4.7 Review

Review of Visual Simultaneous Localization and Mapping Based on Deep Learning

Related references

Note: Only part of the references are listed.
Editorial Material Computer Science, Hardware & Architecture

Neural Radiance Fields Explode on the Scene

Frank Dellaert

COMMUNICATIONS OF THE ACM (2022)

Article Robotics

Kimera-Multi: Robust, Distributed, Dense Metric-Semantic SLAM for Multi-Robot Systems

Yulun Tian et al.

Summary: This paper presents $\mathsf {\text{Kimera-Multi}}$, a multi-robot SLAM system that is robust, fully distributed, and capable of capturing semantic information. Experimental results demonstrate its superior performance.

IEEE TRANSACTIONS ON ROBOTICS (2022)

Article Robotics

Fast and incremental loop closure detection with deep features and proximity graphs

Shan An et al.

Summary: This article proposes an appearance-based loop closure detection pipeline for simultaneous localization and mapping applications. The system extracts global and local deep features using a convolutional neural network, constructs a visual database using a small-world graph, and retrieves similar locations on the traversed route. Experimental results demonstrate high performance and low execution times.

JOURNAL OF FIELD ROBOTICS (2022)

Article Computer Science, Artificial Intelligence

YOLO-SLAM: A semantic SLAM system towards dynamic environment with geometric constraint

Wenxin Wu et al.

Summary: This paper introduces a dynamic-environment-robust visual SLAM system named YOLO-SLAM, which effectively reduces the impact of dynamic objects and improves stability and accuracy in highly dynamic environments by utilizing a lightweight object detection network and a new geometric constraint method.

NEURAL COMPUTING & APPLICATIONS (2022)

Article Engineering, Electrical & Electronic

WF-SLAM: A Robust VSLAM for Dynamic Scenarios via Weighted Features

Yuanhong Zhong et al.

Summary: This paper proposes a robust visual SLAM system, WF-SLAM, to address the reduced accuracy of localization in dynamic scenes. By combining weighted features and dynamic information, WF-SLAM significantly reduces feature mismatch and improves localization accuracy.

IEEE SENSORS JOURNAL (2022)

Article Computer Science, Artificial Intelligence

SelfVIO: Self-supervised deep monocular Visual-Inertial Odometry and depth estimation

Yasin Almalioglu et al.

Summary: In this study, a novel self-supervised deep learning-based VIO and depth map recovery approach (SelfVIO) is presented, which learns the joint estimation of 6-DoF ego-motion and a depth map from unlabelled monocular RGB image sequences and IMU readings.

NEURAL NETWORKS (2022)

Letter Automation & Control Systems

Loop Closure Detection With Reweighting NetVLAD and Local Motion and Structure Consensus

Kaining Zhang et al.

IEEE-CAA JOURNAL OF AUTOMATICA SINICA (2022)

Article Engineering, Electrical & Electronic

MobileSP: An FPGA-Based Real-Time Keypoint Extraction Hardware Accelerator for Mobile VSLAM

Ye Liu et al.

Summary: This paper proposes an FPGA-based real-time keypoint extraction hardware accelerator for mobile VSLAM applications. The accelerator, named MobileSP, achieves high accuracy and improved processing speed through algorithm-hardware co-design. Experimental results demonstrate its superior performance.

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS (2022)

Review Chemistry, Analytical

Visual-SLAM Classical Framework and Key Techniques: A Review

Guanwei Jia et al.

Summary: With the increasing demand for artificial intelligence, environmental map reconstruction has become a hot topic for research in obstacle avoidance navigation, unmanned operations, and virtual reality. The quality of the map is crucial for positioning, path planning, and obstacle avoidance. This review provides an overview of the development of SLAM and V-SLAM, explains the components of the V-SLAM framework, and summarizes the key techniques and challenges. Furthermore, it proposes the development direction and needs of the V-SLAM field.

SENSORS (2022)

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)

Proceedings Paper Computer Science, Interdisciplinary Applications

A Modified Visual Simultaneous Localisation and Mapping (V-SLAM) Technique for Road Scene Modelling

Jibril Abdullahi Bala et al.

Summary: This study presents a modified V-SLAM scheme for road scene modelling, which utilizes object detection and ORB feature updating algorithm to estimate the position and orientation of the robot and map the environment successfully.

2022 IEEE NIGERIA 4TH INTERNATIONAL CONFERENCE ON DISRUPTIVE TECHNOLOGIES FOR SUSTAINABLE DEVELOPMENT (IEEE NIGERCON) (2022)

Article Computer Science, Information Systems

The STDyn-SLAM: A Stereo Vision and Semantic Segmentation Approach for VSLAM in Dynamic Outdoor Environments

Daniela Esparza et al.

