海天线提取是研究海天背景条件下目标跟踪的一项重要内容。考虑到海天背景的多样性, 首先分析了现有算法的缺点, 然后提出了一种适应性较好的海天线提取算法。算法首先用中值滤波去除云层和海杂波等噪声, 然后利用基于相位编组的Hough变换提取出海天线。由于算法融合了相位编组和Hough变换两者的优点, 所以该方法不但能提取出低对比度下的海天线, 而且还具有强的抗干扰性, 克服了相位编组和Hough变换各自的缺点。实验结果证明, 该方法能提取出简单和复杂背景中的海天线, 适应性好、鲁棒性强、定位准确, 降低了后续目标跟踪的复杂度。

Sea-sky-line detection is an important component involved in the target tracking under the condition of sea-sky background. Considering the diversity of the sea-sky background, this paper first analyzes the disadvantages of some existing algorithms, and then a better adaptability sea-sky-line extraction algorithm is presented. First, median filter is used to eliminate noise such as cloud and sea clutter and other noise, and then Hough transform based on phase grouping is used to extract the sea-sky-line. As the algorithm combines the advantages of both the phase grouping and the Hough transform, it can not only extract the sea-sky-line under low-contract, but also has strong anti-interference, and overcome its own shortcomings of phase grouping and Hough transform. The experimental results show that the method can extract the sea-sky-line from the simple and complex background. Through lots of experiments, the results proved that this algorithm is adaptability, robustness, accurate positioning, reducing the complexity of the follow-up target tracking.