Inertial Measurement Unit Information Research Articles

EPVC: A Novel Initialization Approach of Visual-Inertial Integrated Navigation

Abstract The fusion of visual and inertial measurements in robotics community is growing in popularity since both of them have complementary perceptual information. Pre-initializing gyroscope bias and accelerometer bias of the Inertial Measurement Unit (IMU) is a critical issue to achieve a better fusion performance, and the metric scale is another crucial element to be estimated. Current mainstream loosely-coupled initialization methods are unstable as they do not incorporate IMU information into the visual structure from motion(SfM). In addition, the accuracy of the tightly-coupled methods is limited since they do not use visual observations to remove gyroscope bias and usually ignore them in close-form solution. In this paper, a visual-inertial initialization method which we refer to as epipolar plane normal vectors coplanarity (EPVC) constraint method is proposed to solve gyroscope bias. A step further, a novel analytical solution is presented to optimize other parameters. Comparing our proposed method with VINS-Mono and inertial-only optimization through the publicly available EuRoC dataset, the results demonstrate that our method outperforms the existing methods in estimating the gyroscope bias and scale factor, and with the increase of initialization time, the accelerometer bias error and gravity direction error have a clear diminishing tendency.

Robust multiple obstacle tracking method based on depth aware OCSORT for agricultural robots

Multiple Object Tracking (MOT) of dynamic obstacles in field is an important prerequisite for agricultural robots to achieve dynamic obstacle avoidance. The complex and unpredictable road environment in the rural areas will cause severe vibration to the robot, affecting the camera pose and consequently leading to object matching errors. Therefore, we propose an improved method named Depth Aware Observation Centric Simple Online and Realtime Tracking (DA-OCSORT) with two new modules named Inertial Measurement Unit (IMU)-based Camera Motion Compensation (ICMC) and Depth Aware (DA). This method can use IMU information to compensate for camera ego-motion and perform multi-dimensional matching through object depth information, thereby minimizing the influence of camera motion on tracking process. We created an open-source MOT dataset, named MOTorchard. Building upon the pure motion-based method OCSORT, we achieve SOTA on this MOTorchard with HOTA 54.1, MOTA 83.3, IDF1 52.9 and FPS 22.7. Moreover, the proposed two modules prove to have good real-time performance and strong adaptability to other published MOT algorithms.

Longitudinal Velocity Estimation of Driverless Vehicle by Fusing LiDAR and Inertial Measurement Unit

Aiming at the problem that, under certain extreme conditions, relying on tire force or tire angular velocity to represent the longitudinal velocity of the unmanned vehicle will fail, this paper proposes a longitudinal velocity estimation method that fuses LiDAR and inertial measurement unit (IMU). First, in order to improve the accuracy of LiDAR odometry, IMU information is introduced in the process of eliminating point cloud motion distortion. Then, the statistical characteristic of the system noise is tracked by an adaptive noise estimator, which reduces the model error and suppresses the filtering divergence, thereby improving the robustness and filtering accuracy of the algorithm. Next, in order to further improve the estimation accuracy of longitudinal velocity, time-series analysis is used to predict longitudinal acceleration, which improves the accuracy of the prediction step in the unscented Kalman filter (UKF). Finally, the feasibility of the estimation method is verified by simulation experiments and real-vehicle experiments. In the simulation experiments, medium- and high-velocity conditions are tested. In high-velocity conditions (0–30 m/s), the average error is 1.573 m/s; in the experiment, the average error is 0.113 m/s.

Reducing the device complexity for 3D human pose estimation: A deep learning approach using monocular camera and IMUs

Camera and inertial measurement unit (IMU) based three-dimensional (3D) human pose estimation flourished in the last decade. However, existing methods are difficult to apply to clinical environments because of the many required devices. In this study, we attempt to reduce the devices and maintain their robustness. Occ-Corrector, a semantic convolution-based neural network, was proposed to estimate 3D human poses robustly in occlusion cases involving a single camera with the help of a few IMUs. It includes a simple Sensor-Reshape, which helps to fuse IMU information with the camera more effectively, and a new strategy of alternating the loss function, allowing the model to improve its accuracy in predicting challenging poses. By conducting an inverse analysis of the weight matrix, the importance of each IMU was investigated for device simplification purposes. The proposed method was verified by using the Total Capture dataset with two hypothetical occlusion conditions, and the result showed that only five IMUs can make the accuracy stable in different occlusion situations.

