Monitoring the Sewage Draining in Shenzhen Reservoirs Using Hyperspectral Data

Freshwater resources are regarded as the foundation of urban development and assure the sustainable prosperity of the city. The contaminations of fresh water in reservoirs can threaten safety of people directly and force the Industrial processes to be suspended. Therefore, developing a method to detect the potential locations where contaminated water drains off into the reservoirs efficiently and precisely is a challenging task but in urgent need. In this research, we used the air-borne sensor Hymap to get the hyperspectral data of Shenzhen. Finally we find a way to invert five water quality parameters (Suspended Solid (SS), Total Nitrogen (TN), Total Phosphorus (TP), Chemical Oxygen Demand (COD), Biochemical Oxygen Demand (BOD5)) from the Hymap image and we distinguish the clear water and polluted water on the image successfully.

基于注意力金字塔网络的航空影像建筑物变化检测

针对遥感图像语义分割中存在对多尺度目标的漏检和分割边界粗糙等问题,提出了一种基于注意力金字塔网络的航空影像建筑物变化检测方法。该方法采用编码-解码结构,在编码阶段使用ResNet101作为基础网络来提取特征,并在部分残差模块应用空洞卷积增大感受野,同时将金字塔池化结构作为编码网络的最后一层,以提取图像多尺度特征;在解码阶段的横向连接过程中引入注意力机制以突出重要特征,并采用自上而下的密集连接方式计算特征金字塔,有效融合不同阶段、不同分辨率的特征。在大型建筑物变化检测数据集上进行验证实验,实验结果表明所提方法在对不同尺寸建筑物目标的变化检测中展现出了良好的适应性,相比于经典语义分割网络具有一定的优势。