Application of convolutional neural networks trained on optical images for object detection in radar images
Due to the small number of annotated radar image datasets, the use of optical images for training neural networks designed to detect objects in radar images seems promising. However, optical images have some significant differences from radar images and an experimental investigation of this possibil...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Samara National Research University
2024-04-01
|
| Series: | Компьютерная оптика |
| Subjects: | |
| Online Access: | https://www.computeroptics.ru/eng/KO/Annot/KO48-2/480212e.html |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832540916666073088 |
|---|---|
| author | V.A. Pavlov A.A. Belov S.V. Volvenko A.V. Rashich |
| author_facet | V.A. Pavlov A.A. Belov S.V. Volvenko A.V. Rashich |
| author_sort | V.A. Pavlov |
| collection | DOAJ |
| description | Due to the small number of annotated radar image datasets, the use of optical images for training neural networks designed to detect objects in radar images seems promising. However, optical images have some significant differences from radar images and an experimental investigation of this possibility is required. In this work we investigate the applicability of such an approach and show that in the case of detection of ships good results can be achieved. In addition, it is shown that preliminary filtering of speckle noise can improve the results. |
| format | Article |
| id | doaj-art-c437bdb4ca534044a76a7283b19fe814 |
| institution | Kabale University |
| issn | 0134-2452 2412-6179 |
| language | English |
| publishDate | 2024-04-01 |
| publisher | Samara National Research University |
| record_format | Article |
| series | Компьютерная оптика |
| spelling | doaj-art-c437bdb4ca534044a76a7283b19fe8142025-02-04T12:46:25ZengSamara National Research UniversityКомпьютерная оптика0134-24522412-61792024-04-0148225325910.18287/2412-6179-CO-1316Application of convolutional neural networks trained on optical images for object detection in radar imagesV.A. Pavlov0A.A. Belov1S.V. Volvenko2A.V. Rashich3Peter the Great St.Petersburg Polytechnic UniversityPeter the Great St.Petersburg Polytechnic UniversityPeter the Great St.Petersburg Polytechnic UniversityPeter the Great St.Petersburg Polytechnic UniversityDue to the small number of annotated radar image datasets, the use of optical images for training neural networks designed to detect objects in radar images seems promising. However, optical images have some significant differences from radar images and an experimental investigation of this possibility is required. In this work we investigate the applicability of such an approach and show that in the case of detection of ships good results can be achieved. In addition, it is shown that preliminary filtering of speckle noise can improve the results.https://www.computeroptics.ru/eng/KO/Annot/KO48-2/480212e.htmlspeckle noiseradar imagesarnoise reductionimage processingssimgmsdobject detectionneural networks |
| spellingShingle | V.A. Pavlov A.A. Belov S.V. Volvenko A.V. Rashich Application of convolutional neural networks trained on optical images for object detection in radar images Компьютерная оптика speckle noise radar image sar noise reduction image processing ssim gmsd object detection neural networks |
| title | Application of convolutional neural networks trained on optical images for object detection in radar images |
| title_full | Application of convolutional neural networks trained on optical images for object detection in radar images |
| title_fullStr | Application of convolutional neural networks trained on optical images for object detection in radar images |
| title_full_unstemmed | Application of convolutional neural networks trained on optical images for object detection in radar images |
| title_short | Application of convolutional neural networks trained on optical images for object detection in radar images |
| title_sort | application of convolutional neural networks trained on optical images for object detection in radar images |
| topic | speckle noise radar image sar noise reduction image processing ssim gmsd object detection neural networks |
| url | https://www.computeroptics.ru/eng/KO/Annot/KO48-2/480212e.html |
| work_keys_str_mv | AT vapavlov applicationofconvolutionalneuralnetworkstrainedonopticalimagesforobjectdetectioninradarimages AT aabelov applicationofconvolutionalneuralnetworkstrainedonopticalimagesforobjectdetectioninradarimages AT svvolvenko applicationofconvolutionalneuralnetworkstrainedonopticalimagesforobjectdetectioninradarimages AT avrashich applicationofconvolutionalneuralnetworkstrainedonopticalimagesforobjectdetectioninradarimages |