基于神经网络的遥感图像变化检测系统

Change detection system of remote sensing images based on neural network

变化检测是计算机视觉领域极具研究价值的技术分支。为提高长江沿岸生产建设活动的监管效率,以影像配准为基础,结合自注意力与特征信息提取,提出了长江沿岸建筑物变化检测系统。该系统集影像处理、影像配准、变化检测为一体,实现了全流程自动化处理的功能。结果表明:①设计的系统在影像配准上将精度误差控制在2个像素内,达到了像素级精度。②该系统在变化检测测试数据集上的F 1值取得了优于75%的结果,证明该系统的精度较高。研究成果也可应用于大型水库岸线保护监测等场景中,提升库区治理管理的效率。

Change detection is a highly valuable research branch in the field of computer vision.In order to improve the monitoring efficiency of production and construction activities along the Changjaing River,a building change detection system along the Chanjiang River was proposed on the basis of image registration,combined with self-attention and feature extraction.It integrated image processing,image registration and change detection,achieving automatic operation across overall processes.The results show that the designed system minimizes the registration accuracy error within two pixels,achieving pixel-level accuracy.Moreover,the system achieves a result of more than 75%in terms of F 1 score on the proposed change detection test dataset,demonstrating its high accuracy.The research can be further applied in the shoreline management of large reservoirs,improving the efficiency of governance of reservoirs.