任诗曼, 朱军, 方铮, 李闯农, 梁策, 谢亚坤, 李维炼, 张天奕. 联合多尺度注意力机制与边缘约束的SPOT7影像林地提取方法[J]. 武汉大学学报 ( 信息科学版), 2023, 48(12): 1951-1958. DOI: 10.13203/j.whugis20210251
引用本文: 任诗曼, 朱军, 方铮, 李闯农, 梁策, 谢亚坤, 李维炼, 张天奕. 联合多尺度注意力机制与边缘约束的SPOT7影像林地提取方法[J]. 武汉大学学报 ( 信息科学版), 2023, 48(12): 1951-1958. DOI: 10.13203/j.whugis20210251
REN Shiman, ZHU Jun, FANG Zheng, LI Chuangnong, LIANG Ce, XIE Yakun, LI Weilian, ZHANG Tianyi. Woodland Extraction of SPOT7 Image Based on Multi-scale Attention Mechanism and Edge Constraint[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12): 1951-1958. DOI: 10.13203/j.whugis20210251
Citation: REN Shiman, ZHU Jun, FANG Zheng, LI Chuangnong, LIANG Ce, XIE Yakun, LI Weilian, ZHANG Tianyi. Woodland Extraction of SPOT7 Image Based on Multi-scale Attention Mechanism and Edge Constraint[J]. Geomatics and Information Science of Wuhan University, 2023, 48(12): 1951-1958. DOI: 10.13203/j.whugis20210251

联合多尺度注意力机制与边缘约束的SPOT7影像林地提取方法

Woodland Extraction of SPOT7 Image Based on Multi-scale Attention Mechanism and Edge Constraint

  • 摘要: 林地是国家重要的自然资源和经济资源,掌握林地分布状况对林地资源调查管理具有重要意义。针对传统林地提取方法精度较低且边界不规则的问题,设计了一种联合多尺度注意力机制与边缘约束的林地提取方法。首先,构建一种端到端的多尺度注意力神经网络模型,充分提取影像中林地的上下文特征,对不同尺度下的林地进行语义描述,实现高精度的林地像素级表达;其次,构建边缘约束规则,对提取结果进行边界优化,提高林地提取结果的可读性。为证明方法的有效性,以中国四川省绵阳市三台县作为实验区,建立数据集并进行林地提取实验,结果显示,所提方法提取的精确度为81.9%,召回率为75.6%,F1分数为78.1%,交并比为64.2%。结果证明,所提方法在遥感影像林地提取应用上效果良好。

     

    Abstract:
    Objectives As woodland is an important natural and economic resource of China, it is important to understand the distribution of woodland for the investigation and management of woodland resources.We design a woodland extraction method combining multi-scale attention mechanism and edge constraint to tackle the issue of low accuracy and irregular boundaries in traditional forest extraction methods.
    Methods First, an end-to-end multi-scale attentional neural network model is constructed to fully extract the context features of woodland in remote sensing images, and semantically describe woodland at different scales to achieve high-precision pixel-level expression of woodland. Second, the edge constraint rules are constructed to optimize the boundary of the extraction results, to improve the readability of the extraction results. To prove the effectiveness of the proposed method, Santai County, Mianyang City, Sichuan Province, China is taken as the experimental area to establish datasets and carry out woodland extraction experiments.
    Results The results show that the extraction accuracy of this method is 81.9%, the recall rate is 75.6%, F1 score is 78.1%, intersection of union is 64.2%.
    Conclusions The propsed method has a better effect in the application of woodland extraction with remote sensing image.

     

/

返回文章
返回