【摘要】 针对有部分遮挡物或有噪声等复杂背景下海面图像的海天线检测效果欠佳的现象,提出一种有效的方法对海面可见光图像的海天线进行自动检测。该方法首先利用均值漂移(Mean Shift)分析方法对海面可见光图像提取边缘,提取后的图像的区域边界信息用嵌入置信度进行二次筛选,进一步鉴别图像像素属性,剔除一些伪边缘,最后进行Hough变换提取海天线。实验结果表明,所提出的方法不仅可以用于单一背景下海面图像的海天线检测,也可用于部分被遮挡或者其他复杂背景下的海天线检测。高斯噪声下的抗噪性能实验也验证了所提出的方法的鲁棒性。更多还原

【Abstract】 Aiming at the phenomenon that the detection effect of sea-sky line in regard to sea image with complex background including partially occluded by objects or having noises,we proposed an effective method to automatically detect sea-sky line in images with visible light of sea surface. Firstly,the method uses the mean shift analysis method to extract the edges from the images with visible light of sea surface,then it employs the method of embedded confidence to make secondary screening on the regional edges information of the extracted images for further identifying the properties of image pixels and weeding out some pseudo-edges,finally it uses Hough transform to extract the sea-sky line. Experimental results show that the proposed method can be used for detecting the sea-sky lines with both the single background and the partially occluded or other complex backgrounds. The experiment of anti-noise performance carried out under Gaussian noise also proves the robustness of the proposed method.更多还原