Multi-Agent Vision System for Supporting Autonomous Orchard Spraying

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

 The authors proposed a multi-agent vision system supporting the autonomous spraying of orchards and analyzing the condition of trees, and the occurrence of pests and diseases. Experimental results show the proposed method achieves a significant improvement in detection performance. To further improve the quality of the paper, the following issues need to be addressed:

1. In the abstract, the authors better present how much improvement their proposed method achieves compared to the state-of-the-art method. 

2. In section 1, the discussed related works are almost all before 2023, the authors better include the most recent related works.

3. It is better to discuss why the proposed architecture is useful and its advantages.

4. Improved Visual Representation: Enhancements in clarity and resolution are needed for Figures 13 and 14. Additionally, expanding and refining the figure captions will aid readers in better comprehending the presented results.

5. It's essential to assess whether the modified deep convolutional neural networks Xception and

NasNetLarge is truly innovative compared to existing solutions.

Please explain why the validation curve in Figure 18 fluctuates so much.

6. Experiments demonstrate the effectiveness of each component of the proposed method. However, why the authors do not include the comparison with state-of-the-art methods? Please supplement this point, as this comparison is critical to verify the importance of the proposed work.

Author Response

Dear Reviewer,

Please see the attachment with our comments and responses.

Best Regards

Piotr Góral

 

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The paper titled "Multi-agent vision system for supporting the autonomous orchard spraying", attempts to propose a new method for autonomous spraying. But there are some major technical flows in the paper as follows:

- The problem statement and its significance is not clear.

- At many places the paper lacks complete description and details. For example picture classification algorithm.

- At several places citations are missing.

- Which classification algorithms were considered for pictures collected by authors?

- How the weather impacts this approach? can we use proposed method in all seasons? The limitations and assumptions are not very clear.

- Needs citation, "Using the latest data processing methods based on AI, as well as the experience of one of the authors on the work in growing fruit trees and also known strategies for their protection against pests, we propose an intelligent system for protective and autonomous spraying in horticulture based on a multi-agent vision system."

- Needs citation, "The image from the camera is processed by a vision algorithm that detects"

- Overall the main contribution of the paper is not very clear, most of the algorithms used are pre-existing and there is a lack of mathematical expressions and equations used for this research.

Comments on the Quality of English Language

Minor spell checks and grammatical checks.

Author Response

Dear Reviewer,

Please see the attachment with our comments and responses.

Best Regards

Piotr Góral

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

In the paper under review, the authors propose a multi-agent vision system supporting autonomous spraying of orchards and analyze the condition of trees, the occurrence of pests and diseases. The vision system consists of several agents: first, for detection of pests and disease of fruit crops, second, for estimation of the height of trees to be covered with spraying, third, for classification of the developmental status of trees, and fourth, for classification of trees infections by orchard diseases. For the classification, modified deep convolutional neural networks were used. The topic is interesting, the paper is well structured and the results are well discussed. My overall comment is as follows

1- Keywords should be short and concise.

2- In the last paragraph of the introduction “[the paper is organized as follows: after the Introduction, in Chapter 2 characteristics of the….]” instead of using “Chapter 2 etc.” used “Section 2, Section 3, etc.”

3- The authors should specify the type and specificity/characteristics of the camera that detects the pest.

4- How the intelligent system identifies the image considered.

4- Figures 13 and 14 should be labelled and presented as tables.

5- Expand the captions for figures 14-17 to make them almost self-explanatory.

6-Typos and grammatical errors should be edited in the whole manuscript.

Comments on the Quality of English Language

Minor editing of English language can be done to eliminate Typos

Author Response

Dear Reviewer,

Please see the attachment with our comments and responses.

Best Regards

Piotr Góral

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have addressed all of my concerns. the paper can be accepted in present form.

Comments on the Quality of English Language

Minor checks.

Author Response

Dear Reviewer,

Thank you for the review and all your comments and suggestions.

Best Regards

Piotr Góral

Reviewer 3 Report

Comments and Suggestions for Authors

The revised ms is much more readable. I have only one suggestion. The quality of Fig.16 is poor. Why are they blurred?

Author Response

Dear Reviewer,

Thank you for your suggestion, we have added Fig. 16 in the appropriate quality to the manuscript.

Best Regards

Piotr Góral