arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.05676cs.CV
收藏

从摄像机运动学习对象深度和视频对象分割

Learning Object Depth from Camera Motion and Video Object Segmentation

University of Michigan(密歇根大学)

Brent A. Griffin, Jason J. Corso

摘要:

视频对象分割,即,近年来,视频中目标对象与背景的分离在真实和具有挑战性的视频中取得了显著的进展。为了在3D应用中利用这一进展,本文解决了在给定相机运动的一些测量(例如,根据机器人运动学或车辆里程计)。我们首先引入了一个多样化的可扩展数据集,其次设计了一个新的深度网络,该网络仅使用分割掩模和未校准的相机移动来估计对象的深度。我们的数据生成框架创建了人工对象分割,这些分割根据相机和对象之间的距离变化进行缩放,我们的网络即使在分割错误的情况下也能学习估计对象深度。我们展示了我们的方法跨域使用机器人摄像头来定位对象从YCB数据集和车辆摄像头来定位障碍物,而驾驶。

英文摘要:

Video object segmentation, i.e., the separation of a target object from background in video, has made significant progress on real and challenging videos in recent years. To leverage this progress in 3D applications, this paper addresses the problem of learning to estimate the depth of segmented objects given some measurement of camera motion (e.g., from robot kinematics or vehicle odometry). We achieve this by, first, introducing a diverse, extensible dataset and, second, designing a novel deep network that estimates the depth of objects using only segmentation masks and uncalibrated camera movement. Our data-generation framework creates artificial object segmentations that are scaled for changes in distance between the camera and object, and our network learns to estimate object depth even with segmentation errors. We demonstrate our approach across domains using a robot camera to locate objects from the YCB dataset and a vehicle camera to locate obstacles while driving.

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。

↑