Frequency-Adaptive Boundary-Guided Network for Multiclass Raft Aquaculture Segmentation in Remote Sensing Images

Accurate segmentation of multiclass raft aquaculture areas (RAAs) from high-resolution remote sensing images is challenging due to spectral similarity across classes, boundary ambiguity caused by complex marine conditions, and intraregion inconsistency. To address these challenges, this letter proposes PBFANet, a deep segmentation network that integrates boundary guidance and frequency-adaptive filtering mechanisms. A gated boundary–semantic fusion module (GBSFM) dynamically combines pseudo-boundary cues with semantic features to enhance edge localization, while the consistency-aware fusion module (CAFM) employs an adaptive low-pass filter (LPF) and a high-pass filter (HPF) to suppress intraregion noise and restore boundary details. Notably, CAFM leverages the distinct frequency-domain characteristics of different aquaculture classes—such as dense high-frequency textures in laver areas and low-frequency dominance in fish cage regions—to improve class separability. Experiments on GF-1 satellite imagery covering laver, hijiki, and fish cages demonstrate that PBFANet achieves a mean ${F}1$ -score of 0.914 and a mean intersection over union (mIoU) of 82.78%, outperforming state-of-the-art methods in classification accuracy, boundary precision, and segmentation consistency.