Li Ying, Cui Can, Liu Zexi, Liu Bingxin, Xu Jin, Zhu Xueyuan, Hou Yongchao
Navigation College, Dalian Maritime University, Dalian, China.
Environmental Information Institute, Dalian Maritime University, No. 1 Linghai Road, Dalian, Liaoning Province, China.
Arch Environ Contam Toxicol. 2017 Jul;73(1):154-169. doi: 10.1007/s00244-016-0358-5. Epub 2017 Jul 10.
Current marine oil spill detection and monitoring methods using high-resolution remote sensing imagery are quite limited. This study presented a new bottom-up and top-down visual saliency model. We used Landsat 8, GF-1, MAMS, HJ-1 oil spill imagery as dataset. A simplified, graph-based visual saliency model was used to extract bottom-up saliency. It could identify the regions with high visual saliency object in the ocean. A spectral similarity match model was used to obtain top-down saliency. It could distinguish oil regions and exclude the other salient interference by spectrums. The regions of interest containing oil spills were integrated using these complementary saliency detection steps. Then, the genetic neural network was used to complete the image classification. These steps increased the speed of analysis. For the test dataset, the average running time of the entire process to detect regions of interest was 204.56 s. During image segmentation, the oil spill was extracted using a genetic neural network. The classification results showed that the method had a low false-alarm rate (high accuracy of 91.42%) and was able to increase the speed of the detection process (fast runtime of 19.88 s). The test image dataset was composed of different types of features over large areas in complicated imaging conditions. The proposed model was proved to be robust in complex sea conditions.
当前利用高分辨率遥感影像进行海洋溢油检测和监测的方法非常有限。本研究提出了一种新的自下而上和自上而下的视觉显著性模型。我们使用Landsat 8、GF-1、MAMS、HJ-1溢油影像作为数据集。一种简化的基于图的视觉显著性模型被用于提取自下而上的显著性。它能够识别海洋中具有高视觉显著性目标的区域。一种光谱相似性匹配模型被用于获得自上而下的显著性。它能够通过光谱区分油区并排除其他显著干扰。利用这些互补的显著性检测步骤整合包含溢油的感兴趣区域。然后，使用遗传神经网络完成图像分类。这些步骤提高了分析速度。对于测试数据集，检测感兴趣区域的整个过程的平均运行时间为204.56秒。在图像分割过程中，利用遗传神经网络提取溢油。分类结果表明，该方法具有较低的误报率（准确率高达91.42%），并且能够提高检测过程的速度（运行时间快至19.88秒）。测试图像数据集由复杂成像条件下大面积的不同类型特征组成。所提出的模型在复杂海况下被证明是稳健的。
