Cargando…

Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images

Traffic port stations are composed of buildings, infrastructure, and transportation vehicles. The target detection of traffic port stations in high-resolution remote sensing images needs to collect feature information of nearby small targets, comprehensively analyze and classify, and finally complet...

Descripción completa

Detalles Bibliográficos
Autores principales: Fang, Kun, Ouyang, Jianquan, Hu, Buwei
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8662445/
https://www.ncbi.nlm.nih.gov/pubmed/34884117
http://dx.doi.org/10.3390/s21238113
_version_ 1784613438229577728
author Fang, Kun
Ouyang, Jianquan
Hu, Buwei
author_facet Fang, Kun
Ouyang, Jianquan
Hu, Buwei
author_sort Fang, Kun
collection PubMed
description Traffic port stations are composed of buildings, infrastructure, and transportation vehicles. The target detection of traffic port stations in high-resolution remote sensing images needs to collect feature information of nearby small targets, comprehensively analyze and classify, and finally complete the traffic port station positioning. At present, deep learning methods based on convolutional neural networks have made great progress in single-target detection of high-resolution remote sensing images. How to show good adaptability to the recognition of multi-target complexes of high-resolution remote sensing images is a difficult point in the current remote sensing field. This paper constructs a novel high-resolution remote sensing image traffic port station detection model (Swin-HSTPS) to achieve high-resolution remote sensing image traffic port station detection (such as airports, ports) and improve the multi-target complex in high-resolution remote sensing images The recognition accuracy of high-resolution remote sensing images solves the problem of high-precision positioning by comprehensive analysis of the feature combination information of multiple small targets in high-resolution remote sensing images. The model combines the characteristics of the MixUp hybrid enhancement algorithm, and enhances the image feature information in the preprocessing stage. The PReLU activation function is added to the forward network of the Swin Transformer model network to construct a ResNet-like residual network and perform convolutional feature maps. Non-linear transformation strengthens the information interaction of each pixel block. This experiment evaluates the superiority of the model training by comparing the two indicators of average precision and average recall in the training phase. At the same time, in the prediction stage, the accuracy of the prediction target is measured by confidence. Experimental results show that the optimal average precision of the Swin-HSTPS reaches 85.3%, which is about 8% higher than the average precision of the Swin Transformer detection model. At the same time, the target prediction accuracy is also higher than the Swin Transformer detection model, which can accurately locate traffic port stations such as airports and ports in high-resolution remote sensing images. This model inherits the advantages of the Swin Transformer detection model, and is superior to mainstream models such as R-CNN and YOLOv5 in terms of the target prediction ability of high-resolution remote sensing image traffic port stations.
format Online
Article
Text
id pubmed-8662445
institution National Center for Biotechnology Information
language English
publishDate 2021
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-86624452021-12-11 Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images Fang, Kun Ouyang, Jianquan Hu, Buwei Sensors (Basel) Article Traffic port stations are composed of buildings, infrastructure, and transportation vehicles. The target detection of traffic port stations in high-resolution remote sensing images needs to collect feature information of nearby small targets, comprehensively analyze and classify, and finally complete the traffic port station positioning. At present, deep learning methods based on convolutional neural networks have made great progress in single-target detection of high-resolution remote sensing images. How to show good adaptability to the recognition of multi-target complexes of high-resolution remote sensing images is a difficult point in the current remote sensing field. This paper constructs a novel high-resolution remote sensing image traffic port station detection model (Swin-HSTPS) to achieve high-resolution remote sensing image traffic port station detection (such as airports, ports) and improve the multi-target complex in high-resolution remote sensing images The recognition accuracy of high-resolution remote sensing images solves the problem of high-precision positioning by comprehensive analysis of the feature combination information of multiple small targets in high-resolution remote sensing images. The model combines the characteristics of the MixUp hybrid enhancement algorithm, and enhances the image feature information in the preprocessing stage. The PReLU activation function is added to the forward network of the Swin Transformer model network to construct a ResNet-like residual network and perform convolutional feature maps. Non-linear transformation strengthens the information interaction of each pixel block. This experiment evaluates the superiority of the model training by comparing the two indicators of average precision and average recall in the training phase. At the same time, in the prediction stage, the accuracy of the prediction target is measured by confidence. Experimental results show that the optimal average precision of the Swin-HSTPS reaches 85.3%, which is about 8% higher than the average precision of the Swin Transformer detection model. At the same time, the target prediction accuracy is also higher than the Swin Transformer detection model, which can accurately locate traffic port stations such as airports and ports in high-resolution remote sensing images. This model inherits the advantages of the Swin Transformer detection model, and is superior to mainstream models such as R-CNN and YOLOv5 in terms of the target prediction ability of high-resolution remote sensing image traffic port stations. MDPI 2021-12-04 /pmc/articles/PMC8662445/ /pubmed/34884117 http://dx.doi.org/10.3390/s21238113 Text en © 2021 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Fang, Kun
Ouyang, Jianquan
Hu, Buwei
Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title_full Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title_fullStr Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title_full_unstemmed Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title_short Swin-HSTPS: Research on Target Detection Algorithms for Multi-Source High-Resolution Remote Sensing Images
title_sort swin-hstps: research on target detection algorithms for multi-source high-resolution remote sensing images
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8662445/
https://www.ncbi.nlm.nih.gov/pubmed/34884117
http://dx.doi.org/10.3390/s21238113
work_keys_str_mv AT fangkun swinhstpsresearchontargetdetectionalgorithmsformultisourcehighresolutionremotesensingimages
AT ouyangjianquan swinhstpsresearchontargetdetectionalgorithmsformultisourcehighresolutionremotesensingimages
AT hubuwei swinhstpsresearchontargetdetectionalgorithmsformultisourcehighresolutionremotesensingimages