Movement Tracking by Optical Flow Assisted Inertial Navigation
This work addresses movement tracking for portable devices like smartphones, offering incremental improvements in robustness and accuracy in challenging environments.
The paper tackled robust six degree-of-freedom tracking on portable devices by fusing IMU data with dense optical flow from camera data, using a learning-based model to improve flow estimates and demonstrating applicability on real-world iPad data in low-texture environments.
Robust and accurate six degree-of-freedom tracking on portable devices remains a challenging problem, especially on small hand-held devices such as smartphones. For improved robustness and accuracy, complementary movement information from an IMU and a camera is often fused. Conventional visual-inertial methods fuse information from IMUs with a sparse cloud of feature points tracked by the device camera. We consider a visually dense approach, where the IMU data is fused with the dense optical flow field estimated from the camera data. Learning-based methods applied to the full image frames can leverage visual cues and global consistency of the flow field to improve the flow estimates. We show how a learning-based optical flow model can be combined with conventional inertial navigation, and how ideas from probabilistic deep learning can aid the robustness of the measurement updates. The practical applicability is demonstrated on real-world data acquired by an iPad in a challenging low-texture environment.