全方位全景图像技术(英文)

论述一种从图像序列中重建出全方位全景图像的技术 ,旨在克服镜头只是纯粹的摇摄时许多成像条件限制。在块匹配算法中 ,如何选取最佳配准基本块对于增强算法的鲁棒性和性能是非常重要的。本文在包含主要视觉特征的高频图像中自动选取最佳配准基本块 ,为了能够减少累积的配准误差 ,采用了基于相位相关的、带旋转校正的全局配准算法 ,从而得到解决了平移和旋转的优化图像块。然后 ,采用了基于 Levenberg-Marquardt非线性递归型最优化算法 ,解决由于镜头的视差和不规则变形带来的局部误差。文中还采用平滑滤波器解决了在两幅图像镶嵌出可能由于累积配准误差而出现明显的条缝

IMAGE PANORAMIC MOS AICING WITH GLOBAL AND LOCAL REGISTRATION

Technique s for constructing full view panoramic mosaics from sequences of images are pres ented. The goal of this work is to remove too many limitations for pure panning motion. The best reference block is important for the block-matching method for improving the robustness and performance. It is automatically selected in the h igh-frequency image, which always contains the plenty visible features. In orde r to reduce accumulated registration errors, the global registration using the p hase-correlation matching method with rotation adjustment is applied to the who le sequence of images, which results in an optimal image mosaic with resolving t ranslational or rotational motion. The local registration using the Levenberg-M arquardt iterative non-linear minimization algorithm is applied to compensating for small amounts of motion parallax introduced by translations of the camera a nd other unmodeled distortions, then minimizing the discrepancy after applying t he global registration. The accumulated misregistration errors may cause a visib le gap between the two images. A smoothing filter is introduced for removing the visible artifact.