Department of Computer Science and Engineering and the Center for Vision Research, York University, 4700 Keele Street, Toronto, Ontario M3J 1P3, Canada.
IEEE Trans Pattern Anal Mach Intell. 2012 Jun;34(6):1206-19. doi: 10.1109/TPAMI.2011.202.
This paper is concerned with the recovery of temporally coherent estimates of 3D structure and motion of a dynamic scene from a sequence of binocular stereo images. A novel approach is presented based on matching of spatiotemporal quadric elements (stequels) between views, as this primitive encapsulates both spatial and temporal image structure for 3D estimation. Match constraints are developed for bringing stequels into correspondence across binocular views. With correspondence established, temporally coherent disparity estimates are obtained without explicit motion recovery. Further, the matched stequels also will be shown to support direct recovery of scene flow estimates. Extensive algorithmic evaluation with ground truth data incorporated in both local and global correspondence paradigms shows the considerable benefit of using stequels as a matching primitive and its advantages in comparison to alternative methods of enforcing temporal coherence in disparity estimation. Additional experiments document the usefulness of stequel matching for 3D scene flow estimation.
本文研究了从双目立体图像序列中恢复动态场景的三维结构和运动的时间相干估计。提出了一种新的方法，该方法基于视图之间的时空二次型元素（stequels）匹配，因为这种基元对三维估计既包含空间信息又包含时间信息。为了在双目视图之间建立对应关系，开发了匹配约束条件。在建立对应关系后，无需显式运动恢复即可获得时间相干的视差估计值。此外，匹配的 stequels 还将支持直接恢复场景流估计值。使用包含在局部和全局对应范例中的地面实况数据进行的广泛算法评估表明，将 stequels 用作匹配基元具有很大的益处，并且与在视差估计中强制实现时间相干性的替代方法相比具有优势。其他实验证明了 stequel 匹配在三维场景流估计中的有用性。
