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

TL;DR

This paper introduces a novel, efficient method for estimating camera rotation in crowded scenes from monocular video, achieving high accuracy and robustness where previous methods struggled, supported by a new dataset and benchmark.

Contribution

We propose a new generalization of the Hough transform on SO(3) for robust camera rotation estimation in crowded scenes, outperforming existing methods in accuracy and speed.

Findings

Our method reduces rotation estimation error by nearly 50% compared to the next best approach.

It is more accurate than existing methods regardless of computational speed.

The approach is effective in crowded, real-world scenes, as demonstrated on a new dataset.

Abstract

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.