13,243 Hits in 4.5 sec

An optical tracking system based on hybrid stereo/single-view registration and controlled cameras

Guillaume Cortes, Eric Marchand, Jerome Ardouin, Anatole Lecuyer
2017 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
We propose a proofof-concept of such an optical tracking system based on two consumer-grade cameras and a pan-tilt actuator and we used this approach on UAV localization.  ...  First, when the target becomes no longer visible by at least two cameras we propose a single-view tracking mode which requires only one camera.  ...  Such tracking systems could be based on ultrasound, magnetic, inertial or optical sensors.  ... 
doi:10.1109/iros.2017.8206520 dblp:conf/iros/CortesMAL17 fatcat:vxyq5zzgivbsxdrfnjkyqhttra

Tracking gaze direction from far-field surveillance cameras

Karthik Sankaranarayanan, Ming-Ching Chang, Nils Krahnstoever
2011 2011 IEEE Workshop on Applications of Computer Vision (WACV)  
A new cost metric based on location and gaze orientation is proposed to robustly associate head observations with tracker states.  ...  Based on the tracking information, one or more PTZ cameras are cooperatively controlled to obtain close-up facial images of individuals.  ...  Hence, we utilize a hybrid approach where we perform multi-camera multi-target person tracking within a network of fixed cameras, and pass the tracking information to drive one or more PTZ cameras to zoom-in  ... 
doi:10.1109/wacv.2011.5711548 dblp:conf/wacv/SankaranarayananCK11 fatcat:u6dk2ruggbchddyd6jpiwivmu4

Vision-based estimation of three-dimensional position and pose of multiple underwater vehicles

Sachit Butail, Derek A. Paley
2009 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems  
The tracking algorithm uses particle filtering with selective resampling based on a threshold and nearest neighbor data association for multiple targets.  ...  This paper describes a model-based probabilistic framework for tracking a fleet of laboratory-scale underwater vehicles using multiple fixed cameras.  ...  Multi-target: In the multi-target tracking experiment we deployed two subs in the NBRF. The subs are tracked for ten seconds using three cameras.  ... 
doi:10.1109/iros.2009.5353977 dblp:conf/iros/ButailP09 fatcat:4vscihg2dnct3k7rfvypnsxm3y

Occlusion-robust Visual Markerless Bone Tracking for Computer-Assisted Orthopaedic Surgery [article]

Xue Hu, Anh Nguyen, Ferdinando Rodriguez y Baena
2021 arXiv   pre-print
Conventional computer-assisted orthopaedic navigation systems rely on the tracking of dedicated optical markers for patient poses, which makes the surgical workflow more invasive, tedious, and expensive  ...  In this paper, we propose a RGB-D sensing-based markerless tracking method that is robust against occlusion.  ...  The registered initial target pose can then be updated according to the IR markers tracked by the optical tracker.  ... 
arXiv:2108.10608v1 fatcat:3rg46dd4ijdu3h47odrmvep5ni

Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System

Lionel Heng, Benjamin Choi, Zhaopeng Cui, Marcel Geppert, Sixing Hu, Benson Kuan, Peidong Liu, Rang Nguyen, Ye Chuan Yeo, Andreas Geiger, Gim Hee Lee, Marc Pollefeys (+1 others)
2019 2019 International Conference on Robotics and Automation (ICRA)  
The sensor suite employs many cameras for both 360-degree coverage and accurate multi-view stereo; the use of low-cost cameras keeps the cost of this sensor suite to a minimum.  ...  Such capabilities will enable autonomous navigation in urban and rural environments, in day and night, and with cameras as the only exteroceptive sensors.  ...  parameters are inferred from the estimated pose of the target with respect to the multi-camera system.  ... 
doi:10.1109/icra.2019.8793949 dblp:conf/icra/HengCCGHKLNYGLP19 fatcat:d7wcoms3drawhkd7klpu2sivlq

A vision-guided autonomous quadrotor in an air-ground multi-robot system

Wei Li, Tianguang Zhang, Kolja Kuhnlenz
2011 2011 IEEE International Conference on Robotics and Automation  
Two complementary pose/motion estimation methods, respectively marker-based and optical-flow-based, are developed by considering different altitudes in a flight.  ...  This quadrotor is equipped with a monocular camera, IMUs and a flight computer, which enables autonomous flights.  ...  To achieve this, vision-based 3D pose/motion estimation, based on artificial reference markers or optical flow, is developed.  ... 
doi:10.1109/icra.2011.5979579 dblp:conf/icra/LiZK11 fatcat:kw7orq7nsfai3awpzbh6uuhf5a

Beyond Pixels: Leveraging Geometry and Shape Cues for Online Multi-Object Tracking [article]

Sarthak Sharma, Junaid Ahmed Ansari, J. Krishna Murthy, K. Madhava Krishna
2018 arXiv   pre-print
Using images from a monocular camera alone, we devise pairwise costs for object tracks, based on several 3D cues such as object pose, shape, and motion.  ...  This paper introduces geometry and object shape and pose costs for multi-object tracking in urban driving scenarios.  ...  We also introduce a novel cost based on the 3D shape and pose of the target.  ... 
arXiv:1802.09298v2 fatcat:74ufbdhxrjetdgzeqqygdvslki

