Filters








46 Hits in 4.1 sec

Structure Aware SLAM using Quadrics and Planes [article]

Mehdi Hosseinzadeh, Yasir Latif, Trung Pham, Niko Suenderhauf, Ian Reid
2018 arXiv   pre-print
For scene coverage, additional dominant planar structures are modeled as infinite planes.  ...  Experiments show that the proposed points-planes-quadrics representation can easily incorporate Manhattan and object affordance constraints, greatly improving camera localization and leading to semantically  ...  Quadrics based representation was first proposed in [3] and later used in a structure from motion setup [10] .  ... 
arXiv:1804.09111v3 fatcat:355nyuh6kvfujc4i2b4ilm6pqm

Real-Time Monocular Object-Model Aware Sparse SLAM [article]

Mehdi Hosseinzadeh, Kejie Li, Yasir Latif, Ian Reid
2019 arXiv   pre-print
To capture the dominant structure of the scene, additional planar landmarks are detected by a CNN-based plane detector and modeled as independent landmarks in the map.  ...  Extensive experiments support our proposed inclusion of semantic objects and planar structures directly in the bundle-adjustment of SLAM - Semantic SLAM - that enriches the reconstructed map semantically  ...  ACKNOWLEDGMENT This work was supported by ARC Laureate Fellowship FL130100102 to IR and the ARC Centre of Excellence for Robotic Vision CE140100016.  ... 
arXiv:1809.09149v2 fatcat:xgzexi7rkrfrxm2xi6zakjw5gu

Simultaneous Localisation and Mapping with Quadric Surfaces [article]

Tristan Laidlow, Andrew J. Davison
2022 arXiv   pre-print
Human-made environments contain a lot of structure, and we seek to take advantage of this by enabling the use of quadric surfaces as features in SLAM systems.  ...  Finally, we introduce a proof-of-concept SLAM system using our representation, and provide some experimental results using an RGB-D dataset.  ...  More recently, quadric-based representations have been used in "object-aware" and "structure-aware" SLAM systems.  ... 
arXiv:2203.08040v1 fatcat:ha4bd4kv2vhjzdxbvrqoeqdqb4

Feature-based visual simultaneous localization and mapping: a survey

Rana Azzam, Tarek Taha, Shoudong Huang, Yahya Zweiri
2020 SN Applied Sciences  
Visual features can be seen at different levels; low-level features like points and edges, middle-level features like planes and blobs, and high-level features like semantically labeled objects.  ...  Visual simultaneous localization and mapping (SLAM) has attracted high attention over the past few years.  ...  The SLAM problem is formulated as a factor graph where various types of factors are used, including observations of points, objects, and planes as well as point-plane, plane-plane, and object-plane relationships  ... 
doi:10.1007/s42452-020-2001-3 fatcat:g7445is2cbdmdmllewkyp7giby

A Survey of Simultaneous Localization and Mapping with an Envision in 6G Wireless Networks [article]

Baichuan Huang, Jun Zhao, Jingbin Liu
2020 arXiv   pre-print
The paper makes an overview in SLAM including Lidar SLAM, visual SLAM, and their fusion.  ...  Simultaneous Localization and Mapping (SLAM) achieves the purpose of simultaneous positioning and map construction based on self-perception.  ...  , resource awareness, and task driven perception.  ... 
arXiv:1909.05214v4 fatcat:itnluvkewfd6fel7x65wdgig3e

Representations and Benchmarking of Modern Visual SLAM Systems

Yuchen Cao, Lan Hu, Laurent Kneip
2020 Sensors  
We discuss the structure of the representations and optimisation problems involved in Spatial AI, and propose new synthetic datasets that, for the first time, include accurate ground truth information  ...  We furthermore propose evaluation metrics for all aspects of such joint geometric-semantic representations and apply them to a new semantic SLAM framework.  ...  Structure Aware SLAM using Quadrics and Planes. In Proceedings of the Asian Conference on Computer Vision (ACCV), Taipei, Taiwan, 20–24 November 2016. 46.  ... 
doi:10.3390/s20092572 pmid:32366018 pmcid:PMC7248763 fatcat:myrm7wcqtfghxgptlnbphhk3p4

DSP-SLAM: Object Oriented SLAM with Deep Shape Priors

Jingwen Wang, Martin Runz, Lourdes Agapito
2021 2021 International Conference on 3D Vision (3DV)  
Figure 1: DSP-SLAM builds a rich object-aware map, providing complete detailed shapes of detected objects, while representing the background coarsely as sparse feature points.  ...  Reconstructed map and camera trajectory on KITTI 00.  ...  We thank Wonbong Jang and Adam Sherwood for fruitful discussions.  ... 
doi:10.1109/3dv53792.2021.00143 fatcat:zle434gjcvaatklyfrt7dyhzze

