Next Article in Journal
A Novel Markov Model-Based Traffic Density Estimation Technique for Intelligent Transportation System
Next Article in Special Issue
Pavement Roughness Grade Recognition Based on One-dimensional Residual Convolutional Neural Network
Previous Article in Journal
Wearable System Based on Ultra-Thin Parylene C Tattoo Electrodes for EEG Recording
Previous Article in Special Issue
Development of a GIS-Based Methodology for the Management of Stone Pavements Using Low-Cost Sensors
 
 
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 2
10.3390/s23020767
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

Detection and Recognition Algorithm of Arbitrary-Oriented Oil Replenishment Target in Remote Sensing Image

Sensors 2023, 23(2), 767; https://doi.org/10.3390/s23020767
by Yongjie Hou, Qingwen Yang, Li Li and Gang Shi *
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Sensors 2023, 23(2), 767; https://doi.org/10.3390/s23020767
Submission received: 23 December 2022 / Revised: 31 December 2022 / Accepted: 4 January 2023 / Published: 9 January 2023
(This article belongs to the Special Issue Low-Cost Sensors for Road Condition Monitoring)

Round 1

Reviewer 1 Report

This paper proposes a new target detection algorithm to improve the detection effect of existing remote sensing images. This study is interesting and valuable, but needs to be further revised before publication

(1) The author has proposed a detection algorithm based on YOLO framework, but there is less discussion about YOLO in the introduction. In order to highlight the contribution proposed in this paper, more discussion about YOLO is necessary. (e.g., https://doi.org/10.1111/mice.12500 and https://doi.org/10.3390/app11020813)

(2) What are the advantages of MobileNetv3? Why the method proposed in this paper adopts it.

(3) What criteria are used to determine the selection of network parameters?

(4) The author explained the computer configuration. I was a little confused. The NVIDIA GTX 2080Ti GPU handles 1024×1024 images. Can its FPS reach 96.8?

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Reviewer 2 Report

The MR-YOLO algorithm was proposed in this manuscript to improve the accuracy and speed of pavement oil mark detection. MobileNetv3 lightweight network structure was introduced to reduce the model volume and improve the detection rate. SPPNet network structure was instructed to remove redundant feature options and improve the detection accuracy of the model. It can be seen from the experimental results of MR-YOLO and other algorithms that the P-value and mAP value of the algorithm proposed in this paper is improved compared with YOLOv5s. Although the FPS is higher than the YOLOv3 model, it is not the best at present. Now, the faster YOLOv7 is coming, and you can improve your model by considering YOLOv7.  

 

In addition, here are some small tips you need to concern below:

1) In Line 293, The colon is followed by an extra period.

2) Table 1, Line 359 and Line 360 are overlapped with the table.

3) Figure 1 does not appear to be your original, so please make the right citation. 

4) Your title "Oil Replenishment" does not seem appropriate.

Author Response

Please see the attachment.

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

No comment

Back to TopTop