基于深度学习RCF模型的三都澳筏式养殖区提取研究

刘岳明; 杨晓梅; 王志华; 陆尘

doi:10.3969/j.issn.0253-4193.2019.04.011

基于深度学习RCF模型的三都澳筏式养殖区提取研究

doi: 10.3969/j.issn.0253-4193.2019.04.011

1.
中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室, 北京 100101;中国科学院大学, 北京 100049
2.
中国科学院地理科学与资源研究所资源与环境信息系统国家重点实验室, 北京 100101

基金项目: 中国科学院战略性先导科技专项（A类）（XDA19060303）；国家重点研发计划项目（2016YFC1402003）；国家自然科学基金（41671436）；资源与环境信息系统国家重点实验室自主创新项目（O88RAA01YA）。

计量
- 文章访问数: 841
- HTML全文浏览量: 87
- PDF下载量: 330
- 被引次数: 0
出版历程
- 收稿日期: 2018-04-18
- 修回日期: 2018-09-11

Extracting raft aquaculture areas in Sanduao from high-resolution remote sensing images using RCF

1.
State Key Laboratory of Resources and Enviromental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China;University of Chinese Academy of Sciences, Beijing 100049, China
2.
State Key Laboratory of Resources and Enviromental Information System, Institute of Geographic Sciences and Natural Resources Research, Chinese Academy of Sciences, Beijing 100101, China

摘要

摘要: 三都澳是中国重要的海水养殖海湾，在水产养殖中占有较高的经济地位。快速准确地获取养殖区的分布范围、数量以及面积等信息，对养殖区规划、产值估计、生态调查、风暴潮灾害预防等具有重要的意义。然而，随着养殖区域的扩大，海水背景状态愈发复杂多样，光谱特征差异较大，为养殖区提取带来困难。在本实验中，利用高分辨率遥感卫星GF-2图像，引入深度学习RCF（Richer Convolutional Features）网络模型对海湾内的筏式养殖区进行了提取。结果显示：该方法无需事先对区域进行水陆分离处理，且对水中泥沙较多的区域以及海浪较大的区域有很好的提取效果，提取精度达93%以上，适合进行大规模海水养殖区提取应用。
- 筏式养殖区 /
- RCF模型 /
- 深度学习 /
- 高分辨率遥感
Abstract: Sanduao is an important sea-breeding bay in China and holds a high economic status in aquaculture. Quickly and accurately obtaining information such as the distribution area, quantity, and aquaculture area is important for breeding area planning, production value estimation, ecological survey, and storm surge prevention. However, as the aquaculture area expands, the seawater background becomes increasingly complex and spectral characteristics differ dramatically, making it difficult to determine the aquaculture area. In this study, we used a high-resolution remote-sensing satellite GF-2 image to introduce a deep-learning Richer Convolutional Features network model to extract the raft aquaculture area in the bay. The results demonstrate that this method does not require land and water separation of the area in advance, and good extraction can be achieved in areas with more sediment and waves, with an extraction accuracy >93%, which is suitable for large-scale raft aquaculture area extraction.
- raft aquaculture area /
- RCF model /
- deep learning /
- high-resolution remote sensing

HTML全文

参考文献(21)

关长涛, 王清印. 我国海水网箱技术的发展与展望[J]. 渔业现代化, 2005(3):5-7. Guan Changtao, Wang Qingyin. Development and prospect of marine net cage technology in China[J]. Fishery Modernization, 2005(3):5-7.

FAO. The Role of Aquaculture in Sustainable Development[M]. Rome:FAO, 2007.

程田飞, 周为峰, 樊伟. 水产养殖区域的遥感识别方法进展[J]. 国土资源遥感, 2012, 24(3):1-5. Cheng Tianfei, Zhou Weifeng, Fan Wei. Progress in the methods for extracting aquaculture areas from remote sensing data[J]. Remote Sensing for Land & Resources, 2012, 24(3):1-5.

李新国, 江南, 杨英宝, 等. 太湖围湖利用与网围养殖的遥感调查与研究[J]. 海洋湖沼通报, 2006(1):93-99. Li Xinguo, Jiang Nan, Yang Yingbao, et al. Remote sensing investigation and survey of lake reclamation and enclosure aquaculture in Lake Taihu[J]. Transactions of Oceanology and Limnology, 2006(1):93-99.

樊建勇, 黄海军, 樊辉, 等. 利用RADARSAT-1数据提取海水养殖区面积[J]. 海洋科学, 2005, 29(10):44-47. Fan Jianyong, Huang Haijun, Fan Hui, et al. Extracting aquaculture area with RADASAT-1[J]. Marine Science, 2005, 29(10):44-47.

朱长明, 骆剑承, 沈占锋, 等. 高分辨率遥感影像近海养殖区自动识别方法[J]. 大连海事大学学报, 2011, 37(3):66-69. Zhu Changming, Luo Jiancheng, Shen Zhanfeng, et al. Extract enclosure culture in coastal waters based on high spatial resolution remote sensing image[J]. Journal of Dalian Maritime University, 2011, 37(3):66-69.

