This work proposes a fusion of inertial measurement units (IMUs) and a visual tracking system on an embedded device. The sensor-to-sensor calibration and the pose estimation are both achieved through an unscented Kalman filter (UKF). Two approaches for a UKF-based pose estimation are presented: The first uses the estimated pose of the visual SLAM system as measurement input for the UKF; The second modifies the motion model of the visual tracking system. Our results show that IMUs increase tracking accuracy even if the visual SLAM system is untouched, while requiring little computational power. Furthermore, an accelerometer-based map scale estimation is presented and discussed.

No abstract

This paper focuses on the advancement of a monocular sparse-SLAM algorithm via two techniques: Local feature maintenance and descriptor-based sensor fusion. We present two techniques that maintain the descriptor of a local feature: Pooling and bestfit. The maintenance procedure aims at defining more accurate descriptors, increasing matching performance and thereby tracking accuracy. Moreover, sensors besides the camera can be used to improve tracking robustness and accuracy via sensor fusion. State-of-the-art sensor fusion techniques can be divided into two categories. They either use a Kalman filter that includes sensor data in its state vector to conduct a posterior pose update, or they create world-aligned image descriptors with the help of the gyroscope. This paper is the first to compare and combine these two approaches. We release a new evaluation dataset which comprises 21 scenes that include a dense ground truth trajectory, IMU data, and camera data. The results indicate that descriptor pooling significantly improves pose accuracy. Furthermore, we show that descriptor-based sensor fusion outperforms Kalman filter-based approaches (EKF and UKF).