In this paper, we provide an innovative contribution in the research domain dedicated to crop mapping by exploiting the of Sentinel-2 satellite images time series, with the specific aim to extract information on “where and when” crops are grown. The final goal is to set up a workflow able to reliably identify (classify) the different crops that are grown in a given area by exploiting an end-to-end (3+2)D convolutional neural network (CNN) for semantic segmentation. The method also has the ambition to provide information, at pixel level, regarding the period in which a given crop is cultivated during the season. To this end, we propose a solution called Class Activation Interval (CAI) which allows us to interpret, for each pixel, the reasoning made by CNN in the classification determining in which time interval, of the input time series, the class is likely to be present or not. Our experiments, using a public domain dataset, show that the approach is able to accurately detect crop classes with an overall accuracy of about 93% and that the network can detect discriminatory time intervals in which crop is cultivated. These results have twofold importance: (i) demonstrate the ability of the network to correctly interpret the investigated physical process (i.e., bare soil condition, plant growth, senescence and harvesting according to specific cultivated variety) and (ii) provide further information to the end-user (e.g., the presence of crops and its temporal dynamics).

中文翻译：

---

带有 3D 特征金字塔网络和时域类激活间隔的 Sentinel 2 时间序列分析用于作物映射

在本文中，我们通过利用 Sentinel-2 卫星图像时间序列在致力于作物制图的研究领域做出了创新贡献，其具体目的是提取有关作物种植“地点和时间”的信息。最终目标是建立一个工作流程，通过利用端到端 (3+2)D 卷积神经网络 (CNN) 进行语义分割，能够可靠地识别（分类）给定区域内种植的不同作物。该方法还希望在像素级别提供有关特定作物在该季节种植的时间段的信息。为此，我们提出了一种称为类激活间隔 (CAI) 的解决方案，它允许我们为每个像素解释 CNN 在确定输入时间序列的哪个时间间隔的分类中所做的推理，班级可能存在或不存在。我们使用公共领域数据集进行的实验表明，该方法能够以大约 93% 的总体准确率准确检测作物类别，并且网络可以检测作物种植的区分时间间隔。这些结果具有双重重要性：(i) 证明了网络正确解释所调查物理过程的能力（即，根据特定栽培品种的裸露土壤条件、植物生长、衰老和收获）和 (ii) 为研究人员提供进一步的信息。最终用户（例如，作物的存在及其时间动态）。表明该方法能够以大约 93% 的总体准确率准确检测作物类别，并且该网络可以检测作物种植的区分时间间隔。这些结果具有双重重要性：(i) 证明了网络正确解释所调查物理过程的能力（即，根据特定栽培品种的裸露土壤条件、植物生长、衰老和收获）和 (ii) 为研究人员提供进一步的信息。最终用户（例如，作物的存在及其时间动态）。表明该方法能够以大约 93% 的总体准确率准确检测作物类别，并且该网络可以检测作物种植的区分时间间隔。这些结果具有双重重要性：(i) 证明了网络正确解释所调查物理过程的能力（即，根据特定栽培品种的裸露土壤条件、植物生长、衰老和收获）和 (ii) 为研究人员提供进一步的信息。最终用户（例如，作物的存在及其时间动态）。