arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2309.08588cs.CVcs.RO
收藏

拥挤场景下帧间相机旋转估计

Robust Frame-to-Frame Camera Rotation Estimation in Crowded Scenes

University of Massachusetts Amherst(马萨诸塞大学阿默斯特分校);Mitsubishi Electric Research Laboratories(三菱电机研究实验室)

Fabien Delattre, David Dirnfeld, Phat Nguyen, Stephen Scarano, Michael J. Jones, Pedro Miraldo, Erik Learned-Miller

AI总结:

针对拥挤场景下从手持单目视频估计相机旋转时现有方法无法兼顾精度与速度的问题,提出一种SO(3)上Hough变换的新颖泛化方法以高效鲁棒地寻找与光流最兼容的旋转,误差降低近50%,并提供了新数据集与基准。

摘要:

我们提出了一种从手持单目视频估计拥挤真实场景中相机旋转的方法。尽管相机旋转估计是一个被广泛研究的问题,但在该设定下,此前没有方法能同时具备高精度和可接受的速度。由于其他数据集未能很好地解决该设定,我们提供了一个新数据集和基准,在17个视频序列上具有高精度且严格验证的真值。为宽基线立体视觉开发的方法(如5点法)在单目视频上表现不佳。另一方面,自动驾驶中使用的方法(如SLAM)依赖特定传感器设置、特定运动模型或局部优化策略(滞后批处理),不能很好地泛化到手持视频。最后,对于动态场景,常用的鲁棒化技术(如RANSAC)需要大量迭代,速度慢得令人无法接受。我们引入了一种SO(3)上Hough变换的新颖泛化方法,以高效鲁棒地找到与光流最兼容的相机旋转。在速度相当的方法中,我们的方法将误差降低了近50%,并且比任何方法都更准确,无论速度如何。这为拥挤场景这一计算机视觉的重要设定提供了一个强大的新性能基准。代码和数据集可在 https://fabiendelattre.com/robust-rotation-estimation 获取。

英文摘要:

We present an approach to estimating camera rotation in crowded, real-world scenes from handheld monocular video. While camera rotation estimation is a well-studied problem, no previous methods exhibit both high accuracy and acceptable speed in this setting. Because the setting is not addressed well by other datasets, we provide a new dataset and benchmark, with high-accuracy, rigorously verified ground truth, on 17 video sequences. Methods developed for wide baseline stereo (e.g., 5-point methods) perform poorly on monocular video. On the other hand, methods used in autonomous driving (e.g., SLAM) leverage specific sensor setups, specific motion models, or local optimization strategies (lagging batch processing) and do not generalize well to handheld video. Finally, for dynamic scenes, commonly used robustification techniques like RANSAC require large numbers of iterations, and become prohibitively slow. We introduce a novel generalization of the Hough transform on SO(3) to efficiently and robustly find the camera rotation most compatible with optical flow. Among comparably fast methods, ours reduces error by almost 50\% over the next best, and is more accurate than any method, irrespective of speed. This represents a strong new performance point for crowded scenes, an important setting for computer vision. The code and the dataset are available at https://fabiendelattre.com/robust-rotation-estimation.

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。

↑