刘鹏, 杜云艳. 基于遥感案例推理的海岸带养殖信息提取[J]. 遥感技术与应用, 2012, 27(6):857-864. Liu Peng, Du Yunyan. A CBR Approach for extracting coastal aquaculture area[J]. Remote Sensing Technology and Application, 2012, 27(6):857-864.

卢业伟, 李强子, 杜鑫, 等. 基于高分辨率影像的近海养殖区的一种自动提取方法[J]. 遥感技术与应用, 2015, 30(3):486-494. Lu Yewei, Li Qiangzi, Du Xin, et al. A method of coastal aquaculture area automatic extraction with high spatial resolution images[J]. Remote Sensing Technology and Application, 2015, 30(3):486-494.

王静, 高俊峰. 基于对应分析的湖泊围网养殖范围提取[J]. 遥感学报, 2008, 12(5):716-723. Wang Jing, Gao Junfeng. Extraction of enclosure culture in Gehu lake based on correspondence analysis[J]. Journal of Remote Sensing, 2008, 12(5):716-723.

周小成, 汪小钦, 向天梁, 等. 基于ASTER影像的近海水产养殖信息自动提取方法[J]. 湿地科学, 2006, 4(1):64-68. Zhou Xiaocheng, Wang Xiaoqin, Xiang Tianliang, et al. Method of automatic extracting seaside aquaculture land based on aster remote sensing image[J]. Wetland Science, 2006, 4(1):64-68.

Wang Min, Cui Qi, Wang Jie, et al. Raft cultivation area extraction from high resolution remote sensing imagery by fusing multi-scale region-line primitive association features[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2017, 123:104-113.

谢玉林, 汪闽, 张新月. 面向对象的海岸带养殖水域提取[J]. 遥感技术与应用, 2009, 24(1):68-72. Xie Yulin, Wang Min, Zhang Xinyue. An object-oriented approach for extracting farm waters within coastal belts[J]. Remote Sensing Technology and Application, 2009, 24(1):68-72.

初佳兰, 赵冬至, 张丰收. 基于关联规则的裙带菜筏式养殖遥感识别方法[J]. 遥感技术与应用, 2012, 27(6):941-946. Chu Jialan, Zhao Dongzhi, Zhang Fengshou. Wakame raft interpretation method of remote sensing based on association rules[J]. Remote Sensing Technology and Application, 2012, 27(6):941-946.

王志华, 孟樊, 杨晓梅, 等. 高空间分辨率遥感影像分割尺度参数自动选择研究[J]. 地球信息科学学报, 2016, 18(5):639-648. Wang Zhihua, Meng Fan, Yang Xiaomei, at al. Study on the automatic selection of segmentation scale parameters for high spatial resolution remote sensing images[J]. Journal of Geo-information Science, 2016, 18(5):639-648.

张涛, 杨晓梅, 童立强, 等. 基于多尺度图像库的遥感影像分割参数优选方法[J]. 国土资源遥感, 2016, 28(4):59-63. Zhang Tao, Yang Xiaomei, Tong Liqiang, et al. Selection of best-fitting scale parameters in image segmentation based on multiscale segmentation image database[J]. Remote Sensing for Land & Resources, 2016, 28(4):59-63.

Blaschke T, Hay G J, Kelly M, et al. Geographic object-based image analysis-towards a new paradigm[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2014, 87:180-191.

Chen Gang, Weng Qihao, Hay G J, et al. Geographic object-based image analysis (GEOBIA):emerging trends and future opportunities[J]. GIScience & Remote Sensing, 2018, 55(2):159-182.

He Kaiming, Zhang Xiangyu, Ren Shaoqing, et al. Delving deep into rectifiers:surpassing human-level performance on ImageNet classification[C]//2015 IEEE International Conference on Computer Vision. Santiago:IEEE, 2015.

Liu Yun, Cheng Mingming, Hu Xiaowei, et al. Richer convolutional features for edge detection[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, Hawaii:IEEE, 2017.

黄标, 钱鲁闽, 刘家富. 福建三都澳水产养殖区水体氮磷含量及潜在性富营养化程度分析[J]. 台湾海峡, 2002, 21(4):411-415. Huang Biao, Qian Lumin, Liu Jiafu. Nutrient salts content and eutrophication assessment for Sanduao sea area, Fujian[J]. Journal of Oceanography in Taiwan Strait, 2002, 21(4):411-415.

纪炜炜, 周进. 三都澳大型底栖动物群落结构及其对水产养殖的响应[J]. 中国水产科学, 2012, 19(3):491-499. Ji Weiwei, Zhou Jin. Community structure of macrobenthos in response to mariculture practices in Sandu Bay[J]. Journal of Fishery Sciences of China, 2012, 19(3):491-499.

施引文献

资源附件(0)

访问统计