Constrained Bundle Adjustment for Structure From Motion Using Uncalibrated Multi-Camera Systems

TL;DR

This paper introduces a constrained bundle adjustment method for uncalibrated multi-camera systems that maintains fixed relative camera positions, improving 3D reconstruction accuracy in structure from motion tasks.

Contribution

It proposes a novel baseline constraint for bundle adjustment that enforces static relative camera positions in uncalibrated multi-camera setups.

Findings

Achieved a 29.38% improvement over traditional methods.

Successfully reconstructed 3D dense point clouds from uncalibrated camera videos.

Validated approach against LiDAR reference data.

Abstract

Structure from motion using uncalibrated multi-camera systems is a challenging task. This paper proposes a bundle adjustment solution that implements a baseline constraint respecting that these cameras are static to each other. We assume these cameras are mounted on a mobile platform, uncalibrated, and coarsely synchronized. To this end, we propose the baseline constraint that is formulated for the scenario in which the cameras have overlapping views. The constraint is incorporated in the bundle adjustment solution to keep the relative motion of different cameras static. Experiments were conducted using video frames of two collocated GoPro cameras mounted on a vehicle with no system calibration. These two cameras were placed capturing overlapping contents. We performed our bundle adjustment using the proposed constraint and then produced 3D dense point clouds. Evaluations were performed by comparing these dense point clouds against LiDAR reference data. We showed that, as compared to traditional bundle adjustment, our proposed method achieved an improvement of 29.38%.