The Use of the Combination of Texture, Color and Intensity Transformation Features for Segmentation in the Outdoors with Emphasis on Video Processing

Round 1

Reviewer 1 Report

This manuscript is organized well and easy to follow.  There is no significant issues, but there are couple of questions that need to be explained clearly. 

Does this method have any time window (growth stages of fruits) to collect data (video) from fruit trees?  

Does this method work for apple trees only or can be applied to other fruit trees? 

Author Response

1. Does this method have any time window (growth stages of fruits) to collect data (video) from fruit trees?  

Since the algorithm has been trained in different days, times of the day, and weather conditions, so it can work in different growth stages of fruits.

2. Does this method work for apple trees only or can be applied to other fruit trees? 

In this study applied for apple only, but the algorithm can be used for another fruits.

We considered 2 additional references.

The manuscript was revised from the English language by a native professor from the United States.

 

It is in red color is what was corrected and added.

Author Response File: Author Response.docx

Reviewer 2 Report

Publication should be corrected. The authors should:

- Extend the introduction by justifying the significance of devised algorithm for precision farming.

- Describe in greater detail the methodology of obtaining samples for experiments.

 

Specific comments in pdf file.

Comments for author File: Comments.pdf

Author Response

Specific comment 1

Section: Introduction

The authors should describe in greater detail the significance of research regarding the recognition of an image in horticulture – identifying fruits. For what are they planning to use the algorithm? More references should be cited.

A paragraph was included in Introduction, pointing out that we have found that the works are directed to the recognition of fruits, counting, detection of plants, monitoring of irrigation, etc.

We considered 2 additional references.

Specific comment 2

Section 2.1. Data collection

1. The authors should describe filming process in greater detail, e.g:  How many, when and how long (duration) the films were made?

We collected several films of orchard but we used only 12 min (22001 frames) of them for training of algorithm. We had filming in 4 stages of ripening include Unripe (20 days befor maturity), Half-ripe (10 days befor maturity), Ripe and Overripe (10 days after maturity), that combined them for training of algorithm. The filming conditions were full natural, some light intensities were 398 lux, 1096 lux, 692 lux, 1591 lux, 1923 lux, 894 lux, 2010 lux, 918 lux, 798 lux, 493 lux and 579 lux.

2. Was the camera stationary or mobile during the filming? How did the camera move in relation to the trees?  At what height was it placed?

The distance from the trees was between 0.5 and 2 m, the speed was around 1 m/s, and the viewing angle was nearly parallel to the ground. The camera was manually held, simulating a low-medium height flight of a drone. With the system described, which has a horizontal viewing angle around 80^o an apple about 7 cm would be observed with a size of 20 pixels at a distance about 3 m over the trees.

3. Species and varieties of the apple tree and the stage of fruit ripening at which the filming was conducted should be mentioned.

Apple variety was Malus Domestica L., var. Red Delicious. We had filming in 4 stages of ripening include Unripe, Half-ripe , Ripe and Overripe.

The manuscript was revised from the English language by a native professor from the United States.

It is in red color is what was corrected and added.

Author Response File: Author Response.docx

Round 2

Reviewer 2 Report

In the current version, the publication will be more interesting for readers.