IO-YOLOv5: Improved Pig Detection under Various Illuminations and Heavy Occlusion

Round 1

Reviewer 1 Report

The paper describes a new detection algorithm that could be used to detect other objects.

Some grammar errors should be corrected.

Reference 31 was not indicated in the reference section. Insert, 
Improve the format of equations (for example, 3 and 4).

Some english errors should be corrected.

Author Response

Please see the attachment

Reviewer 2 Report

IO-YOLOv5: Improved Pig Detection under Various Illumination and Heavy Occlusion

1. Very interesting research entitled “IO-YOLOv5: Improved Pig Detection under Various Illumination and Heavy Occlusion”.

2. Correct the structure of the article. 

3. The title of the figures (2, 3, 5, 10 and 11) must be short. The previous paragraph should explain the figure.

4. Figure 1 is missing the title of a module. It is indicated in the image below: (See attached file).

5. In the section "2.1 Data Acquisition", you must start with a paragraph and then place the figure.

6. About the images used to test the project.

 

 

 

a. There is a pre-processing of the images obtained?

b. How the images are treated, if there are phenomena such as: a lot of light, shadows, low light, brightness, dust, smog, etc.

         c. In what color model are the images obtained (RGB, rgb, XYZ, L*a*b*, L*u*v*, HSV, HLS, YCrCb, YUV, I1I2I3, TSL, etc) for processing. Is there any conversion?

7. Since the article is about image processing, I suggest you check out the following articles:

·        García-Mateos, G., Hernández-Hernández, J. L., Escarabajal-Henarejos, D., Jaén-Terrones, S., & Molina-Martínez, J. M. (2015). Study and comparison of color models for automatic image analysis in irrigation management applications. Agricultural water management, 151, 158-166.  https://doi.org/10.1016/j.agwat.2014.08.010

 

·        Hernández-Hernández, J. L., García-Mateos, G., González-Esquiva, J. M., Escarabajal-Henarejos, D., Ruiz-Canales, A., & Molina-Martínez, J. M. (2016). Optimal color space selection method for plant/soil segmentation in agriculture. Computers and Electronics in Agriculture, 122, 124-132.  https://doi.org/10.1016/j.compag.2016.01.020

 

8. I suggest developing an algorithm of the " Model  IO-YOLOv5 (Illumination-Occlusion YOLOv5)". I suggest that the algorithms in this article use the following format: (See attached file).

9. Consider future work on this research.

10. Very good bibliography. 

The article has good content and very interesting.

 

Authors are requested to make all indicated corrections.

Comments for author File: Comments.pdf

Author Response

Please see the attachment

Author Response File: Author Response.docx

Reviewer 3 Report

Your study proposes a development called IO-YOLOv5, indicating that a model with high performance in the field of pig counting and recognition has been presented. Experiments show that IO-YOLOV5 performs perfectly even in harsh conditions and can be further improved with the proposed data set. However, taking into account the suggestions I have mentioned below, you need to make some changes in your work.

1- Are there any studies similar to this study in the literature before? Comparing your study with a study on the detection of pigs will clearly reveal the originality of the study. Or, if there is no study aimed at detecting pigs, a comparison should be made with the study aimed at detecting other farm animals. In addition, making a comparison of the proposed model with another data set in the literature will be much more useful for the reader while highlighting the model.

2- In the comparisons given in Table 4, literature information about attention mechanisms such as SE, SimAM, ECA was not given, and literature information should be provided for the metrics used by opening a separate section for the performance metrics used for the evaluation of the study.

3- The Conclusions section should be expanded a little more and should be informative for readers and for future studies.

4- Why are some lines written in bold in table 6, while some lines are not written in bold in other tables, such as table 4 or table 5? do the lines written in bold carry a different meaning? please review this to ensure the integrity of the study.

5- This section should be improved by adding other literature information related to similar studies of the study to the study.

Author Response

Please see the attachment

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

I thank the authors for making the indicated corrections.

 

Reviewer 3 Report

You have successfully made the necessary arrangements. I hope that your work will be presented to the benefit of researchers as soon as possible.