MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry

Company-Corcoles, Joan P.; Garcia-Fidalgo, Emilio; Ortiz, Alberto

doi:10.1109/lra.2022.3142900

Cited by 20 publications

(18 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al (2022) proposed a perspective transformation model for camera patches that can be directly incorporated into the error function of the direct method or feature point method, enhancing algorithm accuracy. Company-Corcoles et al (2022) introduced new spatial constraints to object-level SLAM, including proportional constraints, symmetric texture constraints and plane support constraints and verified the positive effect of this approach on enhancing SLAM system performance using public data sets. In low-light environments, long exposures result in motion blur, while short exposures introduce image noise.…”

Section: Some Of the Latest Research In Visual Simultaneous Localizat...mentioning

confidence: 84%

“…Indirect methods use feature point extraction and matching (such as corners and edges) for localization and mapping (Campos et al , 2021; Company-Corcoles et al , 2022; Mur-Artal et al , 2015; Mur-Artal and Tardós, 2017). They first detect and extract distinctive feature points in the images and then estimate camera motion and scene depth by matching these feature points.…”

Section: Standard Procedures For Classic Simultaneous Localization An...mentioning

confidence: 99%

“…Point-based visual SLAM algorithms tend to suffer performance degradation in low-texture scenes. To overcome this problem, Company-Corcoles et al (2022) modified the initialization and optimization process of Visual SLAM algorithms in Manhattan environments based on the characteristics of indoor Manhattan environments and added support for line features. Additionally, due to the sparse nature of maps generated using point features, Lim et al (2022) proposed a Visual SLAM approach that integrates line features to enrich map information.…”

Section: Some Of the Latest Research In Visual Simultaneous Localizat...mentioning

confidence: 99%

See 2 more Smart Citations

A review of visual SLAM with dynamic objects

Qin,

2023

View full text Add to dashboard Cite

Purpose This paper aims to provide a better understanding of the challenges and potential solutions in Visual Simultaneous Localization and Mapping (SLAM), laying the foundation for its applications in autonomous navigation, intelligent driving and other related domains. Design/methodology/approach In analyzing the latest research, the review presents representative achievements, including methods to enhance efficiency, robustness and accuracy. Additionally, the review provides insights into the future development direction of Visual SLAM, emphasizing the importance of improving system robustness when dealing with dynamic environments. The research methodology of this review involves a literature review and data set analysis, enabling a comprehensive understanding of the current status and prospects in the field of Visual SLAM. Findings This review aims to comprehensively evaluate the latest advances and challenges in the field of Visual SLAM. By collecting and analyzing relevant research papers and classic data sets, it reveals the current issues faced by Visual SLAM in complex environments and proposes potential solutions. The review begins by introducing the fundamental principles and application areas of Visual SLAM, followed by an in-depth discussion of the challenges encountered when dealing with dynamic objects and complex environments. To enhance the performance of SLAM algorithms, researchers have made progress by integrating different sensor modalities, improving feature extraction and incorporating deep learning techniques, driving advancements in the field. Originality/value To the best of the authors’ knowledge, the originality of this review lies in its in-depth analysis of current research hotspots and predictions for future development, providing valuable references for researchers in this field.

show abstract

Section: Some Of the Latest Research In Visual Simultaneous Localizat...mentioning

confidence: 84%

Section: Standard Procedures For Classic Simultaneous Localization An...mentioning

confidence: 99%

Section: Some Of the Latest Research In Visual Simultaneous Localizat...mentioning

confidence: 99%

See 1 more Smart Citation

A review of visual SLAM with dynamic objects

Qin,

2023

View full text Add to dashboard Cite

show abstract

“…Li et al [21] proposed a framework which can robustly utilize the Manhattan world structure and a method to detect Manhattan Frames (MF) directly from planes, allowing the system to model the scene as a mixture of Manhattan Frames. Company-Corcoles et al [22], after combining points, lines, and the Manhattan axis of the scene, calculated the reprojection error of points and lines to optimize the camera pose through local map optimization. Li et al [23] proposed a decoupling-refinement method based on points, lines, and planes, as well as the use of Manhattan relationships in an additional pose refinement module.…”

Section: Related Workmentioning

confidence: 99%

A Visual SLAM Approach to Deeply Explore the Spatial Constraints in Indoor Environment Based on the Manhattan Hypothesis

Zhang

Liu

et al. 2023

Journal of Sensors

View full text Add to dashboard Cite

It is a major challenge for a visual SLAM system to maintain a highly precise and robust mapping and localization ability in an environment with low texture. In this paper, a bundle adjustment method for deeply exploring the spatial constraints based on the Manhattan hypothesis is proposed. First, an energy function for filtering the feature set and segmenting the point cloud is given, and a semantic graph is formed with the minimum energy. Then, a novel factor graph for back-end bundle adjustment is designed to include points, edges, planes, and spatial constraints to improve the stability and positioning accuracy of the system. After that, the corresponding error items of those spatial constraints for bundle adjustment are designed according to the Manhattan hypothesis. Finally, comparison tests are designed to evaluate the performance of the given approach using TUM RGB-D datasets in different scenes. Test results show that the proposed method provides better positioning ability, with the positioning accuracy improved by 18.07% on average compared with that of existing mainstream approaches.

show abstract

“…Therefore, complementary sensors are fused to improve the stability of the algorithm, such as the fusion of cameras and inertial measurement sensors (IMU) to obtain visual-inertial odometry (VIO) [2] .In the current VIO framework, nonlinear optimization and Kalman filtering are two mainstream information fusion frameworks. The mileage calculation method represented by nonlinear optimization is VINS [3] , MSC_VO [4] etc. The representative based on Kalman filter implementation is ROVIO [5] and MSCKF_VIO [6] etc.…”

Section: Introductionmentioning

confidence: 99%

Robust visual odometry based on image enhancement

Gao

Yang

Wang

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

With the rise of augmented reality and autonomous driving, visual SLAM (simultaneous localization and mapping) has become the focus of research again. Visual odometry is an important part of visual SLAM. Too dark or too strong light will reduce the image quality, resulting in a large deviation in the visual odometry trajectory. Therefore, this paper proposes a visual odometry with image enhancement. Identify the lighting state of the image by estimating the brightness value of the input image. Gamma correction based on truncated cumulative distribution function modulation is used to enhance images that are too dark. For too strong images, negative image strategy is used. An improved algorithm can boost the detailed texture of the image in a poor lighting environment accurately, thereby improving the accuracy of feature point matching and the precision of the pose estimation. Tests on the public EuRoC dataset demonstrate that the presented algorithm has better localization precision and robustness.

show abstract

MSC-VO: Exploiting Manhattan and Structural Constraints for Visual Odometry

Cited by 20 publications

References 21 publications

A review of visual SLAM with dynamic objects

A review of visual SLAM with dynamic objects

A Visual SLAM Approach to Deeply Explore the Spatial Constraints in Indoor Environment Based on the Manhattan Hypothesis

Robust visual odometry based on image enhancement

Contact Info

Product

Resources

About