Filters








35 Hits in 4.3 sec

A Robust Extrinsic Calibration Framework for Vehicles with Unscaled Sensors

Celyn Walters, Oscar Mendez, Simon Hadfield, Richard Bowden
2019 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
To solve these limitations, we propose a flexible framework which can estimate extrinsic parameters without an explicit calibration stage, even for sensors with unknown scale.  ...  Accurate extrinsic sensor calibration is essential for both autonomous vehicles and robots.  ...  This means that algorithms which operate on unscaled sensors such as Visual Odometry (VO) may be combined with other data sources in a metric sensor fusion framework.  ... 
doi:10.1109/iros40897.2019.8968244 dblp:conf/iros/WaltersMHB19 fatcat:xqtbr7j5uvhb5fdrftg6wyacwm

A Robust Extrinsic Calibration Framework for Vehicles with Unscaled Sensors [article]

Celyn Walters
2021 pre-print
To solve these limitations, we propose a flexible framework which can estimate extrinsic parameters without an explicit calibration stage, even for sensors with unknown scale.  ...  Accurate extrinsic sensor calibration is essential for both autonomous vehicles and robots.  ...  This means that algorithms which operate on unscaled sensors such as Visual Odometry (VO) may be combined with other data sources in a metric sensor fusion framework.  ... 
doi:10.1109/iros40897.2019.8968244. arXiv:2103.09641v1 fatcat:kbehbexj4nggrpnmg5ircw42q4

Fast automatic camera network calibration through human mesh recovery

Nicola Garau, Francesco G. B. De Natale, Nicola Conci
2020 Journal of Real-Time Image Processing  
In this paper we present an unsupervised and automatic framework for the estimation of the extrinsic parameters of a camera network, which leverages on optimised 3D human mesh recovery from a single image  ...  Camera calibration is a necessary preliminary step in computer vision for the estimation of the position of objects in the 3D world.  ...  Acknowledgements This research was developed within the framework of the project AUSILIA (2015-2020), funded by the Autonomous Province of Trento (Italy).  ... 
doi:10.1007/s11554-020-01002-w fatcat:efoh4ocqpjdvfmahnypxd3savm

A Collaborative Framework for High-Definition Mapping [article]

Alexis Stoven-Dubois, Kuntima Kiala Miguel, Aziz Dziri, Bertrand Leroy, Roland Chapuis
2019 arXiv   pre-print
We present a collaborative framework for high-definition mapping, in which vehicles equipped with standard sensors, such as a GNSS receiver and a mono-visual camera, update a map of geo-localized landmarks  ...  For connected vehicles to have a substantial effect on road safety, it is required that accurate positions and trajectories can be shared.  ...  SYSTEM OVERVIEW For our framework to be fully cooperative, we consider all connected vehicles equipped with the following set of standard sensors: a GNSS receiver and a mono-visual camera.  ... 
arXiv:1910.06014v1 fatcat:3foqoltokfg57mn5sf6gsejtdy

A Collaborative Framework for High-Definition Mapping

Alexis Stoven-Dubois, Kuntima Kiala Miguel, Aziz Dziri, Bertrand Leroy, Roland Chapuis
2019 2019 IEEE Intelligent Transportation Systems Conference (ITSC)  
We present a collaborative framework for high-definition mapping, in which vehicles equipped with standard sensors, such as a GNSS receiver and a mono-visual camera, update a map of geolocalized landmarks  ...  For connected vehicles to have a substantial effect on road safety, it is required that accurate positions and trajectories can be shared.  ...  We present a collaborative framework for high-definition mapping, in which vehicles equipped with standard sensors, such as a GNSS receiver and a mono-visual camera, update a map of geolocalized landmarks  ... 
doi:10.1109/itsc.2019.8917292 dblp:conf/itsc/Stoven-DuboisMD19 fatcat:ljrb6lg5drbxbklm7zju4u77dm

Fast localization and 3D mapping using an RGB-D sensor

Giuseppe Loianno, Vincenzo Lippiello, Bruno Siciliano
2013 2013 16th International Conference on Advanced Robotics (ICAR)  
Moreover, a multiple resolution approach led by the distance of the sensor from surrounding obstacles is proposed for the depth data acquisition process.  ...  Low-cost range sensors represent an interesting class of sensors which are increasingly used for localization and mapping purposes in robotics.The combination of depth data and visual information can be  ...  We assume that the intrinsic and the extrinsic calibration parameters are available for both the IR and for the RGB camera.  ... 
doi:10.1109/icar.2013.6766558 dblp:conf/icar/LoiannoLS13 fatcat:ephdc6mjcbeybaohuy4633crpu

Analysis of the Influence of Training Data on Road User Detection

Carlos Guindel, David Martin, Jose Maria Armingol, Christoph Stiller
2018 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES)  
Stiller and the other members of the MRT team for the four months that I spent there.  ...  A todos ellos quiero agradecerles el haber contribuido a que el día a día fuera un placer, más que un trabajo.  ...  extrinsic calibration.  ... 
doi:10.1109/icves.2018.8519510 dblp:conf/icves/Guindel0AS18 fatcat:fu3cvrvkdjeivndsipd4hnhnqy

