☆ 4.6 Article

Loop Closure Detection Using Local 3D Deep Descriptors

IEEE ROBOTICS AND AUTOMATION LETTERS (2022)

Related references

Note: Only part of the references are listed.

Article Computer Science, Artificial Intelligence

OverlapNet: a siamese network for computing LiDAR scan similarity with applications to loop closing and localization

Xieyuanli Chen et al.

Summary: The paper introduces a modified Siamese network for estimating the similarity between pairs of LiDAR scans, which can be used for loop closing in SLAM and global localization in autonomous systems. The approach utilizes a deep neural network to exploit cues generated from LiDAR data, demonstrating superior performance and generalization in different environments. The method effectively detects loop closures and reliably localizes vehicles globally in urban environments using LiDAR data collected in various seasons.

AUTONOMOUS ROBOTS (2022)

Add to Collection

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)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

SpinNet: Learning a General Surface Descriptor for 3D Point Cloud Registration

Sheng Ao et al.

Summary: SpinNet is a novel and simple neural architecture that extracts rotationally invariant local features for efficient point cloud registration and reconstruction. Extensive experiments have shown that SpinNet outperforms existing techniques and has the best generalization ability for various sensor modalities.

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

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

PointNetLK Revisited

Xueqian Li et al.

Summary: Recent examination of learning-based point cloud registration methods revealed poor performance in mismatched conditions, suggesting the use of classical non-learning methods or hybrid learning methods. PointNetLK, with the inclusion of an analytical Jacobian, showed significant improvement in generalization properties.

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

Add to Collection

Proceedings Paper Automation & Control Systems

Have I been here before? Learning to Close the Loop with LiDAR Data in Graph-Based SLAM

Tim-Lukas Habich et al.

Summary: This work presents an extension of graph-based SLAM methods to exploit the potential of 3D laser scans for loop detection. The proposed algorithm shows improvements in SLAM performance in various environments, with experiments demonstrating better results compared to existing methods such as RTAB-Map and LOAM. The developed ROS package is freely available for use.

2021 IEEE/ASME INTERNATIONAL CONFERENCE ON ADVANCED INTELLIGENT MECHATRONICS (AIM) (2021)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Distinctive 3D local deep descriptors

Fabio Poiesi et al.

Summary: In this study, a novel method is proposed to learn rotation-invariant 3D local deep descriptors for point cloud registration using a PointNet-based deep neural network. The generalization ability and robustness of the descriptors across different sensor modalities are verified.

2020 25TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR) (2021)

Add to Collection

Article Computer Science, Information Systems

Survey and Evaluation of RGB-D SLAM

Shishun Zhang et al.

Summary: This paper introduces the basic concept and structure of RGB-D SLAM systems, explains the differences in tracking, mapping, and loop detection among various RGB-D SLAM systems, and conducts a classification study on different algorithms. Through extensive evaluation experiments, the advantages and disadvantages of multiple RGB-D SLAM systems in different application scenarios are analyzed.

IEEE ACCESS (2021)

Add to Collection

Article Robotics

SegMap: Segment-based mapping and localization using data-driven descriptors

Renaud Dube et al.

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH (2020)

Add to Collection

Proceedings Paper Automation & Control Systems

Intensity Scan Context: Coding Intensity and Geometry Relations for Loop Closure Detection

Han Wang et al.

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

Add to Collection

Proceedings Paper Automation & Control Systems

GOSMatch: Graph-of-Semantics Matching for Detecting Loop Closures in 3D LiDAR data

Yachen Zhu et al.

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

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Semantically Assisted Loop Closure in SLAM Using NDT Histograms

Anestis Zaganidis et al.

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Fully Convolutional Geometric Features

Christopher Choy et al.

2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019) (2019)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

The Perfect Match: 3D Point Cloud Matching with Smoothed Densities

Zan Gojcic et al.

2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019) (2019)

Add to Collection

Proceedings Paper Automation & Control Systems

Characterizing Visual Localization and Mapping Datasets

Sajad Saeedi et al.

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

Add to Collection

Proceedings Paper Automation & Control Systems

RESLAM: A real-time robust edge-based SLAM system

Fabian Schenk et al.

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

Add to Collection

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)

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

3DMatch: Learning Local Geometric Descriptors from RGB-D Reconstructions

Andy Zeng et al.

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

Add to Collection

Proceedings Paper Computer Science, Artificial Intelligence

Fast Global Registration

Qian-Yi Zhou et al.

COMPUTER VISION - ECCV 2016, PT II (2016)

Add to Collection

Article Computer Science, Software Engineering

Real-Time RGB-D Camera Relocalization via Randomized Ferns for Keyframe Encoding

Ben Glocker et al.

IEEE TRANSACTIONS ON VISUALIZATION AND COMPUTER GRAPHICS (2015)

Add to Collection

Article Robotics

Bags of Binary Words for Fast Place Recognition in Image Sequences

Dorian Galvez-Lopez et al.

IEEE TRANSACTIONS ON ROBOTICS (2012)

Add to Collection

Article Robotics

Automatic Appearance-Based Loop Detection from Three-Dimensional Laser Data Using the Normal Distributions Transform

Martin Magnusson et al.

JOURNAL OF FIELD ROBOTICS (2009)

Add to Collection

© Peeref 2019-2024. All rights reserved.