Process-Oriented Change Detection Network Based on Discrete Wavelet Transform

Abstract

Change detection (CD) network for process-oriented model design improves detection efficiency through more complete time modeling. However, the networks accumulated by convolutional operations are limited by the localization of convolutional kernels, resulting in limited perception of spatiotemporal relationships. Therefore, in this letter, a process-oriented CD network based on discrete wavelet transform is proposed by combining the frequency-domain information in the convolutional network. Specifically, the network constructs a dual-time image into a multiframe video stream through video modeling and extracts the change features of different scales, frequencies, and directions in video and image features from the frequency-domain perspective with the help of discrete wavelet transform, which enhances the perception of spatiotemporal relationships. Experimental results on the LEVIR-CD, GVLM-CD, and EGY-BCD datasets validate the effectiveness of the network.