A Novel Georeferenced Dataset for Stereo Visual Odometry
This provides a new dataset for researchers in robotics and computer vision, but it is incremental as it focuses on data collection rather than algorithmic innovation.
The authors tackled the problem of evaluating stereo visual odometry by creating a new georeferenced dataset using a car-mounted stereo rig with GPS groundtruth, and they demonstrated its practical utility for analyzing factors like camera calibration and baseline distance.
In this work, we present a novel dataset for assessing the accuracy of stereo visual odometry. The dataset has been acquired by a small-baseline stereo rig mounted on the top of a moving car. The groundtruth is supplied by a consumer grade GPS device without IMU. Synchronization and alignment between GPS readings and stereo frames are recovered after the acquisition. We show that the attained groundtruth accuracy allows to draw useful conclusions in practice. The presented experiments address influence of camera calibration, baseline distance and zero-disparity features to the achieved reconstruction performance.