Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5
Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area of ship targets is small, and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed and false detection. To...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-09-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4319 |
| _version_ | 1827727844732567552 |
|---|---|
| author | Jun Jian Long Liu Yingxiang Zhang Ke Xu Jiaxuan Yang |
| author_facet | Jun Jian Long Liu Yingxiang Zhang Ke Xu Jiaxuan Yang |
| author_sort | Jun Jian |
| collection | DOAJ |
| description | Due to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area of ship targets is small, and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed and false detection. To solve these problems, this paper proposes an improved-YOLOv5 algorithm mainly including: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce a cross-layer connection channel and lightweight GSConv structures into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) Use the Wise-IoU loss function to calculate the localization loss in the Output, and assign reasonable gradient gains to cope with differences in image quality. In addition, during the preprocessing stage of experimental data, a median+bilateral filter method was used to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Improved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; compared to the original YOLOv5s, the mean Average Precision (mAP) improved by 3.2% and the Frames Per Second (FPN) accelerated by 8.7%. |
| first_indexed | 2024-03-10T23:13:46Z |
| format | Article |
| id | doaj.art-c696a17da6a946b5b12f8221b6e5472c |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:13:46Z |
| publishDate | 2023-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c696a17da6a946b5b12f8221b6e5472c2023-11-19T08:47:33ZengMDPI AGRemote Sensing2072-42922023-09-011517431910.3390/rs15174319Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5Jun Jian0Long Liu1Yingxiang Zhang2Ke Xu3Jiaxuan Yang4Navigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaNavigation College, Dalian Maritime University, Dalian 116026, ChinaDue to the special characteristics of the shooting distance and angle of remote sensing satellites, the pixel area of ship targets is small, and the feature expression is insufficient, which leads to unsatisfactory ship detection performance and even situations such as missed and false detection. To solve these problems, this paper proposes an improved-YOLOv5 algorithm mainly including: (1) Add the Convolutional Block Attention Module (CBAM) into the Backbone to enhance the extraction of target-adaptive optimal features; (2) Introduce a cross-layer connection channel and lightweight GSConv structures into the Neck to achieve higher-level multi-scale feature fusion and reduce the number of model parameters; (3) Use the Wise-IoU loss function to calculate the localization loss in the Output, and assign reasonable gradient gains to cope with differences in image quality. In addition, during the preprocessing stage of experimental data, a median+bilateral filter method was used to reduce interference from ripples and waves and highlight the information of ship features. The experimental results show that Improved-YOLOv5 has a significant improvement in recognition accuracy compared to various mainstream target detection algorithms; compared to the original YOLOv5s, the mean Average Precision (mAP) improved by 3.2% and the Frames Per Second (FPN) accelerated by 8.7%.https://www.mdpi.com/2072-4292/15/17/4319optical remote sensing imagesconvolutional block attention modulecross-layer connection channellightweight GSConvWise-IoU loss functionmedian + bilateral filter |
| spellingShingle | Jun Jian Long Liu Yingxiang Zhang Ke Xu Jiaxuan Yang Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 Remote Sensing optical remote sensing images convolutional block attention module cross-layer connection channel lightweight GSConv Wise-IoU loss function median + bilateral filter |
| title | Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 |
| title_full | Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 |
| title_fullStr | Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 |
| title_full_unstemmed | Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 |
| title_short | Optical Remote Sensing Ship Recognition and Classification Based on Improved YOLOv5 |
| title_sort | optical remote sensing ship recognition and classification based on improved yolov5 |
| topic | optical remote sensing images convolutional block attention module cross-layer connection channel lightweight GSConv Wise-IoU loss function median + bilateral filter |
| url | https://www.mdpi.com/2072-4292/15/17/4319 |
| work_keys_str_mv | AT junjian opticalremotesensingshiprecognitionandclassificationbasedonimprovedyolov5 AT longliu opticalremotesensingshiprecognitionandclassificationbasedonimprovedyolov5 AT yingxiangzhang opticalremotesensingshiprecognitionandclassificationbasedonimprovedyolov5 AT kexu opticalremotesensingshiprecognitionandclassificationbasedonimprovedyolov5 AT jiaxuanyang opticalremotesensingshiprecognitionandclassificationbasedonimprovedyolov5 |