Remote Sensing VQA - High Resolution (RSVQA HR)
收藏资源简介：
Remote sensing images contain a wealth of information which can be useful for a wide range of tasks including land cover classification, object counting or detection. However, most of the available methodologies are task-specific, thus inhibiting generic and easy access to the information contained in remote sensing data. As a consequence, accurate remote sensing product generation still requires expert knowledge. With RSVQA, we propose a system to extract information from remote sensing data that is accessible to every user: we use questions formulated in natural language and use them to interact with the images. With the system, images can be queried to obtain high level information specific to the image content or relational dependencies between objects visible in the images. Using an automatic method, we built two datasets (using low and high resolution data) of image/question/answer triplets. The information required to build the questions and answers is queried from OpenStreetMap (OSM). The datasets can be used to train (when using supervised methods) and evaluate models to solve the RSVQA task. This page is about the high resolution dataset.
遥感影像蕴含丰富信息，可广泛应用于土地覆盖分类、目标计数与检测等诸多任务。然而当前主流方法多为任务特定型，这阻碍了对遥感数据所含信息的通用化、便捷化获取。正因如此，精准生成遥感产品仍需依托专业知识。 为此我们提出遥感视觉问答（RSVQA）系统，用于从遥感数据中提取所有用户均可便捷访问的信息：我们通过自然语言编写问题，并以此与影像进行交互。借助该系统，用户可通过查询影像，获取与影像内容相关的高层信息，或是影像中可见目标间的关联关系。 我们通过自动化方法，基于高、低分辨率数据构建了两组包含「影像-问题-答案」三元组的数据集。生成问答所需的信息均从开放街道地图（OpenStreetMap，OSM）中提取。该数据集可用于训练（采用监督学习方法时）与评估模型，以完成RSVQA任务。 本页面聚焦于高分辨率数据集。
