Pedestrian Detection and Tracking System Based on Deep-SORT, YOLOv5, and New Data Association Metrics

Round 1

Reviewer 1 Report

The authors propose a pedestrian Detection and tracking System based on Deep-SORT, YOLO v5. The paper is interesting. In general, the main conclusions presented in the paper are supported by the figures and supporting text. However, to meet the journal quality standards, the following comments need to be addressed.

1.         Abstract: Should be improved and extended. The authors talk lot about the problem formulation, but novelty of the proposed model is missing. Also provided the general applicability of their model. Please be specific what are the main quantitative results to attract general audiences.

2.         The introduction can be improved. The authors should focus on extending the novelty of the current study. Emphasize should be given in improvement of the  model (in quantitative  sense)  compared to   existing  state-of-the art models.

3.         More details about network architecture and complexity of the model should be provided.

4.         what about comparison of the result with current state-of-the art models?  Did authors perform ablation study to compare with different models?

5.         What are the baseline models and benchmark results? The authors can compared the result with existing models evaluated with datasets

6.         Conclusion parts needs to be strengthened.

7.         Please provide a fair weakness and limitation of the model, and how it can be improved.

8.         Typographical errors: There are several minor grammatical errors and incorrect sentence structures. Please run this through a spell checker.

9.         Following relevant references should be added for relevant YOLO  works    see

-Neural  Comput & Applic (2022)  https://doi.org/10.1007/s00521-021-06651-x;  

- Eco Informatic 2022 https://doi.org/10.1016/j.ecoinf.2022.101919. 

Hence they should be briefly discussed in the related work section.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

Please consider the following remarks:

1) At abstract section put a few numerical results veryfing the proposed approach.

2) At section 1 please compare the proposed approach with published literature. Clearly mention why the proposed approach is better.

3) Literature review on the area is poor, it should be more detailed.

4) At section 2 heading what is the meaning of "materials"?

5) Please put references at sections 2.1 and 2.2.

6) What is the difference between Tables 1 and 2?

7) At section 3 please put references wherever needed. 

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 3 Report

Please revise the paper as per the following comments:

1.    Abstract: The abstract of the paper needs to be rewritten. It has to reflect the research problem, methods, key quantitative research findings, and contributions in a brief way. Currently, the abstract appears like the organization summary of the paper.

        25% on the purpose and importance of the research (Introduction)

          25% on what you did (Methods)

          35% on what you found (Results)

          15% on the implications of the research

2. Related Work is missing: Insufficient references to existing research literature. I believe the authors did not do a thorough literature study, which makes it difficult to evaluate the topic's novelty. The literature review is lacking, in some of the recent studies.

3.    To improve the background study shows an Overview of the object tracking SORT and  Deep-SORT flowchart/algorithm which are missing.

4.    Which metrics are used by authors to evaluate the tracker’s overall strengths and judge its general performance?

5.    A study of the computational complexity of the suggested method is required. Use a plot to show the computational complexity of the proposed model with State-of-art models.

6.    Please provide some comments on the novelty of the proposed methodology. How is it different from other methodologies? How is it more efficient than those networks?

7.    Add more results from the experiment.

8.    What are the limitations of your proposed model?

9.      The conclusion should be supported by results and highlight what will be a future direction for the current research work.

Author Response

"Please see the attachment." 

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

the revised manuscript is now suitable for publication. 

Reviewer 3 Report

The Revised Paper has incorporated all the revisions and now the paper stands Accepted with no further revisions.