SUNet: Change Detection for Heterogeneous Remote Sensing Images from Satellite and UAV Using a Dual-Channel Fully Convolution Network

Round 1

Reviewer 1 Report

According to the authors, the main challenges in satellite-UAV change detection tasks lie in the intensive difference of color for the same ground objects, various resolutions, the parallax effect, and image distortion caused by different shooting angles and platform altitudes.

The main challenges in satellite-UAV change detection are summarized in the introduction part of the paper.

To address these issues, the authors have proposed a method based on dual-channel fully convolution network. The development of that method include four steps:

1.In order to alleviate the influence of differences between heterogeneous images, we employ two different channels to map heterogeneous remote sensing images from satellite and UAV respectively to a mutual high dimension latent space for the downstream change detection task.

2.Adaptation of Hough method to extract the edge of ground objects as auxiliary information to help the change detection model to pay more attention to shapes and contours, instead of colors.

3.IoU-WCE loss is designed to deal with the problem of imbalanced samples in change detection task.

4.Conduction of extensive experiments to verify the proposed method using a new Satellite-UAV heterogeneous image data set, named HTCD, which is annotated in this paper and has been open to public.

The experimental results show that the proposed method significantly outperforms the state-of-the-art change detection methods.

For their future work, the authors will study semi-supervised or unsupervised satellite-UAV change detection methods which have wider application scenarios.

 

I have some reviewer notes:

 

It will be good to add “Discussion” section and to compare your results with those from other authors. Compare with minimum 3 papers.

 

In the “Conclusion” part, you have to show more detailed description of your findings and how they affect the knowledge. Also, what are the advantages of your findings over the existing ones.

 

It will be good to add a link to the open to public data set in “Supplementary materials” section. After line 882.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

Please see the attached report.

Comments for author File: Comments.pdf

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

The authors have addressed all of my comments.

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.