4.2 Article

Real-time monocular visual-inertial SLAM with structural constraints of line and point-line fusion

Related references

Note: Only part of the references are listed.
Article Engineering, Electrical & Electronic

A Real-Time Stereo Visual-Inertial SLAM System Based on Point-and-Line Features

Xin Liu et al.

Summary: In this study, a real-time stereo visual-inertial SLAM system based on point-and-line features is proposed, which improves the front-end process of VINS fusion and adds line features on the basis of existing point features. The method achieves higher accuracy in real-time matching of line features and achieves high precision matching by predicting line features through IMU-assisted optical flow tracking.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2023)

Article Robotics

EPLF-VINS: Real-Time Monocular Visual-Inertial SLAM With Efficient Point-Line Flow Features

Lei Xu et al.

Summary: This letter presents an efficient visual-inertial simultaneous localization and mapping (SLAM) method using both point and line features. Existing point-based SLAM methods have limitations in scenarios with weak textures and motion blur. Researchers have attempted to develop line-based SLAM systems due to the excellent properties of line features in space. However, computational effort and incorrect line detection and matching have limited the real-time performance and accuracy improvement. In this letter, we propose improvements in line detection and matching, resulting in high-quality line features for SLAM constraints, as well as a line optical flow tracking method and an independent measurement model for estimating line residuals, which enhance the efficiency and accuracy of the algorithm.

IEEE ROBOTICS AND AUTOMATION LETTERS (2023)

Article Engineering, Electrical & Electronic

Multi-Stage Refinement Feature Matching Using Adaptive ORB Features for Robotic Vision Navigation

Chao Sun et al.

Summary: This paper proposes a multi-stage refinement matching technique, combined with the adaptive ORB feature extraction method, to develop a KTBER_AORB model that can outperform the state-of-the-art feature extraction and matching techniques. Experimental results demonstrate that the KTBER_AORB model outperforms other state-of-the-art feature matching techniques in terms of accuracy and robustness, while maintaining higher efficiency.

IEEE SENSORS JOURNAL (2022)

Article Computer Science, Artificial Intelligence

SIFT Matching by Context Exposed

Fabio Bellavia

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Computer Science, Artificial Intelligence

luvHarris: A Practical Corner Detector for Event-Cameras

Arren Glover et al.

Summary: In this paper, a corner detection method named look-up event-Harris (luvHarris) is proposed for event cameras. It achieves high accuracy while improving event throughput by using the Harris algorithm and a novel threshold ordinal event-surface. The method minimizes computational load per event and performs convolutions only as computational resources become available. The proposed approach outperforms current state-of-the-art methods in terms of speed and is suitable for real-time use with high-resolution event cameras.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

Article Engineering, Electrical & Electronic

PLJ-SLAM: Monocular Visual SLAM With Points, Lines, and Junctions of Coplanar Lines

Guangli Ren et al.

Summary: This paper proposes a multi-feature monocular SLAM method for indoor environments, which utilizes ORB points, lines, and junctions of coplanar lines. By optimizing the camera pose through multiple constraints of ORB points, lines, and junctions of the coplanar lines, the performance of monocular SLAM is improved.

IEEE SENSORS JOURNAL (2022)

Article Automation & Control Systems

PLC-VIO: Visual-Inertial Odometry Based on Point-Line Constraints

Zhe Liu et al.

Summary: This article introduces a novel tightly coupled monocular VIO system based on point-line constraints, achieving accurate localization through line segment extraction, merging, and feature tracking. Experimental evaluations demonstrate the system's effectiveness and robustness compared to state-of-the-art systems, without compromising real-time performance.

IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING (2022)

Article Robotics

Kalman-Filter-Based, Dynamic 3-D Shape Reconstruction for Steerable Needles With Fiber Bragg Gratings in Multicore Fibers

Abdulhamit Donder et al.

Summary: Steerable needles are a promising technology for safe deployment of tools in minimally invasive surgery, especially in tumor-related procedures. Fiber Bragg gratings (FBGs) have advantages in soft tissue localization due to their flexibility and lack of electromagnetic interference. A novel approach was proposed in this study to reconstruct the shape of the path created by the steerable needle tip, with a Kalman-filter-based sensor fusion method for updating curvature information. Validation through simulation and experiments with a programmable bevel-tip steerable needle (PBN) showed clinically acceptable accuracy.

IEEE TRANSACTIONS ON ROBOTICS (2022)

Article Computer Science, Information Systems

Research on Adaptive ORB-SURF Image Matching Algorithm Based on Fusion of Edge Features

Leng Han et al.

Summary: In this paper, an improved adaptive ORB-SURF image matching algorithm is proposed, which extracts image feature points using an improved ORB algorithm and fuses edge features. The algorithm uses SURF descriptors for feature description and employs the FLANN algorithm for adaptive feature matching. The RANSAC algorithm is used to eliminate false matching point pairs, leading to improved accuracy and reduced matching time.

