Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery
Ship detection in remote sensing images plays an important role in maritime surveillance. Recently, convolution neural network (CNN)-based methods have achieved state-of-the-art performance in ship detection. Even so, there are still two problems that remain in remote sensing. One is that the differ...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-02-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/16/3/600 |
| _version_ | 1797318248396488704 |
|---|---|
| author | Fangli Mou Zide Fan Chuan’ao Jiang Yidan Zhang Lei Wang Xinming Li |
| author_facet | Fangli Mou Zide Fan Chuan’ao Jiang Yidan Zhang Lei Wang Xinming Li |
| author_sort | Fangli Mou |
| collection | DOAJ |
| description | Ship detection in remote sensing images plays an important role in maritime surveillance. Recently, convolution neural network (CNN)-based methods have achieved state-of-the-art performance in ship detection. Even so, there are still two problems that remain in remote sensing. One is that the different modal images observed by multiple satellite sensors and the existing dataset cannot satisfy network-training requirements. The other is the false alarms in detection, as the ship target is usually faint in real view remote sensing images and many false-alarm targets can be detected in ocean backgrounds. To solve these issues, we propose a double augmentation framework for ship detection in cross-modal remote sensing imagery. Our method can be divided into two main steps: the front augmentation in the training process and the back augmentation verification in the detection process; the front augmentation uses a modal recognition network to reduce the modal difference in training and in using the detection network. The back augmentation verification uses batch augmentation and results clustering to reduce the rate of false-alarm detections and improve detection accuracy. Real-satellite-sensing experiments have been conducted to demonstrate the effectiveness of our method, which shows promising performance in quantitative evaluation metrics. |
| first_indexed | 2024-03-08T03:49:40Z |
| format | Article |
| id | doaj.art-453cf78913954875a4590db49086813b |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-08T03:49:40Z |
| publishDate | 2024-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-453cf78913954875a4590db49086813b2024-02-09T15:21:36ZengMDPI AGRemote Sensing2072-42922024-02-0116360010.3390/rs16030600Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing ImageryFangli Mou0Zide Fan1Chuan’ao Jiang2Yidan Zhang3Lei Wang4Xinming Li5Key Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaKey Laboratory of Target Cognition and Application Technology, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100190, ChinaShip detection in remote sensing images plays an important role in maritime surveillance. Recently, convolution neural network (CNN)-based methods have achieved state-of-the-art performance in ship detection. Even so, there are still two problems that remain in remote sensing. One is that the different modal images observed by multiple satellite sensors and the existing dataset cannot satisfy network-training requirements. The other is the false alarms in detection, as the ship target is usually faint in real view remote sensing images and many false-alarm targets can be detected in ocean backgrounds. To solve these issues, we propose a double augmentation framework for ship detection in cross-modal remote sensing imagery. Our method can be divided into two main steps: the front augmentation in the training process and the back augmentation verification in the detection process; the front augmentation uses a modal recognition network to reduce the modal difference in training and in using the detection network. The back augmentation verification uses batch augmentation and results clustering to reduce the rate of false-alarm detections and improve detection accuracy. Real-satellite-sensing experiments have been conducted to demonstrate the effectiveness of our method, which shows promising performance in quantitative evaluation metrics.https://www.mdpi.com/2072-4292/16/3/600remote sensing processingmaritime surveillanceship detectionocean engineeringcross-modal transforming |
| spellingShingle | Fangli Mou Zide Fan Chuan’ao Jiang Yidan Zhang Lei Wang Xinming Li Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery Remote Sensing remote sensing processing maritime surveillance ship detection ocean engineering cross-modal transforming |
| title | Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery |
| title_full | Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery |
| title_fullStr | Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery |
| title_full_unstemmed | Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery |
| title_short | Double Augmentation: A Modal Transforming Method for Ship Detection in Remote Sensing Imagery |
| title_sort | double augmentation a modal transforming method for ship detection in remote sensing imagery |
| topic | remote sensing processing maritime surveillance ship detection ocean engineering cross-modal transforming |
| url | https://www.mdpi.com/2072-4292/16/3/600 |
| work_keys_str_mv | AT fanglimou doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery AT zidefan doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery AT chuanaojiang doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery AT yidanzhang doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery AT leiwang doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery AT xinmingli doubleaugmentationamodaltransformingmethodforshipdetectioninremotesensingimagery |