1,256 Hits in 5.6 sec

PFD-SLAM: A New RGB-D SLAM for Dynamic Indoor Environments Based on Non-Prior Semantic Segmentation

Chenyang Zhang, Rongchun Zhang, Sheng Jin, Xuefeng Yi
2022 Remote Sensing  
Now, most existing dynamic RGB-D SLAM methods are based on deep learning or mathematical models.  ...  To address this problem, different from most feature-level dynamic segmentation based on mathematical models, a non-prior semantic dynamic segmentation based on a particle filter is proposed in this paper  ...  Acknowledgments: We thank the Computer Vision Group from the Technical University of Munich and Imperial College London and National University for making the RGB-D SLAM datasets publicly available.  ... 
doi:10.3390/rs14102445 fatcat:we4s65e3yzc65kt3xz44ugen5u

DRE-SLAM: Dynamic RGB-D Encoder SLAM for a Differential-Drive Robot

Dongsheng Yang, Shusheng Bi, Wei Wang, Chang Yuan, Wei Wang, Xianyu Qi, Yueri Cai
2019 Remote Sensing  
In this paper, by fusing the information of an RGB-D camera and two encoders that are mounted on a differential-drive robot, we aim to estimate the motion of the robot and construct a static background  ...  OctoMap in both dynamic and static environments.  ...  The outputs are 2D robot poses and an OctoMap of the static background. We name the system DRE-SLAM (Dynamic RGB-D Encoder SLAM). DRE-SLAM is built based on the feature-based sparse V-SLAM method.  ... 
doi:10.3390/rs11040380 fatcat:pnt7tbe2uvdh7cl7nqtcrgca7a

OFM-SLAM: A Visual Semantic SLAM for Dynamic Indoor Environments

Xiong Zhao, Tao Zuo, Xinyu Hu, Luis Payá
2021 Mathematical Problems in Engineering  
Most of the current visual Simultaneous Localization and Mapping (SLAM) algorithms are designed based on the assumption of a static environment, and their robustness and accuracy in the dynamic environment  ...  Then, we combine the optical flow method and the MASK-RCNN for full dynamic points' culling, and the SLAM system is able to track without these dynamic points.  ...  Based on the complex and dynamic indoor dynamic environment, this paper explores the methods of constructing the semantic map in the dynamic environment, combining the visual SLAM system based on the RGB-D  ... 
doi:10.1155/2021/5538840 fatcat:hziewxc7drgctjjfsean43vmny

Motion segmentation based robust RGB-D SLAM

Youbing Wang, Shoudong Huang
2014 Proceeding of the 11th World Congress on Intelligent Control and Automation  
It is based on this observation that [54] proposes a simple and efficient method to segment motions using RGB-D data.  ...  SLAM: From Static to Dynamic 24 2-view based methods using RGB-D data, simple distance-based algorithms have been proposed [54] .  ... 
doi:10.1109/wcica.2014.7053228 fatcat:fnbya67qrvcudoksdnwqid3pmq

A New RGB-D SLAM Method with Moving Object Detection for Dynamic Indoor Scenes

Runzhi Wang, Wenhui Wan, Yongkang Wang, Kaichang Di
2019 Remote Sensing  
Simultaneous localization and mapping (SLAM) methods based on an RGB-D camera have been studied and used in robot navigation and perception.  ...  The detailed experimental results of our improved RGB-D SLAM were summarized and demonstrate its effectiveness in dynamic indoor scenes.  ...  Acknowledgments: We thank Computer Vision Group from Technical University of Munich for making the RGB-D SLAM dataset publically available.  ... 
doi:10.3390/rs11101143 fatcat:xl2lmc7pivaz3e4es4bgku263i

Visual-Inertial Multi-Instance Dynamic SLAM with Object-level Relocalisation [article]

Yifei Ren, Binbin Xu, Christopher L. Choi, Stefan Leutenegger
2022 arXiv   pre-print
In this paper, we present a tightly-coupled visual-inertial object-level multi-instance dynamic SLAM system.  ...  Our system can robustly track and reconstruct the geometries of arbitrary objects, their semantics and motion by incrementally fusing associated colour, depth, semantic, and foreground object probabilities  ...  ACKNOWLEDGMENT We thank Tristan Laidlow and Dimos Tzoumanikas for their fruitful discussions. Binbin Xu holds a China Scholarship Council-Imperial Scholarship.  ... 
arXiv:2208.04274v1 fatcat:ggddoqmo7rguvnnsbwp2p45ncy

RDMO-SLAM: Real-time Visual SLAM for Dynamic Environments using Semantic Label Prediction with Optical Flow

Yubao Liu, Jun Miura
2021 IEEE Access  
into feature based approaches, such as ORB-SLAM [2] and RGB-D SLAM [3] , and direct approaches, such as LSD-SLAM [4] and DSO [5] .  ...  [27] proposed a depth edge-based RGB-D SLAM system for dynamic environments based on the frame-tokeyframe registration, which only uses weighted depth edge points. Sun et al.  ...  He has published over 220 articles in international journals and conferences in the areas of intelligent robotics, mobile service robots, robot vision, and artificial intelligence.  ... 
doi:10.1109/access.2021.3100426 fatcat:euyxur5xrnas7kfleok7rfqgja

Semantic Optimization of Feature-Based SLAM

Peng Li, Lili Yin, Jiali Gao, Yuezhongyi Sun, Zain Anwar Ali
2021 Mathematical Problems in Engineering  
The purpose of this paper is to provide reasonable recommendation and removal of inappropriate information for SLAM (Simultaneous Localization and Mapping) technology based on feature method.  ...  The finding of the study is the above method can retain the information of high reliability and good stability for visual SLAM and process the key frames with poor reliability or low stability and the  ...  object, C i D i is the probability product, and sum N I�1 C i D i is the probability product sum of the object category of N.  ... 
doi:10.1155/2021/5581788 fatcat:l6fichhgh5fldmxxhgxunistle

