Next Article in Journal
An Intelligent Correlation Real-Time Analysis Method for the Mechanical Properties of Members in Super-Span Valve Hall Grid Structure Hoisting Process
Next Article in Special Issue
A Study on the Effectiveness of Spatial Filters on Thermal Image Pre-Processing and Correlation Technique for Quantifying Defect Size
Previous Article in Journal
Self-Supervised Learning for Point-Cloud Classification by a Multigrid Autoencoder
Previous Article in Special Issue
A Residual-Inception U-Net (RIU-Net) Approach and Comparisons with U-Shaped CNN and Transformer Models for Building Segmentation from High-Resolution Satellite Images
 
 
Article
Peer-Review Record

Adaptive CFAR Method for SAR Ship Detection Using Intensity and Texture Feature Fusion Attention Contrast Mechanism

Sensors 2022, 22(21), 8116; https://doi.org/10.3390/s22218116
by Nana Li 1, Xueli Pan 1,2,*, Lixia Yang 1, Zhixiang Huang 1, Zhenhua Wu 1 and Guoqing Zheng 2
Reviewer 1: Anonymous
Reviewer 2:
Sensors 2022, 22(21), 8116; https://doi.org/10.3390/s22218116
Submission received: 14 September 2022 / Revised: 17 October 2022 / Accepted: 18 October 2022 / Published: 23 October 2022
(This article belongs to the Special Issue Image Processing and Analysis for Object Detection)

Round 1

Reviewer 1 Report

The article proposes a constant false alarm rate (CFAR) algorithm for synthetic aperture radar (SAR) images to detect ship target based on the attention contrast mechanism of intensity and texture feature fusion. The topic is interesting and the paper is well organized. However, there are some major comments in the following points.

1- The title is general. It should be more specific and related to the methods used for detection and related to the detected objects.

 2- The paper needs more justifications and detailed about the results. For example. In Figure 8, why the detected objects of your method are thicker than the other methods?

3- The authors should add results on some other images with different and more complex backgrounds.

4- Compare your results with more recent methods.

5- More references of some recent methods relevant the topic should be reviewed and discuss their advantages and disadvantages.

6- The conclusions should be supported by the results, showing why and how it can significantly improve the TCR and its limitations as a future direction for researchers.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors have presented a manuscript that addresses the very attractive problem of detecting ships at sea using SAR sensors, with a focus on detecting small ships in a group of many objects at sea, i.e., in a complex environment. The developed model has been tested with a large number of images from a public dataset. In this work, the performance of the algorithm is demonstrated by analysing four selected images from SAR, where the proposed method (based on the mechanism of attentional contrast enhancement) shows the best results - it is compared with three known approaches. The paper includes all the elements relevant to the demonstration of a scientific paper, except for the potential limitations of this method. Here we are most interested in how the proposed method performs in azimuth ambiguities; it appears that this aspect is not discussed or tested at all. We are also interested in the proportion of false-positive detections.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Thank you for improving the quality of the manuscript. The authors updated the manuscript according to the review comments.

Back to TopTop