EUNet-CD: Efficient UNet++ for Change Detection of Very High-Resolution Remote Sensing Images

Abstract

Change detection (CD) is an essential remote sensing application for Earth observations widely used for several monitoring, management, and surveillance-related purposes. Generally, pixel-to-pixel prediction roles are susceptible to position details, as high-resolution bitemporal images contain abundant ground details, and so it needs more precautions to extract features. Recently, various efforts have been made for deep semantic change features, but the importance of grained features has always been ignored, leading to uncertainty of change ground entities. Besides, for an idealistic model, both accuracy and speed need focus. Thus, a novel method EUNet-CD is proposed, based on an efficient nested connection for a robust CD as a remedy for the above issues. The proposed scheme comprises: 1) an efficient convolution module (ECM)-based encoder/decoder to concise the ground entities’ details to minimize the parameters and 2) ultimate fusion strategies (based on spatial/channel attention) act as a repeater to refine the multiscale features and avoid subsampling loss. Experimental validation on different criteria shows the superiority of the proposed EUNet-CD among the state-of-the-arts (SOTA) methods. Our EUNet-CD remarkably improves the overall accuracy and minimizes the computational parameters and time floating point of operations per second (FLOPs) by 33% and 20%.

Topics & Concepts