FGSC-23: a large-scale dataset of high-resolution optical remote sensing image for deep learning-based fine-grained ship recognition

Libo Yao; Xiaohan Zhang; Yafei Lyu; Weiwei Sun; Mengyang Li

doi:10.11834/jig.200261

Dataset | Views : 0 下载量: 312 CSCD: 3

PDF
Export
Share
Collection
Album

FGSC-23: a large-scale dataset of high-resolution optical remote sensing image for deep learning-based fine-grained ship recognition
Vol. 26, Issue 10, Pages: 2337-2345(2021)
Received：17 June 2020，

Revised：2020-8-31，

Accepted：07 September 2020，

Published：16 October 2021
DOI： 10.11834/jig.200261
稿件说明：

移动端阅览

DOI：

Libo Yao, Xiaohan Zhang, Yafei Lyu, Weiwei Sun, Mengyang Li. FGSC-23: a large-scale dataset of high-resolution optical remote sensing image for deep learning-based fine-grained ship recognition[J]. Journal of Image and Graphics, 2021, 26(10): 2337-2345. DOI： 10.11834/jig.200261.

摘要

目的

基于光学遥感图像的舰船目标识别研究广受关注，但是目前公开的光学遥感图像舰船目标识别数据集存在规模小、目标类别少等问题，难以训练出具有较高舰船识别精度的深度学习模型。为此，本文面向基于深度学习的舰船目标精细识别任务研究需求，搜集公开的包含舰船目标的高分辨率谷歌地球和GF-2卫星水面场景遥感图像，构建了一个高分辨率光学遥感图像舰船目标精细识别数据集（fine-grained ship collection-23，FGSC-23）。

方法

将图像中的舰船目标裁剪出来，制作舰船样本切片，人工对目标类别进行标注，并在每个切片中增加舰船长宽比和分布方向两类属性标签，最终形成包含23个类别、4 052个实例的舰船目标识别数据集。

结果

按1：4比例将数据集中各类别图像随机划分为测试集和训练集，并展开验证实验。实验结果表明，在通用识别模型识别效果验证中，VGG16（Visual Geometry Group 16-layer net）、ResNet50、Inception-v3、DenseNet121、MobileNet和Xception等经典卷积神经网络（convolutional neural network，CNN）模型的整体测试精度分别为79.88%、81.33%、83.88%、84.00%、84.24%和87.76%；在舰船目标精细识别的模型效果验证中，以VGG16和ResNet50模型为基准网络，改进模型在测试集上的整体测试精度分别为93.58%和93.09%。

结论

构建的FGSC-23数据集能够满足舰船目标识别算法的验证任务。

Abstract

Objective

Maritime activities are quite important to human society as they influence economic and social development. Thus

maintaining marine safety is of great significance to promoting social stability. As the main vehicle of marine activities

numerous ships of varying types cruise the sea daily. The fine-grained classification of ships has become one of the basic technologies for marine surveillance. With the development of remote sensing technology

satellite optical remote sensing is becoming one of the main means for marine surveillance due to its wide coverage

low acquisition cost

reliability

and real-time monitoring. As a result

ship classification through optical remote sensing images has attracted the attention of researchers. For the image target recognition task in computer vision

deep learning-based methods outperform traditional methods based on handcrafted features due to the powerful representation ability of convolutional neural networks. Thus

it is natural to combine deep learning technology and ship classification task in optical remote sensing images. However

most deep learning-based algorithms are data-driven

which rely on well-annotated large-scale datasets. To date

problems of small amount of data and few target categories exist in public ship classification datasets with optical remote sensing

which cannot meet the requirements of studies on deep learning-based ship classification tasks

especially the fine-grained ship classification task.

Method

On the basis of the above analysis and requirements

a fine-grained ship collection named FGSC-23 with high-resolution optical remote sensing images is established in this study. There are a total of 4 052 instance chips and 23 categories of targets including 22-category ships and 1-category negative samples in FGSC-23. All the images are obtained from public images of Google Earth and GF-2 satellite

and the ship chips are split from these images. All the ships are labeled by human interpretation. Except for the category labels

the attributes of ship aspect ratio and the angle between the ship's central axis and image's horizontal axis are also annotated. To our knowledge

FGSC-23 contains more fine-grained categories of ships compared with the public datasets. Thus

it can be used for fine-grained ship classification research. Overall

FGSC-23 shares the properties of category diversity

imaging scene diversity

instance label diversity

and category imbalance.

Result

Experiments are conducted on the constructed FGSC-23 to test the classification accuracy of classical convolutional neural networks. FGSC-23 is divided into a testing set and training set with a ratio of about 1:4. Models including VGG16(Visual Geometry Group 16-layer net)

ResNet50

Inception-v3

DenseNet121

MobileNet

and Xception are trained using the training set and tested on the testing set. The accuracy rate of each category and the overall accuracy rate are recorded

and the visualization of confusion matrixes of the classification results is also given. The overall accuracies of these models are 79.88%

81.33%

83.88%

84.00%

84.24%

and 87.76%

respectively. Besides these basic classification models

an optimizing model using the ship's attribute feature and enhanced multi-level local features is also tested on FGSC-23. A state-of-the-art classification performance is achieved as 93.58%.

Conclusion

The experimental results show that the constructed FGSC-23 can be used to verify the effectiveness of deep learning-based ship classification methods for optical remote sensing images. It is also helpful to promote the development of related researches.

