V-RSIR: An Open Access Web-Based Image Annotation Tool for Remote Sensing Image Retrieval
V-RSIR: An Open Access Web-Based Image Annotation Tool for Remote Sensing Image Retrieval
复制标题
DOI：
10.1109/access.2019.2924933
复制
发表时间：
2019-06
期刊：
影响因子：
3.9
通讯作者：
Dongyang Hou;Z. Miao;H. Xing;Hao Wu
中科院分区：
文献类型：
--
作者：
Dongyang Hou;Z. Miao;H. Xing;Hao Wu
基准数据集在评估遥感图像检索（RSIR）方法中发挥着重要作用。目前，RSIR 的几个小规模基准数据集已在网络上公开提供，并且大多数是通过 Google Map API 或其他桌面工具收集的。由于Google Map API要求用户具备编程技能，而其他采集工具不公开，这可能会限制广泛的志愿者参与生成大规模基准数据集的可能性。为了应对这一挑战，我们开发了一个基于网络的开放访问工具 V-RSIR，使志愿者能够轻松参与生成 RSIR 新的基准数据集。这个基于网络的工具不仅方便了遥感图像的标注和裁剪，还提供了图像编辑、审阅、数量统计、空间分布、共享等功能。为了验证该工具，我们招募了 32 名志愿者，使用该工具对遥感图像进行标记和裁剪。最后，创建一个新的基准数据集，其中包含 38 个类，每个类至少有 1500 张图像。然后，通过五种手工制作的低级特征方法和四种深度学习高级特征方法对新数据集进行验证。实验结果表明，手工设计的低级特征方法的性能比深度学习方法差，其中前 5 名的精度可以达到 94%。评估结果与我们的理论理解和PatternNet数据集上的实验结果一致。这表明我们的网络工具可以帮助用户与 RSIR 志愿者一起生成有效的基准数据集。
Benchmark datasets play an important role in evaluating remote sensing image retrieval (RSIR) methods. At present, several small-scale benchmark datasets for RSIR are publicly available on the web and are mostly collected through the Google Map API or other desktop tools. Because the Google Map API requires the users to have programming skills and other collection tools are not publicly available, this may limit the possibility for a wide range of volunteers to participate in generating large-scale benchmark datasets. To address this challenge, we develop an open access web-based tool V-RSIR that allows volunteers to easily participate in generating new benchmark datasets for RSIR. This web-based tool not only facilitates the remote sensing image label and cropping, but also provides image editing, review, quantity statistics, spatial distribution, sharing, and so on. To validate this tool, we recruit 32 volunteers to label and crop remote sensing images by using the tool. Finally, a new benchmark dataset that contains 38 classes with at least 1500 images per class is created. Then, the new dataset is validated by five handcrafted low-level feature methods and four deep learning high-level feature methods. The experimental results show that the handcrafted low-level feature methods perform worse than the deep learning methods, in which the precision at top 5 can achieve 94%. The evaluation results are consistent with our theoretical understanding and experimental results on the PatternNet dataset. This indicates that our web-based tool can help users generating valid benchmark datasets with volunteers for the RSIR.