A Novel Ranging and IMU-Based Method for Relative Positioning of Two-MAV Formation in GNSS-Denied Environments.

Global Navigation Satellite Systems (GNSS) with weak anti-jamming capability are vulnerable to intentional or unintentional interference, resulting in difficulty providing continuous, reliable, and accurate positioning information in complex environments. Especially in GNSS-denied environments, relying solely on the onboard Inertial Measurement Unit (IMU) of the Micro Aerial Vehicles (MAVs) for positioning is not practical. In this paper, we propose a novel cooperative relative positioning method for MAVs in GNSS-denied scenarios. Specifically, the system model framework is first constructed, and then the Extended Kalman Filter (EKF) algorithm, which is introduced for its ability to handle nonlinear systems, is employed to fuse inter-vehicle ranging and onboard IMU information, achieving joint position estimation of the MAVs. The proposed method mainly addresses the problem of error accumulation in the IMU and exhibits high accuracy and robustness. Additionally, the method is capable of achieving relative positioning without requiring an accurate reference anchor. The system observability conditions are theoretically derived, which means the system positioning accuracy can be guaranteed when the system satisfies the observability conditions. The results further demonstrate the validity of the system observability conditions and investigate the impact of varying ranging errors on the positioning accuracy and stability. The proposed method achieves a positioning accuracy of approximately 0.55 m, which is about 3.89 times higher than that of an existing positioning method.

A Tightly Coupled Feature-Based Visual-Inertial Odometry With Stereo Cameras

Early works have shown that inertial measurement unit (IMU) can help visual odometry to achieve more accurate pose estimation. However, existing methods mainly focus on fusing visual and inertial information in the back end, while ignoring it in the front end. In this paper, we present a novel Feature-based Visual-Inertial Odometry for Stereo cameras, namely FSVIO, which makes full use of visual and inertial information in both the front and the back ends. Specifically, we firstly introduce an IMU-aided feature-based method in the visual processing part of the front end, in which IMU information is used to build robust descriptors for image perspective deformation caused by the camera motion. Then, in order to improve the efficiency of feature matching, we apply a fast-tracking method by predicting the position of feature points in the current frame with the help of combining stereo camera and IMU measurements. Furthermore, the 2D-2D epipolar geometry constraint and the improved Huber norm are introduced into the tightly coupled optimization of the back end, which reduces the influence of incorrect depth estimation from stereo cameras. Finally, our odometry is evaluated on both EuRoC datasets and real-world experiments. The experimental results verified the effectiveness and superiority of FSVIO.

Event-based feature tracking in a visual inertial odometry framework.

Introduction: Event cameras report pixel-wise brightness changes at high temporal resolutions, allowing for high speed tracking of features in visual inertial odometry (VIO) estimation, but require a paradigm shift, as common practices from the past decades using conventional cameras, such as feature detection and tracking, do not translate directly. One method for feature detection and tracking is the Eventbased Kanade-Lucas-Tomasi tracker (EKLT), an hybrid approach that combines frames with events to provide a high speed tracking of features. Despite the high temporal resolution of the events, the local nature of the registration of features imposes conservative limits to the camera motion speed. Methods: Our proposed approach expands on EKLT by relying on the concurrent use of the event-based feature tracker with a visual inertial odometry system performing pose estimation, leveraging frames, events and Inertial Measurement Unit (IMU) information to improve tracking. The problem of temporally combining high-rate IMU information with asynchronous event cameras is solved by means of an asynchronous probabilistic filter, in particular an Unscented Kalman Filter (UKF). The proposed method of feature tracking based on EKLT takes into account the state estimation of the pose estimator running in parallel and provides this information to the feature tracker, resulting in a synergy that can improve not only the feature tracking, but also the pose estimation. This approach can be seen as a feedback, where the state estimation of the filter is fed back into the tracker, which then produces visual information for the filter, creating a "closed loop". Results: The method is tested on rotational motions only, and comparisons between a conventional (not event-based) approach and the proposed approach are made, using synthetic and real datasets. Results support that the use of events for the task improve performance. Discussion: To the best of our knowledge, this is the first work proposing the fusion of visual with inertial information using events cameras by means of an UKF, as well as the use of EKLT in the context of pose estimation. Furthermore, our closed loop approach proved to be an improvement over the base EKLT, resulting in better feature tracking and pose estimation. The inertial information, despite prone to drifting over time, allows keeping track of the features that would otherwise be lost. Then, feature tracking synergically helps estimating and minimizing the drift.

