论文标题
实例段的建筑高度预测
Building Height Prediction with Instance Segmentation
论文作者
论文摘要
从卫星图像中提取建筑高度是一个活跃的研究领域，用于许多领域，例如电信，城市规划等。许多研究利用了用激光雷达或立体声图像生成的DSM（数字表面模型）为此目的。由于数据量不足，数据质量低，建筑物类型的变化，光和阴影的不同角度等，仅使用RGB图像来预测建筑物的高度，这具有挑战性。在这项研究中，我们提出了一种基于实例的基于分段的建筑物高度提取方法，可以预测来自单个RGB卫星图像的建筑物掩护及其各自的高度。我们使用了带有某些城市的建筑高度注释以及带有转移学习方法的开源卫星数据集的卫星图像。我们到达了，在我们的测试集中，属于每个高度类别的建筑物的界限框图59，蒙版映射52.6和70％的平均准确性值为70％。
Extracting building heights from satellite images is an active research area used in many fields such as telecommunications, city planning, etc. Many studies utilize DSM (Digital Surface Models) generated with lidars or stereo images for this purpose. Predicting the height of the buildings using only RGB images is challenging due to the insufficient amount of data, low data quality, variations of building types, different angles of light and shadow, etc. In this study, we present an instance segmentation-based building height extraction method to predict building masks with their respective heights from a single RGB satellite image. We used satellite images with building height annotations of certain cities along with an open-source satellite dataset with the transfer learning approach. We reached, the bounding box mAP 59, the mask mAP 52.6, and the average accuracy value of 70% for buildings belonging to each height class in our test set.
