329 Hits in 11.6 sec

On the Efficiency of Population-Based Optimization in Finding Best Parameters for RGB-D Visual Odometry

Aleksander Kostusiak, Piotr Skrzypczyński
2019 Journal of Automation, Mobile Robotics & Intelligent Systems  
Therefore, in this ar cle we make an assessment of two popula on-based approaches to parameter op miza on, that are for long me applied in various areas of robo cs, as means to find best parameters of  ...  In the last decade RGB-D cameras proliferated in robo cs, being also the sensors of choice for many prac cal visual odometry systems.  ...  Conclusion We demonstrated how simple to implement population-based optimization methods can be applied to the task of inding best parameters for a RGB-D visual odometry system.  ... 
doi:10.14313/jamris/2-2019/13 fatcat:dgidyg3c4zezrd7tfcjgyvcenu

Low-Bandwidth and Compute-Bound RGB-D Planar Semantic SLAM

Jincheng Zhang, Prashant Ganesh, Kyle Volle, Andrew Willis, Kevin Brink
2021 Sensors  
Visual simultaneous location and mapping (SLAM) using RGB-D cameras has been a necessary capability for intelligent mobile robots.  ...  Two novel compression algorithms for depth data and a method to independently fit planes to RGB-D data are provided, so that plane data can be used for real-time odometry estimation and mapping.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/s21165400 pmid:34450841 pmcid:PMC8399848 fatcat:q62y7p5fyvdo3bdmfwxodu7ye4

Building a grid-point cloud-semantic map based on graph for the navigation of intelligent wheelchair

Cheng Zhao, Huosheng Hu, Dongbing Gu
2015 2015 21st International Conference on Automation and Computing (ICAC)  
This paper proposed a novel Grid-Point Cloud-Semantic Multi-layered Map based on graph optimization for intelligent wheelchair navigation.  ...  For mapping, the 2D grid map is at the bottom, the 3D point cloud map is on the grid map and the semantic markers are labelled in them.  ...  The nodes [12] contain the odometry poses, laser scans, RGB and depth images of each location. In addition, they also save visual words which are used for loop closure detection.  ... 
doi:10.1109/iconac.2015.7313995 dblp:conf/iconac/ZhaoHG15 fatcat:xudjgytnarhhrijzfqy2536lxi

Autonomous Mobile Robot Navigation in Uneven and Unstructured Indoor Environments [article]

Chaoqun Wang, Lili Meng, Sizhen She, Ian M. Mitchell, Teng Li, Frederick Tung, Weiwei Wan, Max. Q. -H. Meng, Clarence W. de Silva
2017 arXiv   pre-print
Our robot first builds a 3D OctoMap representation for the uneven environment with the 3D mapping using wheel odometry, 2D laser and RGB-D data.  ...  Then we project multilayer 2D occupancy maps from OctoMap to generate the the traversable map based on layer differences.  ...  ACKNOWLEDGMENTS The authors would like to thank Ji Zhang from Carnegie Mellon University for the helpful discussion and Wolfram Burgard from University of Freiburg for the suggestion on the supplementary  ... 
arXiv:1710.10523v1 fatcat:wxkkhk6lkzbzrliof7m4sj44ga

Estimation, planning, and mapping for autonomous flight using an RGB-D camera in GPS-denied environments

Abraham Bachrach, Samuel Prentice, Ruijie He, Peter Henry, Albert S Huang, Michael Krainin, Daniel Maturana, Dieter Fox, Nicholas Roy
2012 The international journal of robotics research  
In this paper, we describe a system for visual odometry and mapping using an RGB-D camera, and its application to autonomous flight.  ...  model of the RGB-D camera.  ...  This research was supported by the Office of Naval Research (grant number MURI N00014-07-1-0749), Science of Autonomy (program N00014-09-1-0641) and the Army Research Office under the MAST CTA.  ... 
doi:10.1177/0278364912455256 fatcat:6mm5puzqp5blzl7mabrj3bn43y

A Stacked LSTM based Approach for Reducing Semantic Pose Estimation Error

Rana Azzam, Yusra Alkendi, Tarek Taha, Shoudong Huang, Yahya Zweiri
2020 IEEE Transactions on Instrumentation and Measurement  
To further verify the applicability of the proposed approach, it was tested on real-time sequences from the TUM RGB-D data set, where it was able to improve the estimated trajectories.  ...  In this article, a novel stacked long short-term memory (LSTM)-based error reduction approach is developed to enhance the accuracy of semantic SLAM in presence of such error sources.  ...  Semantic SLAM The adopted semantic SLAM is designed for ground vehicles and is performed based on measurements from the vehicle's wheel encoders and an RGB-D camera that is mounted on top.  ... 
doi:10.1109/tim.2020.3031156 fatcat:pht5eite4ba3nirf52xmxvfria

Simultaneous Localization and Mapping [chapter]

Cyrill Stachniss, John J. Leonard, Sebastian Thrun
2016 Springer Handbook of Robotics  
Finally, a publicly available visual odometry library [46. 130] that is optimized for efficient operation on small unmanned aerial vehicles is available today.  ...  Due to the availability of highly efficient optimization methods for sparse nonlinear optimization problems, graph-based SLAM has become the method of choice for building large-scale maps.  ... 
doi:10.1007/978-3-319-32552-1_46 fatcat:saxfp6tzt5eh7dknegysojmd2u

