Coastal wind turbines operate under severe salt spray, high humidity, and wind-driven erosion, which accelerate coating degradation and corrosion-induced cracking. In such environments, corrosion defects exhibit blurred boundaries, weak textures, and significant scale variations, challenging object detectors in small-target localization and precise boundary regression. To address these limitations, this study proposes CoastCor-Net, an enhanced YOLOv11-based framework that improves spatial–semantic alignment, boundary representation, and channel–spatial dependency modeling. The architecture integrates three complementary modules to enhance boundary sensitivity, spatial–semantic consistency, and cross-channel interaction: a Decoding-Driven Enhancement Block, a Complementary Feature Alignment Module, and a Channel-Transposed Coordinate Attention module. Extensive experiments on the Wind Turbine Blade Damage Dataset show that CoastCor-Net achieves 84.7% mAP@0.5 and 54.1% mAP@0.5:0.95, surpassing YOLOv13n by 3.2 percentage points in mAP@0.5 and improving AP_damage by 5.2 percentage points. The framework also demonstrates strong robustness under composite coastal perturbations. These findings highlight the practical effectiveness of structured multi-level feature enhancement for reliable and high-precision blade inspection in complex coastal environments.
Early forest-fire detection in unmanned aerial vehicle (UAV) imagery is challenged by thin smoke, small flames, low contrast, and complex backgrounds. This paper presents PWM-Net, a computationally efficient detector constructed from a YOLOv11n baseline. PWM-Net replaces the baseline backbone with PartialNet, embeds wavelet convolution (WTConv) in the feature-fusion neck, and introduces a multi-spectral multi-scale (M2S) attention module before the detection heads. The three components respectively improve partial-channel feature extraction, frequency-aware receptive-field modeling, and joint spectral-scale modulation. Across three independent runs, PWM-Net obtains \(81.3\pm0.18\%\) mAP@50 and \(53.7\pm0.22\%\) mAP@50:95 on D-Fire, and \(88.6\pm0.21\%\) mAP@50 and \(70.4\pm0.26\%\) mAP@50:95 on CQ-Fire. The model contains 7·8 M parameters and reaches 145 FPS on an RTX 4090 under batch-one FP32 inference. Ablation and spectral-branch sensitivity analyses indicate complementary contributions from PartialNet, WTConv, and M2S. Embedded-device measurements further demonstrate the deployment efficiency of the model. These results establish a favorable accuracy–efficiency trade-off for UAV-based early forest-fire detection.