CS2125 Paper Review Form - Winter 2019

Reviewer: Mohammad Rashidujjaman Rifat

Paper Title: Springrobot: A prototype autonomous vehicle and its algorithms for lane detection.

Author(s): Qing Li, Nanning Zheng, Hong Cheng

1) Is the paper technically correct?
 [✓] Yes
 [ ] Mostly (minor flaws, but mostly solid)
 [ ] No

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [✓] Good 
 [ ] Marginal (very incremental)
 [ ] Poor (little or nothing that is new)

3) Technical Depth
 [ ] Very good (comparable to best conference papers)
 [✓] Good (comparable to typical conference papers)
 [ ] Marginal depth
 [ ] Little or no depth

4) Impact/Significance
 [ ] Very significant
 [✓] Significant
 [ ] Marginal significance.
 [ ] Little or no significance.

5) Presentation
 [ ] Very well written
 [ ] Generally well written
 [✓] Readable
 [ ] Needs considerable work
 [ ] Unacceptably bad

6) Overall Rating
 [ ] Strong accept (award quality)
 [✓] Accept (high quality - would argue for acceptance)
 [ ] Weak Accept (borderline, but lean towards acceptance)
 [ ] Weak Reject (not sure why this paper was published)


7) Summary of the paper's main contribution and rationale
   for your recommendation. (1-2 paragraphs)

One major aspect of autonomous vehicle research is lane detection.To solve the problem, the paper proposes a new method to robustly detect the lane boundaries on a variety of different road types under a variety of illumination changes and shadowing. The paper introduces an adaptive randomized Hough transform (HT) that globally and rather coarsely detect road markings in a reduced image; this image is then refined in the original image. Experiment results of the system show that it can detect lane markings correctly.

For solving the problem of traffic congestion and accidents, especially in big cities such as Beijing, Shanghai, and Guangzhou, the Chinese government has been increasing funding for improving the traffic infrastructure, enforcing traffic laws, and educating drivers about traffic regulation. In addition, research institutes have launched research and development projects in driver assistance and safety warning systems. This project is a reflection of this effort. To detect lane marking, the paper first make a model of road boundaries. The next step is color Feature Selection and Image Preprocessing. To reduce the 3-D parametric space to the 2-D and the one-dimensional (1-D) space, the paper uses an adaptive randomized Hough Transformation algorithm; it reduces computational costs. Overall, the approach reduces computational costs and increases efficiency.


This paper is one of the earlier efforts in driving forward the research of autonomous vehicle.


8) List 1-3 strengths of the paper.  (1-2 sentences each,
identified as S1, S2, S3.)

S1. This paper is one of the earlier efforts in driving forward the research of autonomous vehicle. Many works have been built on this paper.
S2. The paper shows an effective way to reduce computational costs by using a randomized HT algorithm.
s3. Authors also presented the basic architecture of self-driving car.

9) List 1-3 weaknesses of the paper (1-2 sentences each,
identified as W1, W2, W3.)

W1. This paper is very poorly written. Some references are directly copied from the source without rephrasing them.
W2. The technical components are weakly presented in the paper.
W3. A few examples in the experiment shows that the approach failed to detect some lanes correctly.