Current Issue Cover
FGSC-23:面向深度学习精细识别的高分辨率光学遥感图像舰船目标数据集

姚力波1, 张筱晗1, 吕亚飞2, 孙炜玮1, 李孟洋1(1.海军航空大学信息融合研究所, 烟台 264001;2.91977部队, 北京 100036)

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

Yao Libo1, Zhang Xiaohan1, Lyu Yafei2, Sun Weiwei1, Li Mengyang1(1.Information Fusion Institute, Naval Aviation University, Yantai 264001, China;2.Troops of 91977, Beijing 100036, China)

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.
Keywords

订阅号|日报