Yu Haomiao, Hou Yingzi, Wang Fangxiong, Wang Junfu, Zhu Jianfeng, Guo Jianke
School of Geographical Sciences, Liaoning Normal University, Dalian 116029, China.
Liaoning Provincial Key Laboratory of Physical Geography and Geomatics, Liaoning Normal University, Dalian 116029, China.
Sensors (Basel). 2024 Aug 12;24(16):5220. doi: 10.3390/s24165220.
Accurately extracting large-scale offshore floating raft aquaculture (FRA) areas is crucial for supporting scientific planning and precise aquaculture management. While remote sensing technology offers advantages such as wide coverage, rapid imaging, and multispectral capabilities for FRA monitoring, the current methods face challenges in terms of establishing spatial-spectral correlations and extracting multiscale features, thereby limiting their accuracy. To address these issues, we propose an innovative multiscale spatial-spectral fusion network (MSSFNet) designed specifically for extracting offshore FRA areas from multispectral remote sensing imagery. MSSFNet effectively integrates spectral and spatial information through a spatial-spectral feature extraction block (SSFEB), significantly enhancing the accuracy of FRA area identification. Additionally, a multiscale spatial attention block (MSAB) captures contextual information across different scales, improving the ability to detect FRA areas of varying sizes and shapes while minimizing edge artifacts. We created the CHN-YE7-FRA dataset using Sentinel-2 multispectral remote sensing imagery and conducted extensive evaluations. The results showed that MSSFNet achieved impressive metrics: an F1 score of 90.76%, an intersection over union (IoU) of 83.08%, and a kappa coefficient of 89.75%, surpassing those of state-of-the-art methods. The ablation results confirmed that the SSFEB and MSAB modules effectively enhanced the FRA extraction accuracy. Furthermore, the successful practical applications of MSSFNet validated its generalizability and robustness across diverse marine environments. These findings highlight the performance of MSSFNet in both experimental and real-world scenarios, providing reliable, precise FRA area monitoring. This capability provides crucial data for scientific planning and environmental protection purposes in coastal aquaculture zones.
准确提取大规模近海浮筏式水产养殖（FRA）区域对于支持科学规划和精确的水产养殖管理至关重要。虽然遥感技术在FRA监测方面具有覆盖范围广、成像速度快和多光谱能力等优势，但目前的方法在建立空间-光谱相关性和提取多尺度特征方面面临挑战，从而限制了其准确性。为了解决这些问题，我们提出了一种创新的多尺度空间-光谱融合网络（MSSFNet），专门用于从多光谱遥感影像中提取近海FRA区域。MSSFNet通过空间-光谱特征提取模块（SSFEB）有效地整合了光谱和空间信息，显著提高了FRA区域识别的准确性。此外，一个多尺度空间注意力模块（MSAB）捕获不同尺度的上下文信息，提高了检测不同大小和形状的FRA区域的能力，同时最大限度地减少边缘伪影。我们使用哨兵2号多光谱遥感影像创建了CHN-YE7-FRA数据集，并进行了广泛的评估。结果表明，MSSFNet取得了令人印象深刻的指标：F1分数为90.76%，交并比（IoU）为83.08%，kappa系数为89.75%，超过了现有最先进的方法。消融结果证实，SSFEB和MSAB模块有效地提高了FRA提取的准确性。此外，MSSFNet的成功实际应用验证了其在不同海洋环境中的通用性和鲁棒性。这些发现突出了MSSFNet在实验和实际场景中的性能，提供了可靠、精确的FRA区域监测。这种能力为沿海养殖区的科学规划和环境保护目的提供了关键数据。
