Computing Egomotion with Local Loop Closures for Egocentric Videos
This resolves a long-standing problem in egocentric vision, enabling new applications for users of wearable cameras.
The paper tackles the problem of camera pose estimation in egocentric videos, where existing SLAM algorithms often fail, by proposing a robust method that uses short loop closures aligned with footsteps and 2D rotation averaging, resulting in a more stable algorithm as demonstrated on various datasets.
Finding the camera pose is an important step in many egocentric video applications. It has been widely reported that, state of the art SLAM algorithms fail on egocentric videos. In this paper, we propose a robust method for camera pose estimation, designed specifically for egocentric videos. In an egocentric video, the camera views the same scene point multiple times as the wearer's head sweeps back and forth. We use this specific motion profile to perform short loop closures aligned with wearer's footsteps. For egocentric videos, depth estimation is usually noisy. In an important departure, we use 2D computations for rotation averaging which do not rely upon depth estimates. The two modification results in much more stable algorithm as is evident from our experiments on various egocentric video datasets for different egocentric applications. The proposed algorithm resolves a long standing problem in egocentric vision and unlocks new usage scenarios for future applications.