Summary: This paper proposes a feature-based SLAM system that focuses on object detection and segmentation in dynamic environments. The system utilizes neural networks, optical flow, and depth maps to detect objects in the scene, and employs a stereo camera to capture the scene. The proposed system has fast processing time and can run in real-time both indoors and outdoors.

IEEE ACCESS (2022)

Article Robotics

DSEC: A Stereo Event Camera Dataset for Driving Scenarios

Mathias Gehrig et al.

Summary: Autonomous driving has received significant corporate funding in the past decade, but operating in challenging illumination conditions remains an open problem. To address this issue, a new dataset called DSEC, containing high-resolution event cameras, is proposed to provide rich sensory data for development and evaluation of event-based stereo algorithms.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

DynaSLAM II: Tightly-Coupled Multi-Object Tracking and SLAM

Berta Bescos et al.

Summary: The paper introduces DynaSLAM II, a visual SLAM system for stereo and RGB-D camera configurations with tight integration of multi-object tracking ability, utilizing instance semantic segmentation and ORB features to track dynamic objects. The system not only provides rich clues for scene understanding but also benefits camera tracking.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Computer Science, Artificial Intelligence

SurfaceNet plus : An End-to-end 3D Neural Network for Very Sparse Multi-View Stereopsis

Mengqi Ji et al.

Summary: Researchers investigate sparse-MVS and find that the classical depth-fusion method becomes powerless in cases with larger baseline angles. They introduce SurfaceNet+ as a volumetric solution to address the 'incompleteness' and 'inaccuracy' problems induced by very sparse MVS setups, demonstrating superior performance compared to state-of-the-art methods in terms of precision and recall.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2021)

Article Engineering, Electrical & Electronic

Attention-SLAM: A Visual Monocular SLAM Learning From Human Gaze

Jinquan Li et al.

Summary: This paper introduces a novel SLAM approach called Attention-SLAM, which combines a visual saliency model SalNavNet with traditional monocular visual SLAM. By optimizing the importance of feature points, it demonstrates better performance compared to existing benchmarks in indoor scenes with varying conditions.

IEEE SENSORS JOURNAL (2021)

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)

Article Robotics

ESA-VLAD: A Lightweight Network Based on Second-Order Attention and NetVLAD for Loop Closure Detection

Yan Xu et al.

Summary: ESA-VLAD is a novel loop closure detection algorithm that utilizes EfficientNetB0 as backbone and integrates a second-order attention module to improve feature correlation learning. Knowledge distillation strategy is adopted during training and HNSW is used for loop closure candidate image retrieval, along with LDB descriptors for geometrical consistency check.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

CodeMapping: Real-Time Dense Mapping for Sparse SLAM using Compact Scene Representations

Hidenobu Matsuki et al.

Summary: A novel dense mapping framework is proposed to complement sparse visual SLAM systems, predicting dense depth images and improving consistency through multi-view optimization.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

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)

Article Radiology, Nuclear Medicine & Medical Imaging

On Interpretability of Artificial Neural Networks: A Survey

Feng-Lei Fan et al.

Summary: Deep learning by artificial deep neural networks has achieved great success in various fields, but their black-box nature hinders their adoption in critical applications like medicine. The interpretability of neural networks has become increasingly important, with wide applications in medicine and various future research directions.

IEEE TRANSACTIONS ON RADIATION AND PLASMA MEDICAL SCIENCES (2021)

Proceedings Paper Automation & Control Systems

Implementation of a Mobile Multi-Target Search System with 3D SLAM and Object Localization in Indoor Environments

Juwon Kim et al.

Summary: This paper discusses the issue of recognizing and localizing multiple targets in indoor environments using 3D SLAM, presenting a solution involving a mobile robot and multiple sensors. The system utilizes YOLO for target recognition and depth camera for measuring relative positions, with LeGo-LOAM for 3D SLAM mapping. The mobile multi-target search system is implemented on ROS and tested successfully in various indoor environments.

2021 21ST INTERNATIONAL CONFERENCE ON CONTROL, AUTOMATION AND SYSTEMS (ICCAS 2021) (2021)

Proceedings Paper Computer Science, Artificial Intelligence

NeRV: Neural Reflectance and Visibility Fields for Relighting and View Synthesis

Pratul P. Srinivasan et al.

Summary: The method uses MLPs to parameterize a continuous volumetric function to represent scene properties, enabling the rendering of new views and performing well in complex lighting environments.

