图 书 馆
LSD-SLAM：大型直接单眼SLAMLSD-SLAM: Large-Scale Direct Monocular SLAM |
|
| 课程网址: | http://videolectures.net/eccv2014_engel_monocular_slam/ |
| 主讲教师: | Jakob Engel |
| 开课单位: | 慕尼黑工业大学 |
| 开课时间: | 2014-10-29 |
| 课程语种: | 英语 |
| 中文简介: |  我们提出了一种直接的（特征较少的）单眼SLAM算法，该算法与当前有关直接方法的现有技术相比，可以构建大规模，一致的环境图。除了基于直接图像对齐的高精度姿势估计之外，还可以实时重建3D环境作为具有相关半密集深度图的关键帧的姿势图。这些是通过对大量像素方向的较小基准立体声比较进行过滤而获得的。显着的标度漂移感知公式允许该方法在具有挑战性的序列上运行，包括场景标度的较大变化。主要的推动力是两个关键的新颖性：（1）一种在TeX上运行的新颖直接跟踪方法，从而显式检测尺度漂移；（2）一个优雅的概率解决方案，可将嘈杂的深度值的影响纳入跟踪。由此产生的直接单目SLAM系统可以在CPU上实时运行。 |
| 课程简介: | We propose a direct (feature-less) monocular SLAM algorithm which, in contrast to current state-of-the-art regarding direct methods, allows to build large-scale, consistent maps of the environment. Along with highly accurate pose estimation based on direct image alignment, the 3D environment is reconstructed in real-time as pose-graph of keyframes with associated semi-dense depth maps. These are obtained by filtering over a large number of pixelwise small-baseline stereo comparisons. The explicitly scale-drift aware formulation allows the approach to operate on challenging sequences including large variations in scene scale. Major enablers are two key novelties: (1) a novel direct tracking method which operates on TeX, thereby explicitly detecting scale-drift, and (2) an elegant probabilistic solution to include the effect of noisy depth values into tracking. The resulting direct monocular SLAM system runs in real-time on a CPU. |
| 关 键 词: | 计算机视觉; 单眼SLAM算法; 半密集深度图 |
| 课程来源: | 视频讲座网 |
| 数据采集: | 2020-06-11：吴淑曼 |
| 最后编审: | 2020-06-29：cxin |
| 阅读次数: | 53 |