A Versatile Embedded Platform for Implementation of Biocooperative Control in Upper-Limb Neuromotor Rehabilitation Scenarios

Biocooperative control uses both biomechanical and physiological information of the user to achieve a reliable human-robot interaction. In the context of neuromotor rehabilitation, such control can enhance rehabilitation experience and outcomes. However, the high cost and large volume of the commercial systems for physiological signal acquisition are major limitations for the development of such control. We present a highly versatile, low-cost and wearable embedded system that integrates the most commonly used sensors in this field: inertial measurement unit (IMU), electrocardiography (ECG), electromyography (EMG), galvanic skin response (GSR) and skin temperature (SKT) sensors. Additionally, the compact system combines wireless communication for data transmission and a high-efficiency microcontroller for real-time signal processing and control. We tested the system in two common neuromotor rehabilitation scenarios. The first is an upper-limb rehabilitation VR-based exergame, in which the patient must collect as many coins as possible. Movement recognition of the hand and arm is performed based on EMG and IMU information, respectively. The second is adaptive assistive control that adjusts the level of assistance of a wrist rehabilitation robot according to the physiological state and motor performance of the patient using GSR, ECG and SKT data. The quality of the recorded signals and the processing capacity of the system meet the needs of the two upper-limb rehabilitation applications. The wearable system is highly versatile, open, configurable and low cost, and it could promote the development of real-time biocooperative control for a wide range of neuromotor rehabilitation applications.

Research on Multi-Sensor Fusion SLAM Algorithm Based on Improved Gmapping

Simultaneous Localization and Mapping (SLAM) is the core technology of the intelligent robot system, and it is also the basis for its autonomous movement. In recent years, it has been found that SLAM using a single sensor has certain limitations, such as Inertial Measurement Unit (IMU) noise and serious drift, and 2D radar can only detect environmental information on the same horizontal plane. In this regard, this paper constructs a multi-sensor back-end fusion SLAM algorithm that combines vision, laser, encoder and IMU information. Experiments have proved that compared with using a single sensor, the application of a multi-sensor fusion system makes the edges of the constructed map clearer and the noise reduced. Aiming at the problem of increased calculation caused by particle degradation and too many particles, this paper improves the Gmappping algorithm, and uses the combination of selective resampling and Kullback-Leibler Distance (KLD) sampling to complete resampling. It has been proved by experiments that compared with the original algorithm of Gmapping, the application of the improved algorithm increases the particle convergence speed by 39.85% in the process of indoor mapping. Aiming at the problems that the traditional loop detection algorithm is easily affected by environmental factors, resulting in low detection accuracy, and the loop detection algorithm based on deep convolutional neural network has a large amount of calculation and takes a long time to detect. The main research of this paper is to apply a deep learning-based loop detection algorithm on the multi-sensor fusion framework, and use the combination of high-dimensional and low-dimensional features of the image for loop detection. This paper uses different algorithms to conduct comparative experiments on the dataset CityCentre. The experimental results show that compared with the traditional algorithms Bag of Words (BoW), AlexNet algorithm, VGG19 algorithm, and ResNet32 algorithm, the accuracy of the algorithm proposed in this paper has increased by 31.26%, 14.21%, 3.05%, and 1.56%, respectively. In addition, the comparison experiment results of SLAM mapping with the original Real-Time Appearance-Based Mapping (RTAB-MAP) algorithm prove that the loop closure detection algorithm based on deep learning proposed in this paper can enable the system to better build a globally consistent map, including more environmental information.

Development of an Online Adaptive Parameter Tuning vSLAM Algorithm for UAVs in GPS-Denied Environments.

