基于图像分割的路径规划算法

Path Planning of Virtual Endoscopy Based on Image Segmentation

路径规划技术是虚拟内窥镜实现漫游检查的基础,而由于其计算复杂度高,已经成为虚拟内窥镜走向临床的瓶颈。本文把路径规划的思想融合在图像分割模块之中,充分利用图像分割的结果,从而简化了路径规划的计算复杂度。该算法利用自适应区域生长法及序列切片之间的相关信息进行图像分割,把区域生长的种子点存储在链式数据结构中作为路径的关键点。最后用样条函数插值平滑这些关键点,得到规划路径。试验结果证实该算法的有效性和可行性。

Path planning is a prerequisite task to automatically navigate with virtual camera and plays a crucial role in virtual endoscopy application. The path planning algorithm based on segmentation combines the center-line path with the image segmentation by using the result of image segmentation to reduce the complexity of path planning. The algorithm makes use of the connectivitypreserving features of sequence images and segments a series of images by applying the adaptive region growing algorithm. It stores the seed of growing region into a series of stack as the key point of the navigation plan. The navigation path is obtained after smoothing those points. Experiment results show that our algorithm is feasible and robust.