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

Proceedings Paper Computer Science, Artificial Intelligence

MonoRec: Semi-Supervised Dense Reconstruction in Dynamic Environments from a Single Moving Camera

Felix Wimbauer et al.

Summary: MonoRec is a semi-supervised monocular dense reconstruction architecture that predicts depth maps in dynamic environments using a multi-view stereo setting. The MaskModule is introduced to predict moving object masks by leveraging photometric inconsistencies in the cost volumes, allowing for the reconstruction of both static and moving objects. The model achieves state-of-the-art performance on the KITTI dataset and generalizes well to the Oxford RobotCar dataset and the TUM-Mono dataset.

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

Article Computer Science, Information Systems

RDS-SLAM: Real-Time Dynamic SLAM Using Semantic Segmentation Methods

Yubao Liu et al.

Summary: This paper presents a real-time visual dynamic SLAM algorithm called RDS-SLAM, which enhances robust tracking and mapping in dynamic environments by adding semantic threads and semantic-based optimization threads. It addresses the limitation of existing vSLAM algorithms in using dynamic real-world environments.

IEEE ACCESS (2021)

Article Computer Science, Artificial Intelligence

Mask R-CNN

Kaiming He et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Article Automation & Control Systems

Loop closure detection using supervised and unsupervised deep neural networks for monocular SLAM systems

Azam Rafique Memon et al.

ROBOTICS AND AUTONOMOUS SYSTEMS (2020)

Review Chemistry, Analytical

A Review of Visual-LiDAR Fusion based Simultaneous Localization and Mapping

Cesar Debeunne et al.

SENSORS (2020)

Article Computer Science, Artificial Intelligence

Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images

Haozhe Xie et al.

INTERNATIONAL JOURNAL OF COMPUTER VISION (2020)

Article Robotics

Distributed Consistent Multi-Robot Semantic Localization and Mapping

Vladimir Tchuiev et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Automation & Control Systems

FinnForest dataset: A forest landscape for visual SLAM

Ihtisham Ali et al.

ROBOTICS AND AUTONOMOUS SYSTEMS (2020)

Article Computer Science, Artificial Intelligence

Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery

E. Jared Shamwell et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2020)

Proceedings Paper Computer Science, Artificial Intelligence

D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry

Nan Yang et al.

2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2020)

Article Computer Science, Information Systems

DDL-SLAM: A Robust RGB-D SLAM in Dynamic Environments Combined With Deep Learning

Yongbao Ai et al.

IEEE ACCESS (2020)

Article Computer Science, Information Systems

Compressed Holistic ConvNet Representations for Detecting Loop Closures in Dynamic Environments

Shuo Wang et al.

IEEE ACCESS (2020)

Article Robotics

Panoptic 3D Mapping and Object Pose Estimation Using Adaptively Weighted Semantic Information

Dinh-Cuong Hoang et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

DeepTIO: A Deep Thermal-Inertial Odometry With Visual Hallucination

Muhamad Risqi U. Saputra et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

DOOR-SLAM: Distributed, Online, and Outlier Resilient SLAM for Robotic Teams

Pierre-Yves Lajoie et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

DeepFactors: Real-Time Probabilistic Dense Monocular SLAM

Jan Czarnowski et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

The Rosario dataset: Multisensor data for localization and mapping in agricultural environments

Taihu Pire et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2019)

Article Robotics

Complex urban dataset with multi-level sensors from highly diverse urban environments

Jinyong Jeong et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2019)

Article Chemistry, Multidisciplinary

Loop Closure Detection Based on Multi-Scale Deep Feature Fusion

Baifan Chen et al.

APPLIED SCIENCES-BASEL (2019)

Article Computer Science, Software Engineering

Neural Volumes: Learning Dynamic Renderable Volumes from images

Stephen Lombardi et al.

ACM TRANSACTIONS ON GRAPHICS (2019)

Article Robotics

CubeSLAM: Monocular 3-D Object SLAM

Shichao Yang et al.

IEEE TRANSACTIONS ON ROBOTICS (2019)

Article Robotics

Volumetric Instance-Aware Semantic Mapping and 3D Object Discovery

Margarita Grinvald et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2019)

Proceedings Paper Automation & Control Systems

Beyond Photometric Loss for Self-Supervised Ego-Motion Estimation

Tianwei Shen et al.

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2019)

Proceedings Paper Automation & Control Systems

Pose Graph Optimization for Unsupervised Monocular Visual Odometry

Yang Li et al.

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2019)

Proceedings Paper Automation & Control Systems

GANVO: Unsupervised Deep Monocular Visual Odometry and Depth Estimation with Generative Adversarial Networks

Yasin Almalioglu et al.

