基于多源卫星遥感的渤海海上油气平台识别

针对海上油气平台信息不足的问题，开展多源卫星遥感的油气平台识别方法研究。基于Landsat-8光学遥感影像(2018—2021年)应用阈值分割法、K-means分类法和最大似然分类法分别识别出渤海海域油气平台136座、166座和113座；基于Sentinel-1 SAR影像(2018—2021年)应用阈值分割法识别出油气平台338座；对上述结果进行决策级融合，识别出渤海油气平台428座。利用ZY-3高分辨率影像对融合方法的识别结果进行验证，结果显示识别油气平台的正确率达到85.2%,错判率、漏判率分别为10.9%和3.9%;油气平台位置与相关文献和公开资料一致。研究结果表明，决策级融合方法能够实现海上油气平台的有效判别，具有推广、应用价值。

Identification of offshore oil and gas platform in the Bohai Sea based on multi-source satellite remote sensing

To solve the problem of insufficient information of offshore oil and gas platform, the method of oil and gas platform identification based on multi-source satellite remote sensing was studied. Based on Landsat-8 remote sensing images of the Bohai Sea (2018-2021), 136, 166 and 113 oil and gas platforms in the Bohai Sea were identified by threshold segmentation, K-means unsupervised algorithm and maximum likelihood classification, respectively. Based on Sentinel-1 SAR images (2018-2021), 338 oil and gas platforms were identified by threshold segmentation method. Based on the decision level fusion of the above results, 428 oil and gas platforms in the Bohai Sea were identified. The ZY-3 high-resolution images were used to verify the identification results of the fusion method. The results showed that the accuracy of the identified oil and gas platforms reached 85.2%, and the error rate and miss rate were 10.9% and 3.9%, respectively. The identified oil and gas platform locations are consistent with literature and public data. The research shows that the decision level fusion method can realize the effective identification and extraction of offshore oil and gas platforms, and has the value of popularization and application.