An attention-based U-Net for detecting deforestation within satellite sensor imagery
An attention-based U-Net for detecting deforestation within satellite sensor imagery
复制标题
DOI：
10.1016/j.jag.2022.102685
复制
发表时间：
2022-01-18
影响因子：
7.5
通讯作者：
Zhang, Ce
中科院分区：
文献类型：
--
作者：
John, David;Zhang, Ce
在本文中，我们使用Sentinel-2卫星传感器图像实现并分析了用于语义分割的Attention U-Net深度网络，目的是检测南美洲两个森林生物群落（亚马逊雨林和大西洋森林）内的森林砍伐。将Attention U-Net的性能与U-Net、Residual U-Net、ResNet 50-SegNet和FCN 32-VGG 16在三个不同的数据集（三波段Amazon、四波段Amazon和大西洋森林）上进行了比较。结果表明，在每个数据集上测试时，Attention U-Net提供了最佳的森林砍伐掩模，每个数据集的平均像素F1分数分别为0.9550，0.9769和0.9461。还分析了每个分类器的掩模复制，表明与地面参考相比，Attention U-Net可以比U-Net更准确地检测非森林多边形，总体而言，与基准方法相比，它提供了最准确的森林/毁林分割，尽管其复杂性和训练时间降低，因此是Attention U-Net首次应用于重要的毁林分割任务。本文最后简要讨论了注意力机制抵消注意力U-Net复杂性降低的能力，以及进一步研究优化架构和将注意力机制应用于其他森林砍伐检测架构的想法。
In this paper, we implement and analyse an Attention U-Net deep network for semantic segmentation using Sentinel-2 satellite sensor imagery, for the purpose of detecting deforestation within two forest biomes in South America, the Amazon Rainforest and the Atlantic Forest. The performance of Attention U-Net is compared with U-Net, Residual U-Net, ResNet50-SegNet and FCN32-VGG16 across three different datasets (three-band Amazon, four-band Amazon and Atlantic Forest). Results indicate that Attention U-Net provides the best deforestation masks when tested on each dataset, achieving average pixel-wise F1-scores of 0.9550, 0.9769 and 0.9461 for each dataset, respectively. Mask reproductions from each classifier were also analysed, showing that compared to the ground reference Attention U-Net could detect non-forest polygons more accurately than U-Net and overall it provides the most accurate segmentation of forest/deforest compared with benchmark approaches despite its reduced complexity and training time, thus being the first application of an Attention U-Net to an important deforestation segmentation task. This paper concludes with a brief discussion on the ability of the attention mechanism to offset the reduced complexity of Attention U-Net, as well as ideas for further research into optimising the architecture and applying attention mechanisms into other architectures for deforestation detection.