基于主动轮廓法的复杂背景下飞机图象的轮廓提取

研究了一种适合于复杂背景下单个目标轮廓提取的方法———主动轮廓法(ActiveContourModel)。主动轮廓法是统计学分割方法的一种。基于统计学意义上的图象分割是把图象中各个象素点的灰度看作具有一定概率分布的随机变量 ,观察到的图象是对实际物体作了某种变换并加入噪声的结果。从观察到的图象中正确分割图象从统计学的角度讲就是要找到最有可能的 (即概率最大 )的物体组合。主动轮廓法就是基于这种概率最大的思想提出来的。研究过程中 ,对原有方法进行了大的改进 ,增强了主动轮廓法对初始形状的鲁棒性 ,保持了轮廓的光滑性。仿真中 ,应用该方法提取飞机图象的轮廓 ,取得了较好的效果 ,计算所用的时间少。

Modified RBF Neural Networks Control for the Nonlinear Flight of Chaotic Motion

Active Contour Model is studied which can extract the contour of single object under complex background. Active Contour Model is a method of statistic image segmentation. Pixels's grey value in the image is treated as a random variable which has some probability distribution. The image obtained always contains noise and has some transformation from the object of the image. Image segmentation is used to find most possible object. Active Contour Model is based on the idea of the maximum probability. In this paper, we improve evidently the original method and enhance the robustness of Active Contour Model to keep the smoothness of the contour. In the simulation, this method is applied to extract the contour of aircraft image. The result is good and computation time is less.