Next Article in Journal
Research on Impact of IoT on Warehouse Management
Next Article in Special Issue
Road User Position and Speed Estimation via Deep Learning from Calibrated Fisheye Videos
Previous Article in Journal
Strain Monitoring and Crack Detection in Masonry Walls under In-Plane Shear Loading Using Smart Bricks: First Results from Experimental Tests and Numerical Simulations
Previous Article in Special Issue
Wireless Link Selection Methods for Maritime Communication Access Networks—A Deep Learning Approach
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Sensors
Volume 23
Issue 4
10.3390/s23042208
Review Report
sensors-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
Article
Peer-Review Record

FPGA-Based Vehicle Detection and Tracking Accelerator

Sensors 2023, 23(4), 2208; https://doi.org/10.3390/s23042208
by Jiaqi Zhai 1, Bin Li 1,2,*, Shunsen Lv 1 and Qinglei Zhou 1
Reviewer 1:
Mariusz Rawski
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Sensors 2023, 23(4), 2208; https://doi.org/10.3390/s23042208
Submission received: 1 January 2023 / Revised: 4 February 2023 / Accepted: 10 February 2023 / Published: 16 February 2023
(This article belongs to the Special Issue Application of Deep Learning in Intelligent Transportation)

Round 1

Reviewer 1 Report

The paper is well written. Authors propose many optimizations for both CNN itself and for hardware accelerator. However proposed optimizations are described in very general way. Although the results presented show that proposed solution performs well, it would be good to discuss proposed optimizations in more details.

Some suggestions:
Fig. 5 The number of DMAs is m+n. How large can this number be in practice and how does it affect implementation parameters.

Equation (13) is not sufficiently explained and it is not clear how it affects architecture design decisions. Some parameters are not included in Tab.2. correct oW -> OW. I'm not sure if this is completely correct because the indexes c, r, s are not reflected in the body of the equation.

Equation (16) spaceratio - is the subscript intended?

Equation (17) if it expresses a feature map F, where is F in the equation?


Table 8 is difficult to read. It should be reformatted and perhaps divided into two tables.

Minor spelling errors and formatting can be corrected.


 

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

In this article, the authors presented the FPGA-based vehicle detector using YOLO and a deep sort algorithm. The accelerator architecture was well explained, along with the memory optimization techniques used in the implementation. A detailed background survey was performed, and the relevant references were cited. The mathematical expressions of different neural network layers used in the design were explained. A comparative result analysis is presented. 

It would have been nice to see a section on HLS concepts used in the implementation. 

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

I really enjoyed reading of this work and its overall quality. However, I have some little amendments that you can find in the attached file.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Back to TopTop