Search

In recent years, visual-inertial odometry for state estimation has achieved a huge success in terms of robustness and accuracy. However, current visual-inertial odometry algorithms still struggle with high computational cost, which severely hinders its application on computational resource limited platforms. In this paper, a novel tightly coupled visual-inertial odometry algorithm that can maximize utilize the information provided by 3D map points and IMU pre-integration to reduce the algorithm’s computational cost is proposed. In the front-end, an accelerated optical flow tracking algorithm using the depth known 3D map points and IMU pre-integration between two consecutive frames is proposed to reduce the tracking time. In the back-end, a joint optimization model based on hybrid residuals is proposed, which consists the geometric, the photometric and the IMU residuals. It’s worth noting that partial feature points with good tracking quality from all the feature points that the algorithm is tracking on are selected to construct photometric residuals. Therefore, those selected feature points can provide double constraints for the motion. The one feature point provide double motion constraints strategy allows our odometry algorithm use fewer feature points under the condition of same number of motion constraints which really reduced the amount of feature points also the computational resource needed by our algorithm to achieve a comparable pose estimation accuracy. Experiment results on public available dataset demonstrate the effectiveness of our proposed approach.

This paper proposes a novel approach for metric monocular SLAM Initialization using keypoints and a fiducial marker. SLAM approaches using one camera only can obtain the scale relevant to initial movement and the reference world origin must be attached to the initial frame. These make monocular SLAM approaches hard to achieve metric scale in localization and navigation problems or to provide true scale reference in augmented reality applications. In this paper, a fiducial marker is adopted at the initialization stage of SLAM. The relative and the absolute scale for 3D coordinates of some particular visual features would be calculated. The initial map would be adjusted by the ratio of these two values at the same time. Our experimental results show that feature-based monocular SLAM can acquire metric scale and the world origin can be coordinated to the marker plane after initialization. The scale outputs can reach centimeter accuracy with real-time performance in a normal computing unit.

The augmented reality (AR) has been developed dramatically in recent years, and it has being widely used in military training, medical treatment, education and so on. While the vergence-accommodation conflict (VAC) remains a major problem in head mounted displays (HMD) for augmented reality. In this review, we discuss the cause of the vergence-accommodation conflict in augmented reality, and introduce the various methods to solve the VAC, along with the advantages and shortcomings.

Pose estimation only using a monocular camera and an inertial sensor triggers increasing popularity in recent years. In this paper, we propose a method, that tightly combines direct image information (intensity and gradient) from monocular camera with inertial information from three-axis gyroscope and accelerometer in a multi-state constraint Kalman filter (MSCKF) based framework to perform an effective pose estimation. In contrast to other pose estimation methods using vision, our solution gets rid of traditional feature extraction and expression, instead using image patches with distinct gradient to represent a visual measurement from environment. We adopt sequential inertial information and the poses between two consecutive keyframes to construct the state vector, imposing constraints on the poses and marginalising out expired ones, which would reduce the computational complexity linear to the number of selected patches. Furthermore, we view the data from the inertial sensor as intrinsic information applied in filter propagation, providing fast rate estimation for the state. The result of our method has been tested on real flying data of a micro aerial vehicle in indoor and outdoor environments.