Autonomous Surveillance for an Indoor Security Robot
Round 1
Reviewer 1 Report
This paper proposes an autonomous robotic system based on CNN (Convolutional Neural Network) to perform visual perception and control tasks. The proposed visual perception system includes a motion detection module, a tracking module, face detection and recognition module. The control system includes motion control and navigation (path-planning & obstacle avoidance). Some comments are as followed.
1. Why does the paper perform detection and classification in separate steps? i.e. detect through harr features but classify through CNN?
2. How to quantitatively measure the change of the environment? i.e. the differences of illumination 1-4.
3. The lack of comparison among similar solutions. In the results, the main comparison are performed among different CNN architectures. However, it’s supposed to include the comparison with other existing autonomous robotic systems.
Author Response
Please see the attachment.
Author Response File: 
Author Response.docx
Reviewer 2 Report
The paper is well written and the contribution is clear. However authors should consider the following points to improve the quality of manuscript:
1- the contribution should be listed in bulletin at the end of the introduction section.
2. The description of the paper structure should be placed at the end of the introduction section.
T3 the authors should justify the decisions that made in the article.
4. The practical implications of the work should be stated in the conclusion section
Author Response
Please see the attachment.
Author Response File: Author Response.docx
Round 2
Reviewer 1 Report
All my concerns have been solved.