关键词

Keywords

references

Beamer L J, Carroll S F and Eisenberg D. 1998. The BPI/LBP family of proteins: a structural analysis of conserved regions. Protein Science, 7(4): 906-914[DOI: 10.1002/pro.5560070408]

Chollet F. 2017. Xception: deep learning with depthwise separable convolutions//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 1800-1807[ DOI: 10.1109/CVPR.2017.195 http://dx.doi.org/10.1109/CVPR.2017.195 ]

Gallego A J, Pertusa A and Gil P. 2018. Automatic ship classification from optical aerial images with convolutional neural networks. Remote Sensing, 10(4): #511[DOI: 10.3390/rs10040511]

He K M, Zhang X Y, Ren S Q and Sun J. 2016. Deep residual learning for image recognition//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, USA: IEEE: 770-778[ DOI: 10.1109/CVPR.2016.90 http://dx.doi.org/10.1109/CVPR.2016.90 ]

Howard A G, Zhu M L, Chen B, Kalenichenko D, Wang W J, Weyand T, Andreetto M and Adam H. 2017. MobileNets: efficient convolutional neural networks for mobile vision applications[EB/OL]. [2020-05-17] . https://arxiv.org/pdf/1704.04861.pdf https://arxiv.org/pdf/1704.04861.pdf

Huang G, Liu Z, Van Der Maaten L and Weinberger K Q. 2017. Densely connected convolutional networks//Proceedings of 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, USA: IEEE: 2261-2269[ DOI: 10.1109/CVPR.2017.243 http://dx.doi.org/10.1109/CVPR.2017.243 ]

Jiang D D, Xu Z L and Li K D. 2004. Surface ship target recognition research based on SGA. Engineering Science, 6(8): 79-81

蒋定定, 许兆林, 李开端. 2004. 应用基本遗传算法进行水面舰船目标识别研究. 中国工程科学, 6(8): 79-81 [DOI: 10.3969/j.issn.1009-1742.2004.08.015]

Li J W, QuC W and Peng S J. 2018. Ship classification for unbalanced SAR dataset based on convolutional neural network. Journal of Applied Remote Sensing, 12(3): #035010[DOI: 10.1117/1.JRS.12.035010]

Li N and Liu F. 2012. A SAR target recognition method based on view-aspects partitioned by fuzzy clustering. Acta Electronica Sinica, 40(2): 394-399

李娜, 刘方. 2012. 基于模糊聚类视区划分的SAR目标识别方法. 电子学报, 40(2): 394-399 [DOI: 10.3969/j.issn.0372-2112.2012.02.030]

Liu Z K, Yuan L and Weng L B. 2017. A high resolution optical satellite image dataset for ship recognition and some new baselines//Proceedings of the 6th International Conference on Pattern Recognition Applications and Methods (ICPRAM). Porto, Portugal: SCITEPRESS-Science and Technology Pubications[ DOI: 10.5220/0006120603240331 http://dx.doi.org/10.5220/0006120603240331 ]

Lowe D G. 2004. Distinctive image features from scale-invariant keypoints. International Journal of Computer Vision, 60(2): 91-110[DOI: 10.1023/B:VISI.0000029664.99615.94]

Rainey K and Stastny J. 2011. Object recognition in ocean imagery using feature selection and compressive sensing//Proceedings of 2011 IEEE Applied Imagery Pattern Recognition Workshop (AIPR). Washington, USA: IEEE: 1-6[ DOI: 10.1109/AIPR.2011.6176352 http://dx.doi.org/10.1109/AIPR.2011.6176352 ]

Shi Q Q, Li W and Tao R. 2018. 2D-DFrFT based deep network for ship classi? cation in remote sensing imagery//Proceedings of the 10th IAPR Workshop on Pattern Recognition in Remote Sensing (PRRS). Beijing, China: IEEE: 1-5[ DOI: 10.1109/PRRS.2018.8486413 http://dx.doi.org/10.1109/PRRS.2018.8486413 ]

Shi Q Q, Li W, Tao R, Sun X and Gao L R. 2019. Ship classification based on multifeature ensemble with convolutional neural network. Remote Sensing, 11(4): #419[DOI: 10.3390/rs11040419]

Shi W J, Wang X P and Wang D W. 2009. Alongshore ship detection based on D-S evidence theory. Electronics Optics and Control, 16(11): 87-91

石文君, 汪小平, 王登位. 2009. 基于D-S证据理论的近岸舰船目标识别. 电光与控制, 16(11): 87-91 [DOI: 10.3969/j.issn.1671-637X.2009.11.024]

Simonyan K and Zisserman A. 2015. Very deep convolutional networks for large-scale image recognition[EB/OL]. [2020-05-17] . https://arxiv.org/pdf/1409.1556v6.pdf https://arxiv.org/pdf/1409.1556v6.pdf

Szegedy C, Vanhoucke V, Ioffe S, Shlens J and Wojna Z. 2016. Rethinking the inception architecture for computer vision//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, USA: IEEE: 2818-2826[ DOI: 10.1109/CVPR.2016.308 http://dx.doi.org/10.1109/CVPR.2016.308 ]

Zhang X H, Lv Y F, Yao L B, Xiong W and Fu C L. 2020. A new benchmark and an attribute-guided multilevel feature representation network for fine-grained ship classification in optical remote sensing images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 13: 1271-1285[DOI:10.1109/JSTARS.2020.2981686]

Alert me when the article has been cited

提交

Review of deep learning algorithms for small object detection in optical remote sensing images

Survey of anomaly detection methods in surveillance videos based on deep learning

Large-scale datasets for facial tampering detection with inpainting techniques

Research progress on fetal brain magnetic resonance image segmentation