Towards a benchmark for RGB-D SLAM evaluation

Jürgen Sturm (1) , Stéphane Magnenat (2) , Nikolas Engelhard (3) , François Pomerleau (2) , Francis Colas (2) , Daniel Cremers (1) , Roland Siegwart (2) , Wolfram Burgard (3)

1 CVPR - Computer Vision and Pattern Recognition Group [Münster]
2 ASL - Autonomous Systems Lab
3 Department of Computer Science [Freiburg]

We provide a large dataset containing RGB-D image sequences and the ground-truth camera trajectories with the goal to establish a benchmark for the evaluation of visual SLAM systems. Our dataset contains the color and depth images of a Microsoft Kinect sensor and the ground-truth trajectory of camera poses. The data was recorded at full frame rate (30 Hz) and sensor resolution (640x480). The ground-truth trajectory was obtained from a high-accuracy motion-capture system with eight high-speed tracking cameras (100 Hz). Further, we provide the accelerometer data from the Kinect. Finally, we propose an evaluation criterion for measuring the quality of the estimated camera trajectory of visual SLAM systems.

Mots clés: RGB-D camera; SLAM Simultaneous Localisation and Mapping; Benchmark

Domaines: Robotique [cs.RO]

Jürgen Sturm, Stéphane Magnenat, Nikolas Engelhard, François Pomerleau, Francis Colas, et al.. Towards a benchmark for RGB-D SLAM evaluation. RGB-D Workshop on Advanced Reasoning with Depth Cameras at Robotics: Science and Systems Conf.(RSS), 2011, Los Angeles, United States. ⟨hal-01142608⟩