Bazin Pierre-Louis, Vézien Jean-Marc
Laboratory for Medical Image Computing, Neuroradiology Division, Phipps B100, Johns Hopkins Hospital, 600 North Wolfe Street, Baltimore, MD 21287, USA.
IEEE Trans Pattern Anal Mach Intell. 2005 Dec;27(12):1960-76. doi: 10.1109/TPAMI.2005.245.
This paper presents an approach to shape and motion estimation that integrates heterogeneous knowledge into a unique model-based framework. We describe the observed scenes in terms of structured geometric elements (points, line segments, rectangles, 3D corners) sharing explicitly Euclidean relationships (orthogonality, parallelism, colinearity, coplanarity). Camera trajectories are represented with adaptative models which account for the regularity of usual camera motions. Two different strategies of automatic model building lead us to reduced models for shape and motion estimation with a minimal number of parameters. These models increase the robustness to noise and occlusions, improve the reconstruction, and provide a high-level representation of the observed scene. The parameters are optimally computed within a sequential Bayesian estimation procedure that gives accurate and reliable results on synthetic and real video imagery.
本文提出了一种形状和运动估计方法，该方法将异构知识集成到一个独特的基于模型的框架中。我们根据共享明确欧几里得关系（正交性、平行性、共线性、共面性）的结构化几何元素（点、线段、矩形、3D角点）来描述观察到的场景。相机轨迹用自适应模型表示，该模型考虑了常见相机运动的规律性。两种不同的自动模型构建策略使我们能够用最少的参数减少形状和运动估计模型。这些模型提高了对噪声和遮挡的鲁棒性，改善了重建效果，并提供了观察场景的高级表示。参数在顺序贝叶斯估计过程中进行最优计算，该过程在合成和真实视频图像上给出准确可靠的结果。
