Cross-Temporal Knowledge Injection With Color Distribution Normalization for Remote Sensing Change Detection

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 18; pp. 6249 - 6265
• Main Authors: Zheng, Wenqi, Yang, Junze, Chen, Jianing, He, Jinlong, Li, Pengfei, Sun, Daobo, Chen, Chuhao, Meng, Xiangxu
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2025; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Accuracy; Attention mechanisms; Change detection; Color; Color alignment; Colour; deep learning; Earth surface; Feature extraction; feature refine; Image color analysis; Image processing; Injection; Knowledge; Perception; Redundancy; Remote sensing; remote sensing change detection; Seasonal variation; Seasonal variations; Semantics; Sensors; Shape; Training; Transformers

Remote sensing change detection plays a critical role in monitoring and identifying alterations on the Earth's surface by comparing images captured at various time intervals. Although existing change detection methods have yielded promising results, challenges such as imaging discrepancies aris...