☆ 4.6 Review

Visual SLAM: What Are the Current Trends and What to Expect?

SENSORS (2022)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

Event-Based Vision: A Survey

Guillermo Gallego et al.

Summary: This paper provides a comprehensive overview of event-based vision, focusing on the applications and algorithms developed for event cameras. Event cameras differ from traditional cameras in their asynchronous measurement of per-pixel brightness changes, offering high temporal resolution, very high dynamic range, low power consumption, and high pixel bandwidth. The paper discusses techniques for processing events, including learning-based methods and specialized processors. It also highlights the remaining challenges and opportunities in the field of bio-inspired perception and interaction for machines.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2022)

添加到收藏夹

Article Robotics

NTU VIRAL: A visual-inertial-ranging-lidar dataset, from an aerial vehicle viewpoint

Thien-Minh Nguyen et al.

Summary: Research has shown a relative lack of public datasets for autonomous aerial systems, which led researchers to conduct data collection exercises on an aerial platform equipped with a variety of sensors in order to fill this gap and record multiple datasets.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2022)

添加到收藏夹

Article Environmental Sciences

A Robot Pose Estimation Optimized Visual SLAM Algorithm Based on CO-HDC Instance Segmentation Network for Dynamic Scenes

Jinjie Chen et al.

Summary: This paper proposes a contour optimization hybrid dilated convolutional neural network (CO-HDC) algorithm to improve the accuracy of visual SLAM algorithms in dynamic scenes. The algorithm increases the receptive field using a hybrid dilated convolutional neural network and enhances contour accuracy using a contour quality evaluation algorithm. Experimental results show that the proposed algorithm outperforms traditional methods in pose estimation and map construction.

REMOTE SENSING (2022)

添加到收藏夹

Article Construction & Building Technology

Real-time indoor localization with visual SLAM for in-building emergency response

Po-Yen Tseng et al.

Summary: This paper presents an economical indoor localization system based on visual SLAM, which improves localization accuracy by studying the thresholds for key features and the amount of image input. It also proposes a comprehensive approach to address matching and accuracy issues under varying lighting conditions, achieving a high localization success rate in actual building tests.

AUTOMATION IN CONSTRUCTION (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Deep introspective SLAM: deep reinforcement learning based approach to avoid tracking failure in visual SLAM

Kanwal Naveed et al.

Summary: Reliable and consistent tracking is crucial for achieving power-on-and-go autonomy in mobile robots. However, current visual navigation and mapping tools often suffer from tracking failures, which hinder real autonomy. In this study, we propose an introspection-based approach (Introspective-SLAM) that evaluates the safety of navigation steps to avoid unsafe ones and plan an alternative path. We also introduce a novel deep reinforcement learning (DQN) based network to evaluate the safety of future navigation steps using a single image.

AUTONOMOUS ROBOTS (2022)

添加到收藏夹

Article Engineering, Civil

A Comparative Analysis of LiDAR SLAM-Based Indoor Navigation for Autonomous Vehicles

Qin Zou et al.

Summary: SLAM is crucial for indoor navigation in autonomous vehicles and robots, with visual SLAM having drawbacks in tracking feature points in environments lacking texture. On the other hand, LiDAR SLAM can offer more robust localization by utilizing 3D spatial information directly captured by LiDAR point clouds.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022)

添加到收藏夹

Article Automation & Control Systems

iRotate: Active Visual SLAM for Omnidirectional Robots

Elia Bonetto et al.

Summary: In this paper, an active visual SLAM approach for omnidirectional robots is presented. The approach aims to simultaneously localize the robot and map the environment while maximizing information gain and minimizing energy consumption. It leverages the robot's independent translation and rotation control and introduces a multi-layered approach for active V-SLAM. The approach achieves similar coverage results with lower overall map entropy and shorter traversed distance compared to other methods.

ROBOTICS AND AUTONOMOUS SYSTEMS (2022)

添加到收藏夹

Review Environmental Sciences

An Overview on Visual SLAM: From Tradition to Semantic

Weifeng Chen et al.

Summary: This paper introduces the development of VSLAM technology and semantic VSLAM based on deep learning. It emphasizes the importance of semantic information for robots to understand the environment and provides some classic VSLAM open-source algorithms.

REMOTE SENSING (2022)

添加到收藏夹

Review Computer Science, Artificial Intelligence

A survey of state-of-the-art on visual SLAM

Iman Abaspur Kazerouni et al.

Summary: This paper provides an overview of Visual Simultaneous Localization and Mapping (V-SLAM), covering basic concepts, state-of-the-art methods in vision and SLAM, and the use of Deep Learning techniques and datasets for Visual Odometry and Loop Closure in V-SLAM applications.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

添加到收藏夹

Article Chemistry, Analytical

Multi-Objective Location and Mapping Based on Deep Learning and Visual Slam

Ying Sun et al.

