A Survey of Farmland Boundary Extraction Technology Based on Remote Sensing Images

Round 1

Reviewer 1 Report

This survey presented the details of farmland boundary extraction based on remote sensing images. Authors have covered more than 2 decades and presented various kinds of algorithms, and feature extraction methods for this purpose. There are a few more things I wish to see in this survey to make it more comprehensive and helpful for the readers. 

I would like to see the algorithmic explanation and as well as in summarized form based on classic machine learning vs Deep learning techniques. Importantly would like to see the performance achieved in terms of accuracy those methods have achieved and then relate the computing complexity with those algos to suggest the best one.

I would like to see the all-important section of relevant datasets with their detail available for research purposes.

Author Response

Please see the attachment.

 

 

Author Response File: Author Response.pdf

Reviewer 2 Report

In this work, the authors have surveyed the farm boundary extraction techniques. They collected the relevant articles this field at home and abroad in this review, and systematically assessed the farmland boundary extraction process, detection algorithms, and influencing factors. They discussed the five parts of the assessment: (1) image acquisition; (2) preprocessing; (3) detection algorithms; (4) postprocessing; (5) the evaluation of the boundary information extraction process. Recognition algorithms are discussed in depth. The detection algorithms are discussed by dividing into four types: (1) low-level feature extraction algorithms, which only consider the boundary features; (2) high-level feature extraction algorithms, which consider boundary information and other image information simultaneously; (3) visual hierarchy extraction algorithms, which simulate biological vision systems; (4) boundary object extraction algorithms, which recognize boundary object extraction ideas. Each type of algorithm are divided into several algorithm subclasses. The technical factors and natural factors that affect boundary extraction are discussed. Finally, the development history of this field is summarized, and the problems that exist, such as the lack of algorithms that can be adapted to higher-resolution images, the lack of algorithms with good practical ability, and the lack of a unified and effective evaluation index system are analyzed

Author Response

Please see the attachment.

 

 

Author Response File: Author Response.pdf

Reviewer 3 Report

A review article discussing the exploration of technologies for extracting farmland boundaries using remote sensing images offers a comprehensive overview of the image acquisition, preprocessing, detection algorithms, postprocessing, and evaluation of the boundary extraction process. The article's chapters are logically linked to each other. In the first half, well-known algorithms for preprocessing, segmentation, and extraction of other features from images are presented, along with their application to the topic of the paper. However, this part is diminished by some factual errors, such as the inclusion of the Hough transform among frequency domain algorithms (line 360, Fig. 3). There are also issues with sentence continuity (line 122) and typographical errors (Snakes snake model Tab. 4). The second half of the article covers more advanced algorithms and methods, which appear to be correct, though some of the methods are new to me, and I cannot judge their accuracy. The article is readable, but contains grammatical errors that do not alter the meaning, such as in Tab. 12 Shooting range (Very Huge). The first link in Tab. 11 does not work. Fig. 6 and 7 could be improved, such as by removing decimal places on the y-axis (Fig. 6) or increasing the font size of axis labels (Fig. 7). It is also possible to replace the figures with tables. Despite the aforementioned comments, I consider this article to be valuable, also for other disciplines that use image processing, particularly segmentation methods.

Author Response

Please see the attachment.

 

 

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Improved and accepted.