基于改进的高斯混合模型和图割模型的水体图像提取算法

Water image extraction algorithm based on improved Gaussian mixture model and graph cut model

合成孔径雷达具有全天时、全天候成像,观测范围广、成图周期短等特点,使其在水体提取中的应用具有明显优势。但是在湖泊提取中,已有算法易受湖泊周围环境噪声的干扰,运行效率低。针对此,提出一种将改进的高斯混合模型(GMM)与图割模型相结合的检测方法。先是利用两级Otsu阈值方法以获取湖泊的初始分割图,将对其计算得到的参数集作为GMM初始参数,其后应用最大期望算法(EM)迭代求取GMM的最佳参数,最后基于图割模型精准定位水体位置。实验结果表明初始参数越精确,水体轮廓越清晰,引入两级Otsu算法不仅可大幅度减少EM算法的迭代次数,且与预处理中的下采样相结合有效地提高了算法的运行速度。此外,改进传统图割模型的能量函数使得无需后处理即可得到精确的湖泊边界。

Synthetic aperture radar(SAR)has the characteristics of all-day and all-weather imaging,wide observation range,and short mapping period,which make it highly has achieved its application advantageous in water extraction.However,existing algorithms for lake extraction are easily affected by the surrounding environment of lakes and noise interference,resulting in low operational efficiency.Therefore,this paper proposes a detection method that combines an improved Gaussian mixture model(Gaussian mixture model,GMM)with graph cut model(GCM).First,the two-level Otsu threshold method is used to obtain the initial segmentation map of the lake,and the calculated parameter set is used as the initial parameter of the GMM.The expectation maximum algorithm(expectation-maximum,EM)is employed to obtain the optimal parameters of the GMM iteratively.The experimental results demonstrate that the more accurate the initial parameters,the clearer the outline of the water body.The introduction of the two-level Otsu algorithm not only greatly reduces the times of iterations of the EM algorithm,but also effectively enhances the running speed of the algorithm in combination with downsampling in preprocessing.In addition,the energy function of the graph cut model enables accurate lake boundaries to be obtained without requiring any post-processing.