Next Article in Journal
Investigation of Dual-Flow Deep Learning Models LSTM-FCN and GRU-FCN Efficiency against Single-Flow CNN Models for the Host-Based Intrusion and Malware Detection Task on Univariate Times Series Data
Next Article in Special Issue
On the Impact of the Rules on Autonomous Drive Learning
Previous Article in Journal
Vibrational Quenching of Weakly Bound Cold Molecular Ions Immersed in Their Parent Gas
Previous Article in Special Issue
An Adaptive Approach for Multi-National Vehicle License Plate Recognition Using Multi-Level Deep Features and Foreground Polarity Detection Model
 
 
Article
Peer-Review Record

Highly Curved Lane Detection Algorithms Based on Kalman Filter

Appl. Sci. 2020, 10(7), 2372; https://doi.org/10.3390/app10072372
by Byambaa Dorj 1, Sabir Hossain 2 and Deok-Jin Lee 2,*
Reviewer 1: Anonymous
Reviewer 2: Anonymous
Reviewer 3: Anonymous
Appl. Sci. 2020, 10(7), 2372; https://doi.org/10.3390/app10072372
Submission received: 12 February 2020 / Revised: 19 March 2020 / Accepted: 25 March 2020 / Published: 30 March 2020
(This article belongs to the Special Issue Intelligent Transportation Systems: Beyond Intelligent Vehicles)

Round 1

Reviewer 1 Report

The paper entitled "Highly Curved Lane Detection Algorithms based on Kalman Filter" presents a novel approach for elf-driving cars. Overall, the paper needs a revision, in detail, the following issues should be considered:

 

(i) english and grammar. this is probably one of the most critical points - make sure to proofread the manuscript before submitting.

 

(ii) attention with statements like "the development of the self-driving car is only for driver and passenger safety on the road" - this needs a reference... nevertheless, I think that other reasons are also applicable for the development of self-driving cars, like comfort, time-issues, ...

 

(iii) what means "far distance" ("[...]it is necessary to detect road lane from a far distance [...]")

 

(iv) why is the word "highly" in the title - "Highly Curved Lane..." - what makes it "highly"?

 

(v) I miss a dedicated and comprehensive related work section - currently, related methods and approaches are described in the introduction - but a critical discussion and distinction to your own work is necessary. 

 

(vi) In section 2.2 Figures 17 and 19 are referenced - pls avoid referencing images that are 10 pages ahead in the paper.

 

(vii) what does "The height of the camera is measured by metric"??

 

Generally, the scientific approach is sound, the topic is relevant.

Author Response

Response are attach on the document file. Kindly check the document file for the response based on the review. 

Author Response File: Author Response.docx

Reviewer 2 Report

The paper presents a curved lane detection algorithm based on the Kalman filter for self-driving cars.

This topic is studied by many authors and described in numerous papers. However, the authors do not refer to these recent studies and present an incomplete state of the art (the most recent document was published in 2016).

In Scopus data base there are 462 papers published since 2017,  with the keywords “Lane detection” and “Kalman filter” in Title or Abstract. An extensive and up-to-date section of related work is missing to explain what distinguishes the work presented from those already in the literature. For this reason I suggest to revise Section 1.

I also suggest to review the results by better focusing the following aspect:

The authors present the results “even under a very noisy environment”, but they do not explain which is the noisy environment. Please clarify   the robustness of the lane estimator  in bad conditions : lack of clarity of the lane marks, poor visibility due to bad weather, lighting and light reflection, shadows.

The References  should be presented with more technical  accuracy.

For istance (the first two references]

1. Green, M. “ How long does it take to stop?” Methodological analysis of driver perception-brake times. Transp. Hum. factors 2000, 2, 195–216.

2. Vacek, S.; Schimmel, C.; Dillmann, R. Road-marking Analysis for Autonomous Vehicle Guidance. In Proceedings of the EMCR; 2007. [no inverted commas, no page number]

 

Author Response

Kindly check the pdf file for the response based on the reviews and comments.

Thank you. 

Author Response File: Author Response.pdf

Reviewer 3 Report

Although it is an interesting paper, but the paper need heavily rework before it is acceptable.

  1. Please define all variables. E.g., what is V in (4)?
  2. Page 3 line 100, the relationship between H and Hpixel is not shown in (4), but requires both (4) and (5).
  3. Are xi, yi in equations (5) and (6) same as the Xi, Yi in Figure 2? If it is, then case letter shall be the same.
  4. Page 4 Line 120, the figure numbering shall be in order. If Figure 20 is reference here, then it should be become Figure 3 instead.
  5. Please check any paragraph order mistake such as in Page 5 line 135.
  6. Equation (9) is incorrect, which violates the matrix multiplication rule.
  7. An overall block diagram that show how the proposed algorithm fit into a system would be appreciated.
  8. Author need to explain the simulation results. For example, what is the reason that cause an error spike at 480 seconds in Fig 14 to 16?
  9. Author need to discuss why and what is the impact of the right hand side of Figure 23. For example, how it affect the detection and auto driving?

 

 

 

Author Response

Kindly check the pdf file for the response based on the reviews and comments.

Thank you. 

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

I have no comment. 

Author Response

The English grammar is checked again. Also, we check the repetition rate. We tried to reduce the repetition rate of a single article less than 8%. Kindly check again. 

Back to TopTop