Geometric distortion correction for echo planar images using nonrigid registration with spatially varying scale

One method used to correct geometric and intensity distortions in echo planar images is to register them to undistorted images via nonrigid deformations. However, some areas in the echo planar images are more distorted than others, thus suggesting the use of deformations whose characteristics are adapted spatially. In this article, we incorporate into our previously developed registration algorithm a spatially varying scale mechanism, which adapts the local scale properties of the transformation by means of a scale map. To compute the scale map, a technique is proposed that relies on an estimate of the expected deformation field. This estimate is generated using knowledge of the physical processes that induce distortions in echo planar images. We evaluate the method of spatially varying scale on both simulated and real data. We find that, in comparison with our earlier method using fixed scale, our new method finds deformation fields that are smoother and finds them faster without sacrificing accuracy.     

基于带约束的隐表示非线性形状配准

主要通过对形状进行带约束的隐表示来研究非线性形状配准. 首先, 采用隐函数的零水平集来表示形状, 并结合从整体到局部的策略,对形状配准问题进行了建模. 其次, 为提高模型精度, 对全局尺度形变和局部非线性形变引入了尺度约束和带状约束. 进一步, 给出了一阶变分, 并应用负梯度流进行数值求解. 最后,多个数据集上与现有经典算法的对比实验表明, 给出的算法具有更优的精度.     

基于特征定位的航空航天制孔多视测量拼接方法

为满足航空航天大部件对制孔质量的数字化原位检测需求，提出一种基于特征板的制孔多视点云拼接方法，实现孔壁完整三维形貌重建与检测。分析制孔多视检测的需求，提出采用特征定位板辅助的多视点云配准方法。介绍了内角不等四边形特征板的设计与相应的点云分割、识别算法。说明基于特征自定位的多视点云拼接及参数提取方法。结合机械臂搭建实验平台，对常用钛、铝及复合材料的试件模拟原位检测，结果显示各平均误差分别为0.011 mm、0.034 mm、0.041 mm，验证了配准算法的可靠性；并对比传统单视与该方法检测结果，体现该方法的鲁棒性。