A Semi-Direct Monocular Visual SLAM Algorithm in Complex Environments

Purpose – The purpose of this paper is to present a Rao–Blackwellized particle filter (RBPF) approach for the visual simultaneous localization and mapping (SLAM) of small unmanned aerial vehicles (UAVs). Design/methodology/approach – Measurements from inertial measurement unit, barometric altimeter and monocular camera are fused to estimate the state of the vehicle while building a feature map. In this SLAM framework, an extra factorization method is proposed to partition the vehicle model into subspaces as the internal and external states. The internal state is estimated by an extended Kalman filter (EKF). A particle filter is employed for the external state estimation and parallel EKFs are for the map management. Findings – Simulation results indicate that the proposed approach is more stable and accurate than other existing marginalized particle filter-based SLAM algorithms. Experiments are also carried out to verify the effectiveness of this SLAM method by comparing with a referential global positioning system/inertial navigation system. Originality/value – The main contribution of this paper is the theoretical derivation and experimental application of the Rao–Blackwellized visual SLAM algorithm with vehicle model partition for small UAVs.

Download Full-text

An embedded visual SLAM algorithm based on Kinect and ORB features

2015 34th Chinese Control Conference (CCC) ◽

10.1109/chicc.2015.7260583 ◽

2015 ◽

Cited By ~ 2

Author(s):

Xu Fen ◽

Wang Zhen

Keyword(s):

Visual Slam ◽

Slam Algorithm

Download Full-text

Grid-Based Visual SLAM in Complex Environments

Journal of Intelligent & Robotic Systems ◽

10.1007/s10846-007-9163-8 ◽

2007 ◽

Vol 50 (3) ◽

pp. 241-255 ◽

Cited By ~ 5

Author(s):

Young-Ho Choi ◽

Se-Young Oh

Keyword(s):

Visual Slam ◽

Complex Environments ◽

Grid Based

Download Full-text

Improved Point-Line Feature Based Visual SLAM Method for Complex Environments

Sensors ◽

10.3390/s21134604 ◽

2021 ◽

Vol 21 (13) ◽

pp. 4604

Author(s):

Fei Zhou ◽

Limin Zhang ◽

Chaolong Deng ◽

Xinyue Fan

Keyword(s):

Visual Slam ◽

Complex Environments ◽

Line Segments ◽

Structure Information ◽

Line Feature ◽

Localization And Mapping ◽

Feature Based ◽

Line Features ◽

Point Line ◽

Local Adaptive Threshold

Traditional visual simultaneous localization and mapping (SLAM) systems rely on point features to estimate camera trajectories. However, feature-based systems are usually not robust in complex environments such as weak textures or obvious brightness changes. To solve this problem, we used more environmental structure information by introducing line segments features and designed a monocular visual SLAM system. This system combines points and line segments to effectively make up for the shortcomings of traditional positioning based only on point features. First, ORB algorithm based on local adaptive threshold was proposed. Subsequently, we not only optimized the extracted line features, but also added a screening step before the traditional descriptor matching to combine the point features matching results with the line features matching. Finally, the weighting idea was introduced. When constructing the optimized cost function, we allocated weights reasonably according to the richness and dispersion of features. Our evaluation on publicly available datasets demonstrated that the improved point-line feature method is competitive with the state-of-the-art methods. In addition, the trajectory graph significantly reduced drift and loss, which proves that our system increases the robustness of SLAM.

Download Full-text

Cooperative Visual SLAM based on Adaptive Covariance Intersection

Journal of Advanced Engineering and Computation ◽

10.25073/jaec.201823.91 ◽

2018 ◽

Vol 2 (3) ◽

pp. 151 ◽

Cited By ~ 3

Author(s):

Fethi Denim ◽

Abdelkrim Nemra ◽

Kahina Louadj ◽

Abdelghani Boucheloukh ◽

Mustapha Hamerlain ◽

...

Keyword(s):

Stereo Vision ◽

Variable Structure ◽

Uncertain System ◽

Visual Slam ◽

Creative Commons ◽

Localization And Mapping ◽

Covariance Intersection ◽

Position Data ◽

Modelling Uncertainties ◽

Slam Algorithm

Simultaneous localization and mapping (SLAM) is an essential capability for Unmanned Ground Vehicles (UGVs) travelling in unknown environments where globally accurate position data as GPS is not available. It is an important topic in the autonomous mobile robot research. This paper presents an Adaptive De-centralized Cooperative Vision-based SLAM solution for multiple UGVs, using the Adaptive Covariance Intersection (ACI) supported by a stereo vision sensor. In recent years, SLAM problem has gotten a specific consideration, the most commonly used approaches are the EKF-SLAM algorithm and the FAST-SLAM algorithm. The primary, which requires an accurate process and an observation model, suffers from the linearization problem. The last mentioned is not suitable for real-time implementation. In our work, the Visual SLAM (VSLAM) problem could be solved based on the Smooth Variable Structure Filter (SVSF) is proposed. This new filter is robust and stable to modelling uncertainties making it suitable for UGV localization and mapping problem. This new strategy retains the near optimal performance of the SVSF when applied to an uncertain system, it has the added benefit of presenting a considerable improvement in the robustness of the estimation process. All UGVs will add data features sorted by the ACI that estimate position on the global map. This solution gives, as a result, a large reliable map constructed by a group of UGVs plotted on it. This paper presents a Cooperative SVSF-VSLAM algorithm that contributes to solve the Adaptive Cooperative Vision SLAM problem for multiple UGVs. The algorithm was implemented on three mobile robots Pioneer 3-AT, using stereo vision sensors. Simulation results show eciency and give an advantage to our proposed algorithm, compared to the Cooperative EKF-VSLAM algorithm mainly concerning the noise quality. This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Download Full-text

Research on the Application of Visual SLAM in Embedded GPU

Wireless Communications and Mobile Computing ◽

10.1155/2021/6691262 ◽

2021 ◽

Vol 2021 ◽

pp. 1-17

Author(s):

Tianji Ma ◽

Nanyang Bai ◽

Wentao Shi ◽

Xi Wu ◽

Lutao Wang ◽

...

Keyword(s):

High Performance ◽

Three Dimensional ◽

Image Data ◽

Operating Efficiency ◽

Visual Slam ◽

Mobile Platforms ◽

Unknown Environment ◽

Localization And Mapping ◽

Slam Algorithm ◽

Embedded Gpu

In the automatic navigation robot field, robotic autonomous positioning is one of the most difficult challenges. Simultaneous localization and mapping (SLAM) technology can incrementally construct a map of the robot’s moving path in an unknown environment while estimating the position of the robot in the map, providing an effective solution for robots to fully navigate autonomously. The camera can obtain corresponding two-dimensional digital images from the real three-dimensional world. These images contain very rich colour, texture information, and highly recognizable features, which provide indispensable information for robots to understand and recognize the environment based on the ability to autonomously explore the unknown environment. Therefore, more and more researchers use cameras to solve SLAM problems, also known as visual SLAM. Visual SLAM needs to process a large number of image data collected by the camera, which has high performance requirements for computing hardware, and thus, its application on embedded mobile platforms is greatly limited. This paper presents a parallelization method based on embedded hardware equipped with embedded GPU. Use CUDA, a parallel computing platform, to accelerate the visual front-end processing of the visual SLAM algorithm. Extensive experiments are done to verify the effectiveness of the method. The results show that the presented method effectively improves the operating efficiency of the visual SLAM algorithm and ensures the original accuracy of the algorithm.

Download Full-text