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 2109.05928cs.CVcs.AIstat.ML
收藏

基于视觉的系统辨识和利用动力学约束的3D关键点发现

Vision-based system identification and 3D keypoint discovery using dynamics constraints

University of Edinburgh(爱丁堡大学);Monash University(莫纳什大学)

Miguel Jaques, Martin Asenov, Michael Burke, Timothy Hospedales

摘要:

本文介绍了V-SysId,一种新的方法,使同时关键点发现,3D系统辨识,和外部摄像机校准从一个静态摄像机拍摄的未标记的视频,只使用家庭的运动方程的对象的兴趣作为弱监督。V-SysId采用关键点轨迹建议,并在最大似然参数估计和外部相机校准之间交替,然后应用合适的选择标准来识别感兴趣的轨迹。然后,这被用于使用监督学习来训练关键点跟踪模型。一系列设置(机器人,物理,生理)的结果突出了这种方法的实用性。

英文摘要:

This paper introduces V-SysId, a novel method that enables simultaneous keypoint discovery, 3D system identification, and extrinsic camera calibration from an unlabeled video taken from a static camera, using only the family of equations of motion of the object of interest as weak supervision. V-SysId takes keypoint trajectory proposals and alternates between maximum likelihood parameter estimation and extrinsic camera calibration, before applying a suitable selection criterion to identify the track of interest. This is then used to train a keypoint tracking model using supervised learning. Results on a range of settings (robotics, physics, physiology) highlight the utility of this approach.

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。

↑