Summary: SLAM technology is used for locating and mapping in unknown environments, but the constructed maps often lack readability and interactivity, making it difficult to grasp the information accurately. To enable intelligent robots to interact meaningfully with their environment, it is necessary to understand both the geometric and semantic properties of the scene. The proposed method reduces absolute positional errors, constructs dense semantic point cloud maps, and segments point cloud models of objects in the environment with high accuracy.

SENSORS (2022)

添加到收藏夹

Article Robotics

Situational Graphs for Robot Navigation in Structured Indoor Environments

Hriday Bavle et al.

Summary: This study proposes a novel real-time built Situational Graph (S-Graph) that combines the representation of the environment with geometric, semantic, and relational/topological dimensions, along with the robot pose. The method utilizes odometry readings and planar surfaces extracted from 3D LiDAR scans to construct and optimize a three-layered S-Graph, achieving state-of-the-art results in robot pose estimation and contributing to the modeling of the environment with metric-semantic-topological features.

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

添加到收藏夹

Article Computer Science, Information Systems

Real-Time Dynamic SLAM Algorithm Based on Deep Learning

Peng Su et al.

Summary: In this paper, a real-time visual SLAM algorithm based on deep learning is proposed. The algorithm incorporates a lightweight object detection network to extract semantic information in the scene more quickly, and utilizes this information to optimize the homography matrix and calculate more accurate optical flow vectors. Experimental results show that this algorithm effectively reduces the trajectory error of visual SLAM in dynamic environments and improves real-time performance.

IEEE ACCESS (2022)

添加到收藏夹

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)

添加到收藏夹

Article Remote Sensing

CNN-Based Dense Monocular Visual SLAM for Real-Time UAV Exploration in Emergency Conditions

Anne Steenbeek et al.

Summary: This paper investigates the real-time capabilities of a commercial, inexpensive UAV for indoor mapping in emergency conditions. By integrating SLAM and CNN-based depth estimation algorithms using input images, a map of the environment suitable for real-time exploration is generated. The results demonstrate that this method meets the requirements of First Responders in exploring indoor volumes before entering the building.

DRONES (2022)

添加到收藏夹

Article Robotics

A Comprehensive Survey of Visual SLAM Algorithms

Andrea Macario Barros et al.

Summary: This study provides a review of the main algorithms and methods of visual-based SLAM techniques, and compares their advantages and disadvantages. It also proposes six criteria to facilitate the analysis of SLAM algorithms and discusses future directions. The aim of this study is to provide beginners with a clear understanding of technology selection and application in SLAM projects.

ROBOTICS (2022)

添加到收藏夹

Article Automation & Control Systems

iRotate: Active Visual SLAM for Omnidirectional Robots

Elia Bonetto et al.

Summary: This paper presents an active visual SLAM approach for omnidirectional robots, which aims to simultaneously localize and map an unknown environment efficiently. Through multi-layered path planning and execution, the method achieves maximum information gain and reduced energy consumption compared to state-of-the-art methods, with similar coverage results.

ROBOTICS AND AUTONOMOUS SYSTEMS (2022)

添加到收藏夹

Article Engineering, Multidisciplinary

A deep-learning real-time visual SLAM system based on multi-task feature extraction network and self-supervised feature points

Guangqiang Li et al.

Summary: The paper proposes a real-time visual SLAM system based on deep learning, which enhances the accuracy and stability of the system by using a multi-task feature extraction network and self-supervised feature points instead of the traditional feature extractor.

MEASUREMENT (2021)

添加到收藏夹

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)

添加到收藏夹

Review Chemistry, Analytical

Role of Deep Learning in Loop Closure Detection for Visual and Lidar SLAM: A Survey

Saba Arshad et al.

Summary: Loop closure detection is crucial in SLAM, reducing error and creating a consistent global map. This survey examines existing literature on loop closure detection algorithms, particularly focusing on deep learning-based methods, identifying challenges, and discussing future directions.

SENSORS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Semantic visual SLAM in dynamic environment

Shuhuan Wen et al.

Summary: This study proposes a new SLAM method that utilizes mask R-CNN to detect dynamic objects in the environment and build a semantic map, effectively separating dynamic and static points and achieving geometric segmentation of dynamic objects, outperforming current state-of-the-art SLAM algorithms in experimental testing.

AUTONOMOUS ROBOTS (2021)

添加到收藏夹

Article Computer Science, Information Systems

DP-SLAM: A visual SLAM with moving probability towards dynamic environments

Ao Li et al.