IEEE ACCESS (2022)

Article Computer Science, Information Systems

Visual SLAM Based on Semantic Segmentation and Geometric Constraints for Dynamic Indoor Environments

Shiqiang Yang et al.

Summary: This paper improves the positioning accuracy of the SLAM system by combining semantic information and a geometric constraint algorithm based on feature point homogenization. It proposes a feature point homogenization algorithm based on quadtree and adaptive threshold to solve the problem of concentrated feature points and low extraction rate in weak texture areas. Additionally, it filters out dynamic information and constructs a semantic map to reduce redundancy and improve map quality.

IEEE ACCESS (2022)

Article Engineering, Electrical & Electronic

Feasibility Study of Drone-Based 3-D Measurement of Defects in Concrete Structures

Daniele Marchisotti et al.

Summary: Recognition of defects in concrete structures is crucial for structural damage detection. The use of drones and 3-D reconstruction techniques can improve the accuracy of defect identification and evaluation.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2022)

Article Computer Science, Information Systems

LSDNet: Trainable Modification of LSD Algorithm for Real-Time Line Segment Detection

Lev Teplyakov et al.

Summary: The study introduces a fast and accurate CNN-based line segment detector, LSDNet, by incorporating a lightweight CNN into a traditional LSD detector. Experimental results show that LSDNet achieves the best performance in terms of speed and accuracy on the Wireframe dataset.

IEEE ACCESS (2022)

Article Engineering, Electrical & Electronic

PLS-VINS: Visual Inertial State Estimator With Point-Line Features Fusion and Structural Constraints

Gaochao Yang et al.

Summary: The proposed visual-inertial state estimator system based on point-line features and structure constraints enhances feature extraction performance in various scenarios and improves accuracy of pose estimation. It outperforms state-of-the-art methods in different scenarios and is particularly effective in environments with scarce or unevenly distributed point features.

IEEE SENSORS JOURNAL (2021)

Article Robotics

ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial, and Multimap SLAM

Carlos Campos et al.

Summary: ORB-SLAM3 is the first system capable of performing various SLAM tasks, including visual, visual-inertial, and multi-map SLAM, with improved accuracy and robustness, while also being able to survive in situations with poor visual information and achieve high accuracy.

IEEE TRANSACTIONS ON ROBOTICS (2021)

Article Robotics

PLF-VINS: Real-Time Monocular Visual-Inertial SLAM With Point-Line Fusion and Parallel-Line Fusion

Junesuk Lee et al.

Summary: This method improves localization accuracy by integrating corner and line features as well as parallel 3D lines, and experimental results demonstrate its effectiveness.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

A Point-Line VIO System With Novel Feature Hybrids and With Novel Line Predicting-Matching

Hao Wei et al.

Summary: The study proposed a point-line-based VIO system with novel feature hybrids and predicting-matching method to improve reliability and stability in challenging scenes. Experimental results demonstrate the method's superiority in accuracy.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Proceedings Paper Automation & Control Systems

A Visual Inertial Odometry Framework for 3D Points, Lines and Planes

Shenbagaraj Kannapiran et al.

Summary: This paper addresses the challenge of recovering rigid registration between successive camera poses in feature-poor environments using 3D geometric entities. By directly exploiting these entities, improved registration is achieved, suitable for small mobile robots.

2021 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2021)

Proceedings Paper Automation & Control Systems

OpenVINS: A Research Platform for Visual-Inertial Estimation

Patrick Geneva et al.

2020 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2020)

Article Robotics

Improving Visual Feature Extraction in Glacial Environments

Steven D. Morad et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

PL-SLAM: A Stereo SLAM System Through the Combination of Points and Line Segments

Ruben Gomez-Ojeda et al.

IEEE TRANSACTIONS ON ROBOTICS (2019)

Article Robotics

VINS-Mono: A Robust and Versatile Monocular Visual-Inertial State Estimator

Tong Qin et al.

IEEE TRANSACTIONS ON ROBOTICS (2018)

Article Robotics

ORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras

Raul Mur-Artal et al.

IEEE TRANSACTIONS ON ROBOTICS (2017)

Article Robotics

The EuRoC micro aerial vehicle datasets

Michael Burri et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2016)

Article Robotics

Building a 3-D Line-Based Map Using Stereo SLAM

Guoxuan Zhang et al.

IEEE TRANSACTIONS ON ROBOTICS (2015)

Article Robotics

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

Raul Mur-Artal et al.

IEEE TRANSACTIONS ON ROBOTICS (2015)

Article Computer Science, Artificial Intelligence

Nonlinear estimation of the fundamental matrix with minimal parameters

A Bartoli et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2004)