arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1806.08498cs.CVcs.RO
收藏

视觉-惯性目标检测和映射

Visual-Inertial Object Detection and Mapping

University of California, Los Angeles(加州大学洛杉矶分校)

Xiaohan Fei, Stefano Soatto

摘要:

我们提出了一种方法来填充一个未知的环境与以前看到的对象的模型,放置在一个欧几里得参考系,因果关系推断和在线使用单目视频以及惯性传感器。我们实现的系统返回一个稀疏的点云的场景,是可见的,但没有被识别为以前看到的对象的区域,以及一个详细的对象模型和它的姿势在欧几里德框架,否则。该系统包括自下而上和自上而下的组件,由此,经过检测训练的深度网络为非线性滤波器提供的对象假设提供似然分数,该滤波器的状态用作记忆。额外的网络提供边缘的似然分数,这补充了训练成对小变形不变的检测网络。我们在现有数据集上测试我们的算法,并介绍了VISMA数据集,该数据集提供地面真实姿态,点云地图和对象模型,以及带有时间戳的惯性测量。

英文摘要:

We present a method to populate an unknown environment with models of previously seen objects, placed in a Euclidean reference frame that is inferred causally and on-line using monocular video along with inertial sensors. The system we implement returns a sparse point cloud for the regions of the scene that are visible but not recognized as a previously seen object, and a detailed object model and its pose in the Euclidean frame otherwise. The system includes bottom-up and top-down components, whereby deep networks trained for detection provide likelihood scores for object hypotheses provided by a nonlinear filter, whose state serves as memory. Additional networks provide likelihood scores for edges, which complements detection networks trained to be invariant to small deformations. We test our algorithm on existing datasets, and also introduce the VISMA dataset, that provides ground truth pose, point-cloud map, and object models, along with time-stamped inertial measurements.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