Fast place recognition with plane-based maps

E. Fernandez-Moral, W. Mayol-Cuevas, V. Arevalo, J. Gonzalez-Jimenez
2013 2013 IEEE International Conference on Robotics and Automation  
This paper presents a new method for recognizing places in indoor environments based on the extraction of planar regions from range data provided by a hand-held RGB-D sensor.  ...  The experimental results indicate that the proposed approach is an efficient way to solve this problem, working satisfactorily even when there are substantial changes in the scene (lifelong maps).  ...  ACKNOWLEDGMENT We are very grateful to our colleagues Miguel Algaba for providing an implementation for visual odometry and Jose Martínez-Carranza for useful discussions about this work.  ... 
doi:10.1109/icra.2013.6630951 dblp:conf/icra/Fernandez-MoralMAJ13 fatcat:65cokueymvgrtc4b3xezejxgcq

Stairs detection with odometry-aided traversal from a wearable RGB-D camera

A. Perez-Yus, D. Gutierrez-Gomez, G. Lopez-Nicolas, J.J. Guerrero
2017 Computer Vision and Image Understanding  
Stairs are one of the most common structures present in human-made scenarios, but also one of the most dangerous for those with vision problems.  ...  Simultaneously, the detection of the staircase during the traversal is used to correct the drift of the visual odometry.  ...  The scaling parameters are fixed to σ r I = 5 and σ r W = 0.0025m −1 based on tests on static sequences and the disparity measurement model of RGB-D sensors [37] .  ... 
doi:10.1016/j.cviu.2016.04.007 fatcat:fbjzrzicazhzfc5qwamj3xzm3i

Multi-Scale Extension in an Entorhinal-Hippocampal Model for Cognitive Map Building

Jiru Wang, Rui Yan, Huajin Tang
2021 Frontiers in Neurorobotics  
in the lack of viability for real environments.  ...  In this work, an optimized dynamical model of grid cells is built for path integration in which recurrent weight connections between grid cells are parameterized in a more optimized way and the non-linearity  ...  All authors provided contributions to study conception and design, acquisition of data or analysis and interpretation of data, drafting the article or revising it critically for important intellectual  ... 
doi:10.3389/fnbot.2020.592057 pmid:33519410 pmcid:PMC7840836 fatcat:4ult5vj42jfedak4jcfss6ayxm

MD-SLAM: Multi-cue Direct SLAM [article]

Luca Di Giammarino, Leonardo Brizi, Tiziano Guadagnino, Cyrill Stachniss, Giorgio Grisetti
2022 arXiv   pre-print
We present comparative experiments with state-of-the-art approaches on publicly available benchmarks using RGB-D cameras and 3D LiDARs.  ...  This paper presents a novel direct 3D SLAM pipeline that works independently for RGB-D and LiDAR sensors.  ...  To the best of our knowledge, our approach is the only open-source SLAM system that can deal with RGB-D and LiDAR in a unified manner.  ... 
arXiv:2203.13237v1 fatcat:5cqoqbecpzc6fjcshqwnexraqa

The Urban Last Mile Problem: Autonomous Drone Delivery to Your Balcony [article]

Gino Brunner, Bence Szebedy, Simon Tanner, Roger Wattenhofer
2018 arXiv   pre-print
In this paper we tackle the problem of autonomous last mile delivery in urban environments using an off-the-shelf drone.  ...  Finally, we deploy our drone in a real-world environment and show how it can find the drop-off point on a balcony. To stimulate future research in this topic we open source our code.  ...  Then, it switches to vision based navigation and starts descending in order to find the target balcony, tagged by a visual marker.  ... 
arXiv:1809.08022v1 fatcat:axmde33k7rapneuamxuaphqrqi

Photorealistic 3D mapping of indoors by RGB-D scanning process

Tommi Tykkala, Andrew I. Comport, Joni-Kristian Kamarainen
2013 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems  
In this work, a RGB-D input stream is utilized for GPU-boosted 3D reconstruction of textured indoor environments.  ...  Depending on the trajectory shape, the reference is either fetched from a concurrently built keyframe model or from a previous RGB-D measurement.  ...  The first feature-based visual SLAM methods were based on the extended Kalman filter (EKF) [3] .  ... 
doi:10.1109/iros.2013.6696480 dblp:conf/iros/TykkalaCK13 fatcat:liggt5uinzbapbvnrcuzllwezi

Sparse Representations for Object- and Ego-Motion Estimations in Dynamic Scenes

Hirak J. Kashyap, Charless C. Fowlkes, Jeffrey L. Krichmar
2020 IEEE Transactions on Neural Networks and Learning Systems  
Disentangling the sources of visual motion in a dynamic scene during self-movement or ego motion is important for autonomous navigation and tracking.  ...  field (EMF) basis set, which eliminates the irrelevant components in both static and dynamic segments for the task of ego-motion estimation.  ...  The objective in (19) can be optimized efficiently using an autoencoder neural network with θ s as its encoder parameters and {T, R} as its decoder parameters.  ... 
doi:10.1109/tnnls.2020.3006467 pmid:32687472 fatcat:vyzezhpwzbhrrjebw6so5ury2q

Trail following with omnidirectional vision

C Rasmussen, Yan Lu, M Kocamaz
2010 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems  
Stereo visual odometry improves tracker dynamics on uneven terrain and permits local obstacle map maintenance.  ...  Through a combination of visual cues provided by stereo omnidirectional color cameras and ladar-based structural information, the algorithm is able to detect and track rough paths despite widely varying  ...  ACKNOWLEDGMENTS The authors gratefully acknowledge the support of the National Science Foundation under award 0546410.  ... 
doi:10.1109/iros.2010.5650189 dblp:conf/iros/RasmussenLK10 fatcat:m73qyd7xbrarhhkh5xzqnpy2u4
« Previous Showing results 1 — 15 out of 329 results