Trajectory Optimization for Self-Calibration and Navigation

James Preiss, Karol Hausman, Gaurav Sukhatme, Stephan Weiss
2017 Robotics: Science and Systems XIII  
We show that the optimized trajectories lead to more accurate navigation while eliminating the need for a separate calibration procedure. • An optimization framework including a multi-state balancing strategy  ...  Trajectory generation approaches for mobile robots generally aim to optimize with respect to a cost function such as energy, execution time, or other mission-relevant parameters within the constraints  ...  The proprioceptive system inputs are particularly important for more complex sensor fusion frameworks which include self-calibration states and multiple sensors.  ... 
doi:10.15607/rss.2017.xiii.054 dblp:conf/rss/PreissHSW17 fatcat:kqr4wf5mb5crvayvh22av6gafi

Monocular Visual Inertial Direct SLAM with Robust Scale Estimation for Ground Robots/Vehicles

Bismaya Sahoo, Mohammad Biglarbegian, William Melek
2021 Robotics  
In this paper, we present a novel method for visual-inertial odometry for land vehicles.  ...  Our technique is robust to unintended, but unavoidable bumps, encountered when an off-road land vehicle traverses over potholes, speed-bumps or general change in terrain.  ...  [27] proposed a method of on-the-fly scale estimation and camera-IMU extrinsic calibration but this method is based on sparse key points.  ... 
doi:10.3390/robotics10010023 fatcat:4hgjdr7idrgulhl3ncckwtzrwm

Self-Calibration and Visual SLAM with a Multi-Camera System on a Micro Aerial Vehicle

Lionel Heng, Gim Hee Lee, Marc Pollefeys
2014 Robotics: Science and Systems X  
If vision-based simultaneous localization and mapping (vSLAM) is expected to provide reliable pose estimates for a micro aerial vehicle (MAV) with a multi-camera system, an accurate calibration of the  ...  We propose a novel vSLAM-based self-calibration method for a multicamera system that includes at least one calibrated stereo camera, and an arbitrary number of monocular cameras.  ...  We explore existing work on SLAM with a multi-camera system (Kaess and Dellaert, 2006; Kim et al., 2008; Carrera et al., 2011a; Harmat et al., 2012; Tribou, 2014) .  ... 
doi:10.15607/rss.2014.x.008 dblp:conf/rss/HengLP14 fatcat:zcixlq74jfhjhofvk7eqsq4j6i

Self-calibration and visual SLAM with a multi-camera system on a micro aerial vehicle

Lionel Heng, Gim Hee Lee, Marc Pollefeys
2015 Autonomous Robots  
If vision-based simultaneous localization and mapping (vSLAM) is expected to provide reliable pose estimates for a micro aerial vehicle (MAV) with a multi-camera system, an accurate calibration of the  ...  We propose a novel vSLAM-based self-calibration method for a multicamera system that includes at least one calibrated stereo camera, and an arbitrary number of monocular cameras.  ...  We explore existing work on SLAM with a multi-camera system (Kaess and Dellaert, 2006; Kim et al., 2008; Carrera et al., 2011a; Harmat et al., 2012; Tribou, 2014) .  ... 
doi:10.1007/s10514-015-9466-8 fatcat:gb6yoizpijhzpn7bzmtqmrjtby

Towards Safe, Real-Time Systems: Stereo vs Images and LiDAR for 3D Object Detection [article]

Matthew Levine
2022 arXiv   pre-print
Furthermore, doing so also has calibration benefits with respect to image-only methods.  ...  Towards understanding the efficacy of stereo as a replacement for monocular input or LiDAR in object detectors, we show that multimodal learning with traditional disparity algorithms can improve image-based  ...  The flexibility of these proposal methodologies combined with the fundamental power of convolutional frameworks in image domains provides for robust potential when optimizing traditional, 2D localization  ... 
arXiv:2202.12773v1 fatcat:zulrn7ahrzhgfbelzdmcb2ince

Image-Aided Navigation Using Cooperative Binocular Stereopsis

Justin Soeder, John Raquet
2015 Navigation  
This thesis proposes a novel method for cooperatively estimating the positions of two vehicles in a global reference frame based on synchronized image and inertial information.  ...  Instead, the optimal vehicle motion over a single time interval is estimated from the positions of common features using a modified bundle adjustment algorithm and is used as a measurement in a delayed  ...  in the sensor-aided IMU framework.  ... 
doi:10.1002/navi.112 fatcat:xgs6icaixbab7ggkxrncvyk7ri

People detection in RGB-D data

Luciano Spinello, Kai O. Arras
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
With an equal error rate of 85% in a range up to 8m, the results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected with a Kinect sensor in a populated indoor environment  ...  People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task.  ...  A calibration procedure is required to determine the extrinsic parameters that provide the proper correspondence between the two images.  ... 
doi:10.1109/iros.2011.6095074 dblp:conf/iros/SpinelloA11 fatcat:d2x7ucghfbavjbmkt7qfk4jjzi

People detection in RGB-D Data

L. Spinello, K. O. Arras
2011 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems  
With an equal error rate of 85% in a range up to 8m, the results demonstrate the robustness of HOD and Combo-HOD on a real-world data set collected with a Kinect sensor in a populated indoor environment  ...  People detection is a key issue for robots and intelligent systems sharing a space with people. Previous works have used cameras and 2D or 3D range finders for this task.  ...  A calibration procedure is required to determine the extrinsic parameters that provide the proper correspondence between the two images.  ... 
doi:10.1109/iros.2011.6048835 fatcat:vuonsxi42nf7dcwdvrd5ah5x64
« Previous Showing results 1 — 15 out of 35 results