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2019)

Proceedings Paper Automation & Control Systems

Enhancing V-SLAM Keyframe Selection with an Efficient ConvNet for Semantic Analysis

Inigo Alonso et al.

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2019)

Article Engineering, Civil

ERFNet: Efficient Residual Factorized ConvNet for Real-Time Semantic Segmentation

Eduardo Romera et al.

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2018)

Article Multidisciplinary Sciences

Neural scene representation and rendering

S. M. Ali Eslami et al.

SCIENCE (2018)

Review Computer Science, Information Systems

Visual interpretability for deep learning: a survey

Quan-shi Zhang et al.

FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING (2018)

Article Computer Science, Information Systems

Peeking Inside the Black-Box: A Survey on Explainable Artificial Intelligence (XAI)

Amina Adadi et al.

IEEE ACCESS (2018)

Article Robotics

DynaSLAM: Tracking, Mapping, and Inpainting in Dynamic Scenes

Berta Bescos et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

Article Robotics

Geometric Correspondence Network for Camera Motion Estimation

Jiexiong Tang et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2018)

Proceedings Paper Computer Science, Artificial Intelligence

RayNet: Learning Volumetric 3D Reconstruction with Ray Potentials

Despoina Paschalidou et al.

2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2018)

Article Computer Science, Artificial Intelligence

Unsupervised learning to detect loops using deep neural networks for visual SLAM system

Xiang Gao et al.

AUTONOMOUS ROBOTS (2017)

Article Robotics

1 year, 1000 km: The Oxford RobotCar dataset

Will Maddern et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2017)

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)

Article Robotics

EVO: A Geometric Approach to Event-Based 6-DOF Parallel Tracking and Mapping in Real Time

Henri Rebecq et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2017)

Article Computer Science, Hardware & Architecture

ImageNet Classification with Deep Convolutional Neural Networks

Alex Krizhevsky et al.

COMMUNICATIONS OF THE ACM (2017)

Proceedings Paper Computer Science, Artificial Intelligence

SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsis

Mengqi Ji et al.

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

Proceedings Paper Computer Science, Artificial Intelligence

Unsupervised Monocular Depth Estimation with Left-Right Consistency

Clement Godard et al.

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

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)

Article Robotics

The EuRoC micro aerial vehicle datasets

Michael Burri et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2016)

Proceedings Paper Computer Science, Artificial Intelligence

Video Summarization with Long Short-Term Memory

Ke Zhang et al.

COMPUTER VISION - ECCV 2016, PT VII (2016)

Article Computer Science, Artificial Intelligence

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Kaiming He et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2015)

Article Robotics

ORB-SLAM: A Versatile and Accurate Monocular SLAM System

Raul Mur-Artal et al.

IEEE TRANSACTIONS ON ROBOTICS (2015)

Article Robotics

The Malaga urban dataset: High-rate stereo and LiDAR in a realistic urban scenario

Jose-Luis Blanco-Claraco et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2014)

Proceedings Paper Computer Science, Artificial Intelligence

LSD-SLAM: Large-Scale Direct Monocular SLAM

Jakob Engel et al.

COMPUTER VISION - ECCV 2014, PT II (2014)

Article Computer Science, Artificial Intelligence

OctoMap: an efficient probabilistic 3D mapping framework based on octrees

Armin Hornung et al.

AUTONOMOUS ROBOTS (2013)

Article Robotics

Vision meets robotics: The KITTI dataset

A. Geiger et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2013)

Article Computer Science, Artificial Intelligence

Analysis of focus measure operators for shape-from-focus

Said Pertuz et al.

PATTERN RECOGNITION (2013)

Article Computer Science, Artificial Intelligence

BRIEF: Computing a Local Binary Descriptor Very Fast

Michael Calonder et al.

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE (2012)

Article Computer Science, Artificial Intelligence

Visual SLAM: Why filter?

Hauke Strasdat et al.

IMAGE AND VISION COMPUTING (2012)

Article Robotics

Factoring the Mapping Problem: Mobile Robot Map-building in the Hybrid Spatial Semantic Hierarchy

Patrick Beeson et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2010)

Article Computer Science, Software Engineering

SBA: A Software Package for Generic Sparse Bundle Adjustment

Manolis I. A. Lourakis et al.

ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE (2009)

Article Computer Science, Artificial Intelligence

Speeded-Up Robust Features (SURF)

Herbert Bay et al.

COMPUTER VISION AND IMAGE UNDERSTANDING (2008)

Article Engineering, Electrical & Electronic

A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking

MS Arulampalam et al.

IEEE TRANSACTIONS ON SIGNAL PROCESSING (2002)