Clustering Algorithm of Remote Sensing Image Change Detection Based on Improved U-Net Network

Disaster assessment, urban planning and environmental monitoring urgently need to be combined with remote sensing image change detection to play a role. An improved U-Net network combined with clustering algorithm is proposed for remote sensing image change detection. In this paper, firstly, the U-Net network is improved to enhance its feature extraction ability. Next, this paper takes the improved U-Net output feature map as the input of clustering algorithm, and uses K-means clustering algorithm, density-based noisy application spatial clustering (DBSCAN) and Mean Shift clustering to process the change detection results. The final experimental results show that the improved U-Net network combined with K-means algorithm has achieved remarkable performance improvement in remote sensing image change detection, with the maximum OA of 98%, the maximum Kappa coefficient of 0.94 and the maximum BAI of 0.98.