Summary: This paper proposes a novel visual SLAM system named DP-SLAM, based on a sparse feature model with a moving probability propagation for dynamic keypoints detection. By integrating geometry constraints and semantic segmentation, the system tracks dynamic keypoints within a Bayesian probability estimation framework. Experimental results demonstrate improved performance in challenging scenarios, showing potential for enhancing state-of-the-art SLAM systems.

INFORMATION SCIENCES (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

LIFT-SLAM: A deep-learning feature-based monocular visual SLAM method

Hudson Martins Silva Bruno et al.

Summary: SLAM tackles the challenge of a robot localizing itself and mapping an environment simultaneously, with VSLAM employing cameras to do so. While traditional VSLAM algorithms can struggle with complex robot or environmental movements, the integration of deep learning with geometry-based VSLAM in the proposed LIFT-SLAM system shows promising results for noise reduction and enhanced performance in challenging environments.

NEUROCOMPUTING (2021)

添加到收藏夹

Article Robotics

OV2SLAM: A Fully Online and Versatile Visual SLAM for Real-Time Applications

Maxime Ferrera et al.

Summary: OV(2)SLAM is a fully online algorithm for various applications such as augmented reality, virtual reality, robotics and autonomous driving. It combines recent contributions in visual localization within an efficient multi-threaded architecture, demonstrating state-of-the-art accuracy and real-time performance. The source code is released for the benefit of the community.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

添加到收藏夹

Proceedings Paper Automation & Control Systems

Avoiding Degeneracy for Monocular Visual SLAM with Point and Line Features

Hyunjun Lim et al.

Summary: This paper proposes a degeneracy avoidance method for a point and line based visual SLAM algorithm, effectively addressing the shortcomings of point features in low-texture and illuminance variant environments. By using line features to compensate for the weaknesses of point features, and introducing a novel structural constraint to avoid degeneracy problems.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

添加到收藏夹

Proceedings Paper Automation & Control Systems

CamVox: A Low-cost and Accurate Lidar-assisted Visual SLAM System

Yuewen Zhu et al.

Summary: Combining low-cost Livox lidars with visual SLAM system CamVox enhances overall accuracy, with an automatic lidar-camera calibration method for uncontrolled scenes. The long depth detection range of Livox lidars also contributes to more accurate mapping. Performance comparison with other SLAM systems like VINS-mono and LOAM further validates the effectiveness of CamVox.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Comparing Representations in Tracking for Event Camera-based SLAM

Jianhao Jiao et al.

Summary: This paper investigates two typical image-type representations for event camera-based tracking: time surface (TS) and event map (EM). An enhanced tracker is developed by utilizing the complementary strengths of these representations, and a comparison of six tracker variations is conducted on sequences covering various scenarios and motion complexities.

2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS, CVPRW 2021 (2021)

添加到收藏夹

Article Imaging Science & Photographic Technology

Direct and Indirect vSLAM Fusion for Augmented Reality

Mohamed Outahar et al.

Summary: Augmented reality (AR) is an emerging technology with limitations in device accessibility and cost. A new method proposed in the study fuses direct and indirect methods to enhance AR robustness and seamless scene transitions.

JOURNAL OF IMAGING (2021)

添加到收藏夹

Review Computer Science, Software Engineering

A review of monocular visual odometry

Ming He et al.

VISUAL COMPUTER (2020)

添加到收藏夹

Article Robotics

SLAM for autonomous planetary rovers with global localization

Dimitrios Geromichalos et al.

JOURNAL OF FIELD ROBOTICS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

UcoSLAM: Simultaneous localization and mapping by fusion of keypoints and squared planar markers

Rafael Munoz-Salinas et al.

PATTERN RECOGNITION (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Tightly-coupled ultra-wideband-aided monocular visual SLAM with degenerate anchor configurations

Thien Hoang Nguyen et al.

AUTONOMOUS ROBOTS (2020)

添加到收藏夹

Article Automation & Control Systems

Multi-camera visual SLAM for off-road navigation

Yi Yang et al.

ROBOTICS AND AUTONOMOUS SYSTEMS (2020)

添加到收藏夹

Proceedings Paper Automation & Control Systems

Are We Ready for Service Robots? The OpenLORIS-Scene Datasets for Lifelong SLAM

Xuesong Shi et al.

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

添加到收藏夹

Proceedings Paper Automation & Control Systems

TextSLAM: Visual SLAM with Planar Text Features

Boying Li et al.

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

添加到收藏夹

Proceedings Paper Automation & Control Systems

DXSLAM: A Robust and Efficient Visual SLAM System with Deep Features

Dongjiang Li et al.

2020 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2020)

添加到收藏夹

Article Computer Science, Information Systems

VPS-SLAM: Visual Planar Semantic SLAM for Aerial Robotic Systems

Hriday Bavle et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Robotics

DeepFactors: Real-Time Probabilistic Dense Monocular SLAM

Jan Czarnowski et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SPM-SLAM: Simultaneous localization and mapping with squared planar markers

Rafael Munoz-Salinas et al.