In recent years, unmanned aerial vehicles (UAVs) have been applied in many fields owing to their mature flight control technology and easy-to-operate characteristics. No doubt, these UAV-related applications rely heavily on location information provided by the positioning system. Most UAVs nowadays use a global navigation satellite system (GNSS) to obtain location information. However, this outside-in 3rd party positioning system is particularly susceptible to environmental interference and cannot be used in indoor environments, which limits the application diversity of UAVs. To deal with this problem, in this paper, a stereo-based visual simultaneous localization and mapping technology (vSLAM) is applied. The presented vSLAM algorithm fuses onboard inertial measurement unit (IMU) information to further solve the navigation problem in an unknown environment without the use of a GNSS signal and provides reliable localization information. The overall visual positioning system is based on the stereo parallel tracking and mapping architecture (S-PTAM). However, experiments found that the feature-matching threshold has a significant impact on positioning accuracy. Selection of the threshold is based on the Hamming distance without any physical meaning, which makes the threshold quite difficult to set manually. Therefore, this work develops an online adaptive matching threshold according to the keyframe poses. Experiments show that the developed adaptive matching threshold improves positioning accuracy. Since the attitude calculation of the IMU is carried out based on the Mahony complementary filter, the difference between the measured acceleration and the gravity is used as the metric to online tune the gain value dynamically, which can improve the accuracy of attitude estimation under aggressive motions. Moreover, a static state detection algorithm based on the moving window method and measured acceleration is proposed as well to accurately calculate the conversion mechanism between the vSLAM system and the IMU information; this initialization mechanism can help IMU provide a better initial guess for the bundle adjustment algorithm (BA) in the tracking thread. Finally, a performance evaluation of the proposed algorithm is conducted by the popular EuRoC dataset. All the experimental results show that the developed online adaptive parameter tuning algorithm can effectively improve the vSLAM accuracy and robustness.

An Aerial and Ground Multi-Agent Cooperative Location Framework in GNSS-Challenged Environments

In order to realize the cooperative localization of multi-unmanned platforms in the GNSS-denied environment, this paper proposes a collaborative SLAM (simultaneous localization and mapping, SLAM) framework based on image feature point matching. Without GNSS, a single unmanned platform UGV and UAV (unmanned ground vehicle, UGV; unmanned aerial vehicle, UAV) equipped with vision and IMU (inertial measurement unit, IMU) sensors can exchange information through data communication to jointly build a three-dimensional visual point map, and determine the relative position of each other through visual-based position re- identification and PnP (Perspective-n-Points, PnP) methods. When any agent can receive reliable GNSS signals, GNSS positioning information will greatly improve the positioning accuracy without changing the positioning algorithm framework. In order to achieve this function, we designed a set of two-stage position estimation algorithms. In the first stage, we used the modified ORB-SLAM3 algorithm for position estimation by fusing visual and IMU information. In the second stage, we integrated GNSS positioning and cooperative positioning information using the factor graph optimization (FGO) algorithm. Our framework consists of an UGV as the central server node and three UAVs carried by the UGV, that will collaborate on space exploration missions. Finally, we simulated the influence of different visibility and lighting conditions on the framework function on the virtual simulation experiment platform built based on ROS (robot operating system, ROS) and Unity3D. The accuracy of the cooperative localization algorithm and the single platform localization algorithm was evaluated. In the two cases of GNSS-denied and GNSS-challenged, the error of co-location reduced by 15.5% and 19.7%, respectively, compared with single-platform independent positioning.

Precise and robust sideslip angle estimation based on INS/GNSS integration using invariant extended Kalman filter

Sideslip angle estimation is vital to the safety and active control of autonomous vehicles. In this paper, an innovative vehicle kinematic-based sideslip angle estimation method is proposed. The method is built on multi-sensor fusion, which fuses the information of inertial measurement unit, global navigation satellite system (GNSS), and onboard sensors to continuously estimate the attitude and velocity of the vehicle and thus obtain the sideslip angle. The invariant extended Kalman filter framework is adopted and the left-invariant form is derived to implement the GNSS measurement update. In order to solve the unobservability problem when only a single GNSS receiver is equipped, the vehicle motion constraint is introduced into the filter to improve the accuracy of heading angle estimation. The method is validated by field test and the results show that the method is robust in terms of converge efficiency. Furthermore, the sideslip angle estimation accuracy is satisfactory with the average absolute error less than 0.25°, which meets the active safety control requirements for autonomous driving.

An Enhanced Hybrid Visual-Inertial Odometry System for Indoor Mobile Robot.

As mobile robots are being widely used, accurate localization of the robot counts for the system. Compared with position systems with a single sensor, multi-sensor fusion systems provide better performance and increase the accuracy and robustness. At present, camera and IMU (Inertial Measurement Unit) fusion positioning is extensively studied and many representative Visual–Inertial Odometry (VIO) systems have been produced. Multi-State Constraint Kalman Filter (MSCKF), one of the tightly coupled filtering methods, is characterized by high accuracy and low computational load among typical VIO methods. In the general framework, IMU information is not used after predicting the state and covariance propagation. In this article, we proposed a framework which introduce IMU pre-integration result into MSCKF framework as observation information to improve the system positioning accuracy. Additionally, the system uses the Helmert variance component estimation (HVCE) method to adjust the weight between feature points and pre-integration to further improve the positioning accuracy. Similarly, this article uses the wheel odometer information of the mobile robot to perform zero speed detection, zero-speed update, and pre-integration update to enhance the positioning accuracy of the system. Finally, after experiments carried out in Gazebo simulation environment, public dataset and real scenarios, it is proved that the proposed algorithm has better accuracy results while ensuring real-time performance than existing mainstream algorithms.

