Next Article in Journal
Recurrent Neural Network Based Short-Term Load Forecast with Spline Bases and Real-Time Adaptation
Previous Article in Journal
A Novel Decision Support System for Long-Term Management of Bridge Networks
 
 
Article

Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing

1
National Engineering Research Center for Water Transport Safety, Wuhan University of Technology, Wuhan 430063, China
2
College of Technology, Hubei Engineering University, Xiaogan 432000, China
*
Author to whom correspondence should be addressed.
Academic Editor: Antonio Fernández-Caballero
Appl. Sci. 2021, 11(13), 5931; https://doi.org/10.3390/app11135931
Received: 25 April 2021 / Revised: 19 June 2021 / Accepted: 21 June 2021 / Published: 25 June 2021
(This article belongs to the Topic Applied Computer Vision and Pattern Recognition)
Large amounts of high-quality image data are the basis and premise of the high accuracy detection of objects in the field of convolutional neural networks (CNN). It is challenging to collect various high-quality ship image data based on the marine environment. A novel method based on CNN is proposed to generate a large number of high-quality ship images to address this. We obtained ship images with different perspectives and different sizes by adjusting the ships’ postures and sizes in three-dimensional (3D) simulation software, then 3D ship data were transformed into 2D ship image according to the principle of pinhole imaging. We selected specific experimental scenes as background images, and the target ships of the 2D ship images were superimposed onto the background images to generate “Simulation–Real” ship images (named SRS images hereafter). Additionally, an image annotation method based on SRS images was designed. Finally, the target detection algorithm based on CNN was used to train and test the generated SRS images. The proposed method is suitable for generating a large number of high-quality ship image samples and annotation data of corresponding ship images quickly to significantly improve the accuracy of ship detection. The annotation method proposed is superior to the annotation methods that label images with the image annotation software of Label-me and Label-img in terms of labeling the SRS images. View Full-Text
Keywords: SRS images; data augmentation; convolutional neural networks; target detection; image annotation SRS images; data augmentation; convolutional neural networks; target detection; image annotation
Show Figures

Figure 1

MDPI and ACS Style

You, J.; Hu, Z.; Peng, C.; Wang, Z. Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing. Appl. Sci. 2021, 11, 5931. https://doi.org/10.3390/app11135931

AMA Style

You J, Hu Z, Peng C, Wang Z. Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing. Applied Sciences. 2021; 11(13):5931. https://doi.org/10.3390/app11135931

Chicago/Turabian Style

You, Ji’an, Zhaozheng Hu, Chao Peng, and Zhiqiang Wang. 2021. "Generation and Annotation of Simulation-Real Ship Images for Convolutional Neural Networks Training and Testing" Applied Sciences 11, no. 13: 5931. https://doi.org/10.3390/app11135931

Find Other Styles
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Back to TopTop