Direct Visual-Inertial Odometry with Semi-Dense Mapping
This work addresses scale drift in visual odometry for robotics or autonomous systems, but it is incremental as it builds on existing methods like DSO and IMU pre-integration.
The paper tackles the problem of visual-inertial odometry by proposing a tightly coupled nonlinear optimization method that integrates direct dense tracking and IMU pre-integration to estimate camera pose and build a semi-dense map, achieving competitive results on real-world benchmark datasets in indoor scenes.
The paper presents a direct visual-inertial odometry system. In particular, a tightly coupled nonlinear optimization based method is proposed by integrating the recent advances in direct dense tracking and Inertial Measurement Unit (IMU) pre-integration, and a factor graph optimization is adapted to estimate the pose of the camera and rebuild a semi-dense map. Two sliding windows are maintained in the proposed approach. The first one, based on Direct Sparse Odometry (DSO), is to estimate the depths of candidate points for mapping and dense visual tracking. In the second one, measurements from the IMU pre-integration and dense visual tracking are fused probabilistically using a tightly-coupled, optimization-based sensor fusion framework. As a result, the IMU pre-integration provides additional constraints to suppress the scale drift induced by the visual odometry. Evaluations on real-world benchmark datasets show that the proposed method achieves competitive results in indoor scenes.