Autonomous Navigation System of Greenhouse Mobile Robot Based on 3D Lidar and 2D Lidar SLAM.

The application of mobile robots is an important link in the development of intelligent greenhouses. In view of the complex environment of a greenhouse, achieving precise positioning and navigation by robots has become the primary problem to be solved. Simultaneous localization and mapping (SLAM) technology is a hot spot in solving the positioning and navigation in an unknown indoor environment in recent years. Among them, the SLAM based on a two-dimensional (2D) Lidar can only collect the environmental information at the level of Lidar, while the SLAM based on a 3D Lidar demands a high computation cost; hence, it has higher requirements for the industrial computers. In this study, the robot navigation control system initially filtered the information of a 3D greenhouse environment collected by a 3D Lidar and fused the information into 2D information, and then, based on the robot odometers and inertial measurement unit information, the system has achieved a timely positioning and construction of the greenhouse environment by a robot using a 2D Lidar SLAM algorithm in Cartographer. This method not only ensures the accuracy of a greenhouse environmental map but also reduces the performance requirements on the industrial computer. In terms of path planning, the Dijkstra algorithm was used to plan the global navigation path of the robot while the Dynamic Window Approach (DWA) algorithm was used to plan the local navigation path of the robot. Through the positioning test, the average position deviation of the robot from the target positioning point is less than 8 cm with a standard deviation (SD) of less than 3 cm; the average course deviation is less than 3° with an SD of less than 1° at the moving speed of 0.4 m/s. The robot moves at the speed of 0.2, 0.4, and 0.6 m/s, respectively; the average lateral deviation between the actual movement path and the target movement path is less than 10 cm, and the SD is less than 6 cm; the average course deviation is <3°, and the SD is <1.5°. Both the positioning accuracy and the navigation accuracy of the robot can meet the requirements of mobile navigation and positioning in the greenhouse environment.

Object Detection Deployed on UAVs for Oblique Images by Fusing IMU Information

Object detection is a very challenging task due to the serious object scale diversity. There is an obvious scale distribution in the oblique images captured by the unmanned aerial vehicles (UAVs): the objects at the top of the image are smaller in scale, while the objects at the bottom of the image are larger in scale. Based on this prior information, we propose an object detector with the divide-and-conquer strategy. First, we estimate the object scale using inertial measurement unit (IMU) information. Then the small objects at the top of image are detected by shallow networks with small receptive field and the big objects at the bottom of image are detected by deep networks with big receptive field. Compared with YOLOv5, our method improves the accuracy by 4.6&#x0025; on mean of average precision (mAP) metric and improves the speed by 79&#x0025;. Our method can also be performed in real-time on an NVIDIA XAVIER NX with about 30 frames/s. The code is made available on GitHub (<uri>https://github.com/bitshenwenxiao/UAVYOLO</uri>).

Information sparsification for visual-inertial odometry by manipulating Bayes tree

A new information sparsification method is developed for visual-inertial odometry (VIO) used for exploratory unmanned aerial vehicles (UAV's). While most of the existing methods are designed for global (and thus postprocessing) bundle adjustment (BA) problems, our method is specifically designed to run incrementally on a local BA formulation in real time. The majority of the existing state-of-the-art methods are designed for pose graph optimization (PGO). Unlike PGO problems where the only variables to be optimized are robot poses, a combination of pose, velocity, and inertial measurement unit (IMU) bias is used in VIO. Existing approaches to sparsification cannot be directly applied to this formulation. Therefore, we design a trick to split the dense information matrix into two parts: IMU information and purely visual information and by doing so, existing methods of sparsification can be reused and applied to the purely visual information, which accounts for most of the nonzero entries within the dense information matrix. In addition, we design a new way of summarizing the dense information matrix: using Bayes tree in an incremental smoothing framework for fast data retrieval. Results using public benchmark dataset EuRoC show that the marginalized and sparsified smoother achieves the primary goal of power saving in terms of shortened pipeline cycle time while maintaining absolute trajectory accuracies comparable to that of the complete formulation and better than those offered by fellow sparsification solutions.

