Detailed real-time urban 3D reconstruction from video
Detailed real-time urban 3D reconstruction from video
复制标题
DOI：
10.1007/s11263-007-0086-4
复制
发表时间：
2008-07-01
影响因子：
19.5
通讯作者：
Towles, H.
中科院分区：
文献类型：
--
作者：
Pollefeys, M.;Nister, D.;Towles, H.
该论文提出了一种根据城市场景视频进行自动、地理配准、实时 3D 重建的系统。该系统收集视频流以及 GPS 和惯性测量值，以便将重建的模型放置在地理注册坐标中。它的所有处理步骤均采用当前最先进的实时模块进行设计。它采用商用图形硬件和标准 CPU 来实现实时性能。我们提出了设计系统和处理管道的步骤时的主要考虑因素。我们的系统扩展了现有算法，以满足实验室外操作所需的稳健性和可变性。为了考虑户外视频的大动态范围，处理管道在特征跟踪阶段估计全局相机增益变化，并在立体估计中有效地补偿这些变化，而不影响实时性能。许多应用所需的精度是通过利用帧间冗余的两步立体重建过程来实现的。我们展示了包含数十万帧的真实视频序列的结果。
The paper presents a system for automatic, geo-registered, real-time 3D reconstruction from video of urban scenes. The system collects video streams, as well as GPS and inertia measurements in order to place the reconstructed models in geo-registered coordinates. It is designed using current state of the art real-time modules for all processing steps. It employs commodity graphics hardware and standard CPU's to achieve real-time performance. We present the main considerations in designing the system and the steps of the processing pipeline. Our system extends existing algorithms to meet the robustness and variability necessary to operate out of the lab. To account for the large dynamic range of outdoor videos the processing pipeline estimates global camera gain changes in the feature tracking stage and efficiently compensates for these in stereo estimation without impacting the real-time performance. The required accuracy for many applications is achieved with a two-step stereo reconstruction process exploiting the redundancy across frames. We show results on real video sequences comprising hundreds of thousands of frames.