Next Article in Journal
A Survey for the Ranking of Trajectory Prediction Algorithms on Ubiquitous Wireless Sensors
Next Article in Special Issue
Influence of Neighborhood Size and Cross-Correlation Peak-Fitting Method on Location Accuracy
Previous Article in Journal
A Novel Method for Sea-Land Clutter Separation Using Regularized Randomized and Kernel Ridge Neural Networks
Previous Article in Special Issue
Application of Crowd Simulations in the Evaluation of Tracking Algorithms
 
 
Article
Peer-Review Record

Study on the Moving Target Tracking Based on Vision DSP

Sensors 2020, 20(22), 6494; https://doi.org/10.3390/s20226494
by Xuan Gong 1, Zichun Le 2,*, Hui Wang 1 and Yukun Wu 1
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Sensors 2020, 20(22), 6494; https://doi.org/10.3390/s20226494
Submission received: 28 September 2020 / Revised: 10 November 2020 / Accepted: 12 November 2020 / Published: 13 November 2020
(This article belongs to the Special Issue Object Tracking and Motion Analysis)

Round 1

Reviewer 1 Report

This paper embeds KCF tracker into vision DSP. The following issues should be addressed.

  1. Please clearly clarify the contributions of this paper.
  2. Please conduct extensive evaluations on benchmark datasets, such as OTB100, VOT2018, etc.
  3. Can the method readily extend to other tracking algorithms, such as Parallel attentive correlation tracking, Robust visual tracking via convolutional networks without training?  
  4. What are the limitations of the proposed method ?

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The work is interesting. 

I would, however, discuss and cite similar works from 2020 and would decrease the references in Chinese as the journal is international and not all people know Chinese language. 

The algorithms and computer programs are presented very well, but I would prefer seeing their computer flowcharts   

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

General Comments:

The paper handles visual tracking systems and presents a study on evaluating hardware optimization methods that provide efficient utilization under limited hardware resources. This paper also studies the performance of kernel correlation filter tracking algorithm based on a vision digital signal processor. The topic is important for moving target tracking systems and the presented study is useful. However, clarity and lack of referencing are the main issues in this paper. A major revision is necessary to clarify the presented methods and specify the proper references.

Specific Comments:

  1. Section 3.1:
  2. All formulas in this section should be referenced and explained clearly. The same comment applies to Section 3.2.
  3. Better explanation is required to show how tracking is performed; also, how the correlation coefficient is calculated.
  4. Section 4.1:
  5. Training of the classifier is unclear.
  6. Image features should be defined and clarified.
  7. Section 5:
  8. A clear performance measure is required.
  9. In Figure 10, the term “precision” should be clearly defined.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

The Authors have performed a major revision on this manuscript, where they addressed the Reviewers’ comments in detail. The current version of the manuscript is useful and ready for publication.

Back to TopTop