Dynamic scene semantics SLAM based on semantic segmentation

Shuangquan Han, Zhihong Xi
2020 IEEE Access  
We performed experiments on the TUM RGB-D dataset.  ...  Most of the current SLAM research is based on the assumption of static scenes, and dynamic objects in the indoor environment are inevitable.  ...  The assumption based on static scenes greatly limits the SLAM development research and the application of the SLAM system in real life.  ... 
doi:10.1109/access.2020.2977684 fatcat:nlnbvcm6sfenrjazxw2ewqjayu

RDS-SLAM: Real-time Dynamic SLAM using Semantic Segmentation Methods

Yubao Liu, Jun Miura
2021 IEEE Access  
In this paper, we present RDS-SLAM, a real-time visual dynamic SLAM algorithm that is built on ORB-SLAM3 and adds a semantic thread and a semantic-based optimization thread for robust tracking and mapping  ...  Finally, we evaluate the tracking accuracy and real-time performance using the public TUM RGB-D datasets and Kinect camera in dynamic indoor scenarios.  ...  [5] proposed a real-time depth edge-based RGB-D SLAM system for dynamic environments based on the frameto-keyframe registration.  ... 
doi:10.1109/access.2021.3050617 fatcat:6ks7e4lopneingpkt5wks6sza4

DM-SLAM: A Feature-Based SLAM System for Rigid Dynamic Scenes

Junhao Cheng, Zhi Wang, Hongyan Zhou, Li Li, Jian Yao
2020 ISPRS International Journal of Geo-Information  
In the third module, two different strategies are presented to detect dynamic feature points for RGB-D/stereo and monocular cases.  ...  DM-SLAM combines an instance segmentation network with optical flow information to improve the location accuracy in dynamic environments, which supports monocular, stereo, and RGB-D sensors.  ...  On the TUM RGB-D dataset, DM-SLAM exhibits an order of magnitude improvement compared to ORB-SLAM2 in high-dynamic scenes.  ... 
doi:10.3390/ijgi9040202 fatcat:g44v57jhobh5piuufmarip7dbq

EM-Fusion: Dynamic Object-Level SLAM with Probabilistic Data Association [article]

Michael Strecke, Jörg Stückler
2019 arXiv   pre-print
The majority of approaches for acquiring dense 3D environment maps with RGB-D cameras assumes static environments or rejects moving objects as outliers.  ...  In this paper, we propose a novel approach to dynamic SLAM with dense object-level representations.  ...  Recently, some RGB-D SLAM methods have been proposed that represent and track moving rigid objects. An early approach extends keyframe-based RGB-D SLAM to object-level dynamic SLAM [20] .  ... 
arXiv:1904.11781v1 fatcat:cefngwywdfct3cdswvno2gzuc4

AcousticFusion: Fusing Sound Source Localization to Visual SLAM in Dynamic Environments

Tianwei Zhang, Huayan Zhang, Xiaofei Li, Junfeng Chen, Tin Lun Lam, Sethu Vijayakumar
2021 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
Therefore, in this paper, we propose a novel audio-visual fusion approach that fuses sound source direction into the RGB-D image and thus removes the effect of dynamic obstacles on the multi-robot SLAM  ...  Dynamic objects in the environment, such as people and other agents, lead to challenges for existing simultaneous localization and mapping (SLAM) approaches.  ...  ACKNOWLEDGEMENT This work is supported by the Shenzhen Institute of Artificial Intelligence and Robotics for Society (2019-ICP002), The Alan Turing Institute and EU H2020 project Enhancing Healthcare with  ... 
doi:10.1109/iros51168.2021.9636585 fatcat:2lsmodgrzjggvh7nuzbrsg6zfm

A survey: which features are required for dynamic visual simultaneous localization and mapping?

Zewen Xu, Zheng Rong, Yihong Wu
2021 Visual Computing for Industry, Biomedicine, and Art  
Compared to standard SLAM under the static world assumption, dynamic SLAM divides features into static and dynamic categories and leverages each type of feature properly.  ...  This article presents a survey on dynamic SLAM from the perspective of feature choices. A discussion of the advantages and disadvantages of different visual features is provided in this article.  ...  Authors' contributions All authors read and approved the final manuscript. Authors' information  ... 
doi:10.1186/s42492-021-00086-w fatcat:7tfm7sqb7za45nnzhn3fpiqcti

Fusing Semantics and Motion State Detection for Robust Visual SLAM

Gaurav Singh, Meiqing Wu, Siew-Kei Lam
2020 2020 IEEE Winter Conference on Applications of Computer Vision (WACV)  
Achieving robust pose tracking and mapping in highly dynamic environments is a major challenge faced by existing visual SLAM (vSLAM) systems.  ...  Specifically, semantic information is fused with motion states of the scene via a probability framework to enable accurate and robust moving object extraction in order to retain the useful features for  ...  Evaluation on TUM Dataset (RGB-D) The TUM RGB-D dataset [25] consists of several lowdynamic (sitting people) to highly dynamic sequences (walking people).  ... 
doi:10.1109/wacv45572.2020.9093359 dblp:conf/wacv/SinghWL20 fatcat:mkgfwsfnnzbdpbxrf5i6bva64a
« Previous Showing results 1 — 15 out of 1,256 results