Benchmarking Pedestrian Odometry: The Brown Pedestrian Odometry Dataset (BPOD)

TL;DR

The BPOD dataset provides a comprehensive benchmark for evaluating visual odometry algorithms in pedestrian scenarios with real-world challenges like motion blur and self-rotation, highlighting the need for further development in this area.

Contribution

We introduce the BPOD dataset, capturing diverse pedestrian environments with realistic motion artifacts, and evaluate various VO methods to identify current limitations.

Findings

Existing VO methods struggle with pedestrian-specific challenges.

BPOD includes diverse indoor and outdoor pedestrian scenarios.

Significant improvements are needed for reliable pedestrian odometry.

Abstract

We present the Brown Pedestrian Odometry Dataset (BPOD) for benchmarking visual odometry algorithms in head-mounted pedestrian settings. This dataset was captured using synchronized global and rolling shutter stereo cameras in 12 diverse indoor and outdoor locations on Brown University's campus. Compared to existing datasets, BPOD contains more image blur and self-rotation, which are common in pedestrian odometry but rare elsewhere. Ground-truth trajectories are generated from stick-on markers placed along the pedestrian's path, and the pedestrian's position is documented using a third-person video. We evaluate the performance of representative direct, feature-based, and learning-based VO methods on BPOD. Our results show that significant development is needed to successfully capture pedestrian trajectories. The link to the dataset is here: \url{https://doi.org/10.26300/c1n7-7p93