An EKF-based multiple data fusion for mobile robot indoor localization

Purpose Indoor localization is a key tool for robot navigation in indoor environments. Traditionally, robot navigation depends on one sensor to perform autonomous localization. This paper aims to enhance the navigation performance of mobile robots, a multiple data fusion (MDF) method is proposed for indoor environments. Design/methodology/approach Here, multiple sensor data i.e. collected information of inertial measurement unit, odometer and laser radar, are used. Then, an extended Kalman filter (EKF) is used to incorporate these multiple data and the mobile robot can perform autonomous localization according to the proposed EKF-based MDF method in complex indoor environments. Findings The proposed method has experimentally been verified in the different indoor environments, i.e. office, passageway and exhibition hall. Experimental results show that the EKF-based MDF method can achieve the best localization performance and robustness in the process of navigation. Originality/value Indoor localization precision is mostly related to the collected data from multiple sensors. The proposed method can incorporate these collected data reasonably and can guide the mobile robot to perform autonomous navigation (AN) in indoor environments. Therefore, the output of this paper would be used for AN in complex and unknown indoor environments.

Terrain classification and adaptive locomotion for a hexapod robot Qingzhui

Legged robots have potential advantages in mobility compared with wheeled robots in outdoor environments. The knowledge of various ground properties and adaptive locomotion based on different surface materials plays an important role in improving the stability of legged robots. A terrain classification and adaptive locomotion method for a hexapod robot named Qingzhui is proposed in this paper. First, a force-based terrain classification method is suggested. Ground contact force is calculated by collecting joint torques and inertial measurement unit information. Ground substrates are classified with the feature vector extracted from the collected data using the support vector machine algorithm. Then, an adaptive locomotion on different ground properties is proposed. The dynamic alternating tripod trotting gait is developed to control the robot, and the parameters of active compliance control change with the terrain. Finally, the method is integrated on a hexapod robot and tested by real experiments. Our method is shown effective for the hexapod robot to walk on concrete, wood, grass, and foam. The strategies and experimental results can be a valuable reference for other legged robots applied in outdoor environments.

Joint optimization based on direct sparse stereo visual-inertial odometry

This paper proposes a novel fusion of an inertial measurement unit (IMU) and stereo camera method based on direct sparse odometry (DSO) and stereo DSO. It jointly optimizes all model parameters within a sliding window, including the inverse depth of all selected pixels and the internal or external camera parameters of all keyframes. The vision part uses a photometric error function that optimizes 3D geometry and camera pose in a combined energy functional. The proposed algorithm uses image blocks to extract neighboring image features and directly forms measurement residuals in the image intensity space. A fixed-baseline stereo camera solves scale drift. IMU information is accumulated between several frames using manifold pre-integration and is inserted into the optimization as additional constraints between keyframes. The scale and gravity inserted are incorporated into the stereo visual inertial odometry model and are optimized together with other variables such as poses. The experimental results show that the tracking accuracy and robustness of the proposed method are superior to those of the state-of-the-art fused IMU method. In addition, compared with previous semi-dense direct methods, the proposed method displays a higher reconstruction density and scene recovery.

Fast and robust visual odometry with a low-cost IMU in dynamic environments

PurposeTo realize stable and precise localization in the dynamic environments, the authors propose a fast and robust visual odometry (VO) approach with a low-cost Inertial Measurement Unit (IMU) in this study.Design/methodology/approachThe proposed VO incorporates the direct method with the indirect method to track the features and to optimize the camera pose. It initializes the positions of tracked pixels with the IMU information. Besides, the tracked pixels are refined by minimizing the photometric errors. Due to the small convergence radius of the indirect method, the dynamic pixels are rejected. Subsequently, the camera pose is optimized by minimizing the reprojection errors. The frames with little dynamic information are selected to create keyframes. Finally, the local bundle adjustment is performed to refine the poses of the keyframes and the positions of 3-D points.FindingsThe proposed VO approach is evaluated experimentally in dynamic environments with various motion types, suggesting that the proposed approach achieves more accurate and stable location than the conventional approach. Moreover, the proposed VO approach works well in the environments with the motion blur.Originality/valueThe proposed approach fuses the indirect method and the direct method with the IMU information, which improves the localization in dynamic environments significantly.