EF-Razor: An effective edge-feature processing method in Visual SLAM

Wen Liu, Yaokai Mo, Jichao Jiao, Zhongliang Deng
2020 IEEE Access  
Feature-based visual simultaneous localization and mapping (SLAM) is an effective localization approach for robots in unknown environments.  ...  EF-Razor first uses the semantics provided by the object detection YOLOv3 to distinguish edge-features.  ...  Additionally, further combination works like [5] use quadrics as 3D landmark representations. These landmarks can be directly constrained via a novel geometric error formulation.  ... 
doi:10.1109/access.2020.3013806 fatcat:mitmhnefenbbdovgjjjrcdhibm

Advances in Inference and Representation for Simultaneous Localization and Mapping [article]

David M. Rosen, Kevin J. Doherty, Antonio Teran Espinoza, John J. Leonard
2021 arXiv   pre-print
This article reviews recent progress in SLAM, focusing on advances in the expressive capacity of the environmental models used in SLAM systems (representation) and the performance of the algorithms used  ...  has led to the development of novel classes of certifiable and robust inference methods that dramatically improve the reliability of SLAM systems in real-world operation.  ...  SLAM for self-supervised learning. Work on SLAM-aware perception methods originated in the desire to leverage global spatial structure when recognizing objects in video streams (135) .  ... 
arXiv:2103.05041v1 fatcat:gv2emjyvhbgi3dhd4agxdjha2i

FroDO: From Detections to 3D Objects

Martin Runz, Kejie Li, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
Figure 1: Given a localized input RGB sequence, FroDO dectects objects and infers their pose and a progressively fine grained and expressive object shape representation.  ...  Pillai and Leonard [34] aggregate multiview detections to perform SLAM-aware object recognition and semi-dense reconstruction, while [31] fit per-object 3D quadric surfaces.  ...  Multi-view category-specific shape estimation Structurefrom-Motion (SfM) and simultaneous localization and mapping (SLAM) are useful to reconstruct 3D structure from image collections or videos.  ... 
doi:10.1109/cvpr42600.2020.01473 dblp:conf/cvpr/RunzLTMKS0ASLN20 fatcat:rax2vea64nbdhlreuauajyqebi

Table of Contents

2022 IEEE Robotics and Automation Letters  
Hauser Accurate and Robust Object SLAM With 3D Quadric Landmark Reconstruction in Outdoors . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ...  Unconstrained Line-Based SLAM Using Vanishing Points for Structural Mapping . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/lra.2022.3165102 fatcat:enjzebowe5hn7hsfwklc7nieuy

FroDO: From Detections to 3D Objects [article]

Kejie Li, Martin Rünz, Meng Tang, Lingni Ma, Chen Kong, Tanner Schmidt, Ian Reid, Lourdes Agapito, Julian Straub, Steven Lovegrove, Richard Newcombe
2020 arXiv   pre-print
A shape code is regressed using an encoder network before optimizing shape and pose further under the learnt shape priors using sparse and dense shape representations.  ...  The optimization uses multi-view geometric, photometric and silhouette losses.  ...  Pillai and Leonard [34] aggregate multiview detections to perform SLAM-aware object recognition and semi-dense reconstruction, while [31] fit per-object 3D quadric surfaces.  ... 
arXiv:2005.05125v1 fatcat:ein67ktbl5bcla5l3kizbstjee

A Comprehensive Study of Mobile Robot: History, Developments, Applications, and Future Research Perspectives

Ravi Raj, Andrzej Kos
2022 Applied Sciences  
In this article, we discuss a complete century of mobile robotics research, major sensors used in robotics, some major applications of mobile robots, and their impact on our lives and in applied engineering  ...  Since then, mobile robot research has transformed robotics and information engineering.  ...  Acknowledgments: The authors wish to express their thanks for financial support from subvention No. 16.16.230.434 paid for by the AGH University of Science and Technology, Krakow, Poland.  ... 
doi:10.3390/app12146951 fatcat:galacswrujgbxjcswk62q5qm5a

Review on Panoramic Imaging and Its Applications in Scene Understanding [article]

Shaohua Gao, Kailun Yang, Hao Shi, Kaiwei Wang, Jian Bai
2022 arXiv   pre-print
With the rapid development of high-speed communication and artificial intelligence technologies, human perception of real-world scenes is no longer limited to the use of small Field of View (FoV) and low-dimensional  ...  , panoramic visual localization, and so on.  ...  The design difficulty of a catadioptric imaging system mainly lies in determining the initial structural parameters of the quadric mirror of the system.  ... 
arXiv:2205.05570v1 fatcat:p77fuqtz2re7zna7kapypcwv5i

Curved Surface Patches for Rough Terrain Perception [article]

Dimitrios Kanoulas
2016 arXiv   pre-print
We introduce a new method to identify and model potential contact areas between the robot's foot and a surface using a set of bounded curved patches.  ...  Having defined the environment representation using the patch model, we introduce a way to assemble patches into a spatial map.  ...  (SLAM) problem, and as we mentioned above it is well studied [26, 136] .  ... 
arXiv:1612.06164v1 fatcat:nsh4wfxxpfdhflj4obtdnryjpu
« Previous Showing results 1 — 15 out of 46 results