Aerial imagery can be used for important work on a global scale. Nevertheless, the analysis of this data using neural network architectures lags behind the current state-of-the-art on popular datasets such as PASCAL VOC, CityScapes and Camvid. In this paper we bridge the performance-gap between these popular datasets and aerial imagery data. Little work is done on aerial imagery with state-of-the-art neural network architectures in a multi-class setting. Our experiments concerning data augmentation, normalisation, image size and loss functions give insight into a high performance setup for aerial imagery segmentation datasets. Our work, using the state-of-the-art DeepLabv3+ Xception65 architecture, achieves a mean IOU of 70% on the DroneDeploy validation set. With this result, we clearly outperform the current publicly available state-of-the-art validation set mIOU (65%) performance with 5%. Furthermore, to our knowledge, there is no mIOU benchmark for the test set. Hence, we also propose a new benchmark on the DroneDeploy test set using the best performing DeepLabv3+ Xception65 architecture, with a mIOU score of 52.5%.
翻译:然而,使用神经网络结构对这些数据的分析落后于目前流行数据集的最新性能设置,如PASAL VOC、CityScapes和Camvid。在本文中,我们将这些流行数据集和航空图像数据之间的性能差距连接起来。在多级环境下,用最新神经网络结构对航空图像做的工作很少。我们关于数据增强、正常化、图像大小和损失功能的实验揭示了空中图像分离数据集的高性能设置。我们使用目前最先进的DeepLab3+Xcepion65 结构开展的工作,在DrooneDeplove验证数据集中实现了70 % 的平均IOU值。因此,我们明显地超越了目前公开提供的最新神经网络结构 mIOU(65%) 的性能5%。此外,据我们了解,测试数据集没有 mIOUU基准。因此,我们还提议在DrooneDrove3 测试中采用一个新的基准,在Dregone-Droib3 上进行一个新的IDroveB3号测试。