PATTERN RECOGNITION (2019)

添加到收藏夹

Article Robotics

Improving monocular visual SLAM in dynamic environments: an optical-flow-based approach

Jiyu Cheng et al.

ADVANCED ROBOTICS (2019)

添加到收藏夹

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)

添加到收藏夹

Article Automation & Control Systems

Dynamic-SLAM: Semantic monocular visual localization and mapping based on deep learning in dynamic environment

Linhui Xiao et al.

ROBOTICS AND AUTONOMOUS SYSTEMS (2019)

添加到收藏夹

Article Construction & Building Technology

An Occupancy Grid Mapping enhanced visual SLAM for real-time locating it applications in indoor GPS-denied environments

Lichao Xu et al.

AUTOMATION IN CONSTRUCTION (2019)

添加到收藏夹

Article Chemistry, Analytical

DMS-SLAM: A General Visual SLAM System for Dynamic Scenes with Multiple Sensors

Guihua Liu et al.

SENSORS (2019)

添加到收藏夹

Proceedings Paper Computer Science, Cybernetics

A Review of SLAM Techniques and Security in Autonomous Driving

Ashutosh Singandhupe et al.

2019 THIRD IEEE INTERNATIONAL CONFERENCE ON ROBOTIC COMPUTING (IRC 2019) (2019)

添加到收藏夹

Proceedings Paper Computer Science, Hardware & Architecture

Pair-Navi: Peer-to-Peer Indoor Navigation with Mobile Visual SLAM

Erqun Dong et al.

IEEE CONFERENCE ON COMPUTER COMMUNICATIONS (IEEE INFOCOM 2019) (2019)

添加到收藏夹

Review Transportation Science & Technology

Deep Learning for Visual SLAM in Transportation Robotics: A review

Chao Duan et al.

TRANSPORTATION SAFETY AND ENVIRONMENT (2019)

添加到收藏夹

Article Computer Science, Information Systems

SOF-SLAM: A Semantic Visual SLAM for Dynamic Environments

Linyan Cui et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Theory & Methods

Visual SLAM and Structure from Motion in Dynamic Environments: A Survey

Muhamad Risqi U. Saputra et al.

ACM COMPUTING SURVEYS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Direct Sparse Odometry

Jakob Engel et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2018)

添加到收藏夹

Article Computer Science, Information Systems

Monocular Vision SLAM-Based UAV Autonomous Landing in Emergencies and Unknown Environments

Tao Yang et al.

ELECTRONICS (2018)

添加到收藏夹

Article Robotics

Ultimate SLAM? Combining Events, Images, and IMU for Robust Visual SLAM in HDR and High-Speed Scenarios

Antoni Rosinol Vidal et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Vijay Badrinarayanan et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2017)

添加到收藏夹

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)

添加到收藏夹

Article Robotics

The event-camera dataset and simulator: Event-based data for pose estimation, visual odometry, and SLAM

Elias Mueggler et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction

Keisuke Tateno et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes

Angela Dai et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

GMS: Grid-based Motion Statistics for Fast, Ultra-robust Feature Correspondence

JiaWang Bian et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

HPatches: A benchmark and evaluation of handcrafted and learned local descriptors

Vassileios Balntas et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

添加到收藏夹

Article Robotics

Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age

Cesar Cadena et al.

IEEE TRANSACTIONS ON ROBOTICS (2016)

添加到收藏夹

Article Robotics

The EuRoC micro aerial vehicle datasets

Michael Burri et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2016)

添加到收藏夹

Article Robotics

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

Raul Mur-Artal et al.

IEEE TRANSACTIONS ON ROBOTICS (2015)

添加到收藏夹

Article Engineering, Electrical & Electronic

StructSLAM: Visual SLAM With Building Structure Lines

Huizhong Zhou et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2015)

添加到收藏夹

Article Robotics

3-D Mapping With an RGB-D Camera

Felix Endres et al.

IEEE TRANSACTIONS ON ROBOTICS (2014)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

LSD-SLAM: Large-Scale Direct Monocular SLAM

Jakob Engel et al.

COMPUTER VISION - ECCV 2014, PT II (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

CoSLAM: Collaborative Visual SLAM in Dynamic Environments

Danping Zou et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2013)

添加到收藏夹

Article Robotics

Information-Based Compact Pose SLAM

Viorela Ila et al.

IEEE TRANSACTIONS ON ROBOTICS (2010)

添加到收藏夹

Article Computer Science, Artificial Intelligence

MonoSLAM: Real-time single camera SLAM

Andrew J. Davison et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2007)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.