kumoh national institute of technology
Networked Systems Lab.

Anti-Drone System: A Visual-based Drone Detection using Neural Networks, ICTC 2020 (Accepted)
By : Aj
Date : 2020-09-14
Views : 45

--------------- Reviews ------------------------------------

======= Review 1 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Excellent (5)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Good (4)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Good (4)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Excellent (5)

> *** Comments to authors: Please provide detailed comments to the authors.

The authors focus on video surveillance technology using Faster R-CNN (Region-based Convolutional Neural Network) with ResNet-101. The problem is well presented and related to the state of the art. The proposed method sounds and the results are promissing.

> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Accept (4)

======= Review 2 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Marginal (2)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Marginal (2)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Marginal (2)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Marginal (2)

> *** Comments to authors: Please provide detailed comments to the authors.

The paper tries to visually sense a drone by using Faster R-CNN. Neural Network can detect the target objects with moderately high accuracy, which is well-known. The main technical issues for sensing a drone is classification of drone movement. The paper also claims the same technical aspect, "classify the type of drone". However, evaluation seems to just for identification of drones.

> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Neutral (2)

======= Review 3 =======

> *** Relevance: How well does the content fit the conference scope? Is this paper handling an important theme in this area?
Good (4)

> *** Completeness: Does this paper describe the problem clearly? Are the results of this paper reproducible via experiments (implementations, proofs)? How well is the result analysis done with the previous works? How clear is the paper's conclusion for the problem tackled?
Good (4)

> *** Originality: Does this paper include any novel approaches or new applications that have never been tried?
Good (4)

> *** Presentation: Are the title, abstract, and keywords appropriate? How proper is the organization and description method of this paper?
Good (4)

> *** Comments to authors: Please provide detailed comments to the authors.

This work proposes an anti-drone system that uses visual sensing to detect drones.
Some suggestions are given below.
1. Number citations consecutively in square brackets.
2. Reference about the SafeShore dataset should be provided.

> *** Recommendation: Please provide your overall recommendation on the acceptance of the paper. (Final acceptance decisions will also consider literal responses to the questions below.)
Accept (4)