Enhanced-HisSegNet: Improved SAR Image Flood Segmentation with Learnable Histogram Layers and Active Contour Model

Synthetic Aperture Radar (SAR) imagery plays a vital role in identifying flooded areas in the aftermath causing loss of life and significant economic and environmental damage, as water surfaces reflect less microwave energy compared to land due to their smooth texture and low surface roughness. In this study, we present a multimodal fusion strategy that enhances the existing model introduced in [1] through an integration of histogram extraction layers designed for SAR data with Active Contour Models (ACMs), which are integrated into fine-tuned Deep Segmentation Neural Networks (DSNNs). The model was tested on a real SAR dataset, with cross-dataset validation using an external cohort, representing a second innovation in our approach. Experimental results demonstrate that our model, with histogram layers + ACM, outperforms previous approaches by up to 10% in internal and 4% in external cohorts as intersection over union (IoU) and provides a comprehensive evaluation through metrics like Accuracy and Loss.

合成孔径雷达（Synthetic Aperture Radar，SAR）影像在灾后洪涝区域识别中发挥着至关重要的作用——洪涝灾害往往会造成人员伤亡以及严重的经济与环境破坏，这是由于水面相较于陆地质地更为平滑、表面粗糙度更低，故而反射的微波能量远少于陆地。本研究提出一种多模态融合策略：通过将专为SAR数据设计的直方图提取层与主动轮廓模型（Active Contour Models，ACMs）相集成，并将二者嵌入经微调的深度分割神经网络（Deep Segmentation Neural Networks，DSNNs）中，以此优化[1]中提出的现有模型。本研究采用真实SAR数据集对所提模型进行测试，并借助外部测试队列开展跨数据集验证，此为本研究的第二项创新之处。实验结果表明，搭载直方图提取层与主动轮廓模型的所提模型，在内部测试队列与外部测试队列中的交并比（Intersection over Union，IoU）相较于既往方法分别最高提升10%与4%，并通过准确率、损失值等指标完成了全面的性能评估。