time and the prediction time. The topic of the paper is good, and the presentation is generally understandable despite having a number of typos/grammar errors. However, there are several concerns should be addressed:

1. The paper is based on the PHD filters, which is recently less attractive since the pmbm and other methods have outperformed them. Why didn't you consider constructing your method based on, e.g., trajectory pmb trackers cited in [23]? 

2. The literature review is unbalanced since it missed many state-of-the-art trajectory formation and fast data association methods, including but not limited to the following literature:

1. Meyer, F., Thomas K., Jason L. Williams, Roslyn Lau, Franz Hlawatsch, Paolo Braca, and Moe Z. Win. "Message passing algorithms for scalable multitarget tracking." Proceedings of the IEEE 106, no. 2 (2018): 221-259.

2. Gan, R., Q. Li, and S. Godsill. "A Variational Bayes Association-based Multi-object Tracker under the Non-homogeneous Poisson Measurement Process." In 2022 25th International Conference on Information Fusion (FUSION), pp. 1-8. IEEE, 2022.

3. Khan, Zia, Tucker Balch, and Frank Dellaert. "MCMC data association and sparse factorization updating for real time multitarget tracking with merged and multiple measurements." IEEE transactions on pattern analysis and machine intelligence 28, no. 12 (2006): 1960-1972.

4 .Davey, Samuel J., Giuseppe A. Fabrizio, and Mark G. Rutten. "Detection and tracking of multipath targets in over-the-horizon radar." IEEE Transactions on Aerospace and Electronic Systems 55, no. 5 (2018): 2277-2295.

5. Streit, Roy, Christoph Degen, and Wolfgang Koch. "The pointillist family of multitarget tracking filters." arXiv preprint arXiv:1505.08000 (2015).

3.  From the results, the proposed method seems much less accurate than glmb filter regarding ospa. Could you justify this comparison result? Have you compared with the T-PMB filter, since it may be even better than GLMB generally.

 

 

 

 

Author Response

The co-authors and I would like to thank you for the time and effort spent in reviewing the manuscript. We have corrected some typos/grammatical errors throughout and revised the manuscript according to the reviewer's suggestion. Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

This paper presents the computationally efficient sector-matching PHD filter for multiple target tracking. The overall composition of the manuscript is good and the contribution is clear. However, when performing simulations to compare the performance of the proposed algorithm, parameters for performance evaluation and various scenarios should be added.

Author Response

The co-authors and I would like to thank you for the time and effort spent in reviewing the manuscript. We have corrected some typos/grammatical errors throughout and revised the manuscript according to the reviewer's suggestion. Please see the attachment.

Author Response File: Author Response.docx