WaveletUMamba: a frequency-enhanced state space model for extraction of multi-stage celery planting areas from UAV imagery.

In the task of extracting celery cultivation areas across different growth stages from high-resolution UAV remote sensing imagery, the original Mamba model exhibits a bias toward low-frequency information during state-space modeling and responds relatively poorly to high-frequency details such as boundaries and textures, thereby affecting its ability to characterize fine-grained spatial structures in complex scenes. To address this issue, this paper proposes a WaveletUMamba network that integrates frequency-domain enhancement with state-space modeling. First, a Low-Frequency Masking High-Frequency Enhancer (LFM-HFE) was designed to enhance high-frequency information-such as edges and textures-based on two-dimensional Haar wavelet decomposition, thereby compensating for the state-space model's shortcomings in modeling local details. Second, a Dual-Gated Frequency-Spatial State-Space Module (DG-SSM) was constructed to achieve the synergistic fusion of high-frequency detail features with the global state-space modeling process, thereby enhancing the model's ability to represent complex spatial structures. Finally, to mitigate category confusion caused by similar textural and spectral features across different growth stages, a Context-Guided Feature Supervision module (CGFS) was designed to enhance the discriminative power and consistency of intermediate layer features through global semantic constraints. Experimental results show that this method achieves 88.70% and 93.90% for the mIoU and mF1 metrics, respectively-representing improvements of 1.07% and 0.30% over the second-best model, UNetMamba-while striking an optimal balance between extraction accuracy and computational efficiency. Ablation experiments and visualization results further validate the effectiveness of each module. The WaveletUMamba framework proposed in this paper offers a new methodological approach for the precise extraction of crop planting areas across multiple growth stages in complex open-field agricultural environments, while also providing a technical solution for the practical application of UAV remote sensing technology in extracting crop planting areas.