Low Altitude Georeferencing for Imaging Sensors in Maritime Tracking

Øystein Kaarstad Helgesen, Edmund Førland Brekke, Annette Stahl, Øystein Engelhardtsen
2020 IFAC-PapersOnLine  
Using real world data this method is applied in a maritime tracking system based on the Joint Integrated Probabilistic Data Association method and compared to radar tracking.  ...  Using real world data this method is applied in a maritime tracking system based on the Joint Integrated Probabilistic Data Association method and compared to radar tracking.  ...  ACKNOWLEDGEMENTS This work was made possible by DNV GL which provided a sensor rig complete with sensors.  ... 
doi:10.1016/j.ifacol.2020.12.1449 fatcat:wdcfxxg3vfet7gjcjukgyi4yxe

3D Reconstruction and Restoration Monitoring of Sculptural Artworks by a Multi-Sensor Framework

Sandro Barone, Alessandro Paoli, Armando Razionale
2012 Sensors  
These applications require robust multi-view procedures based on aligning several high resolution 3D measurements.  ...  The stereo photogrammetric sensor measures the spatial location of each view by tracking a marker frame integral to the optical scanner.  ...  Pose Estimation of the Optical Scanner The last step of the developed tracking approach consists of estimating the rigid motions of the optical scanner in order to align the acquired range maps (Figure  ... 
doi:10.3390/s121216785 pmid:23223079 pmcid:PMC3571811 fatcat:wldbck6ccjal7byixdqxvmyq4u

On-the-fly Augmented Reality for Orthopaedic Surgery Using a Multi-Modal Fiducial [article]

Sebastian Andress, Alex Johnson, Mathias Unberath, Alexander Winkler, Kevin Yu, Javad Fotouhi, Simon Weidert, Greg Osgood, Nassir Navab
2018 arXiv   pre-print
The proposed system builds upon a multi-modality marker and simultaneous localization and mapping technique to co-calibrate an optical see-through head mounted display to a C-arm fluoroscopy system.  ...  In most cases, the patient as well as the instruments are tracked by optical markers attached to them visible to infrared cameras.  ...  Therefore, the proposed system effectively avoids the use of dedicated but impractical optical or electromagnetic tracking solutions with 2-D/3-D registration, complicated setup or use of which is associated  ... 
arXiv:1801.01560v1 fatcat:zlqm5imat5fvzes7jaskxzdji4

CAN: Composite Appearance Network for Person Tracking and How to Model Errors in a Tracking System [article]

Neeti Narayan, Nishant Sankaran, Srirangaraj Setlur, Venu Govindaraju
2019 arXiv   pre-print
We demonstrate the efficiency of our approach with experiments on the challenging multi-camera tracking dataset, DukeMTMC.  ...  It is typically divided into two tasks: (i) single-camera tracking (SCT) - identify trajectories in the same scene, and (ii) inter-camera tracking (ICT) - identify trajectories across cameras for real  ...  In [10] , a unified framework for multi-person pose estimation and tracking with spatial and temporal embeddings is proposed.  ... 
arXiv:1811.06582v4 fatcat:jnwbuuc6uzha7hrsqgbqbvkgum

No Blind Spots: Full-Surround Multi-Object Tracking for Autonomous Vehicles using Cameras & LiDARs [article]

Akshay Rangesh, Mohan M. Trivedi
2019 arXiv   pre-print
This work is a generalization of the MDP framework for MOT, with some key extensions - First, we track objects across multiple cameras and across different sensor modalities.  ...  Online multi-object tracking (MOT) is extremely important for high-level spatial reasoning and path planning for autonomous and highly-automated vehicles.  ...  Transfer t to the tracked state and initialize the target template for each camera view in which target is observed; Multi-object tracking with MDPs.  ... 
arXiv:1802.08755v4 fatcat:mpiwothglzaljhtct6fburgcwu

Pedestrian Models for Autonomous Driving Part I: Low-Level Models, From Sensing to Tracking

Fanta Camara, Nicola Bellotto, Serhan Cosar, Dimitris Nathanael, Matthias Althoff, Jingyuan Wu, Johannes Ruenz, Andre Dietrich, Charles Fox
2020 IEEE transactions on intelligent transportation systems (Print)  
Unlike static obstacles, pedestrians are active agents with complex, interactive motions.  ...  Planning AV actions in the presence of pedestrians thus requires modelling of their probable future behaviour as well as detecting and tracking them.  ...  [25] proposed a multi-target tracker based on MWIS data association algorithm.  ... 
doi:10.1109/tits.2020.3006768 fatcat:awa5dgk4rbazteetyyqrndbgxq

ROW-SLAM: Under-Canopy Cornfield Semantic SLAM [article]

Jiacheng Yuan, Jungseok Hong, Junaed Sattar, Volkan Isler
2021 arXiv   pre-print
To overcome these challenges, we present a multi-camera system where a side camera (facing the plants) is used for detection whereas front and back cameras are used for motion estimation.  ...  We study a semantic SLAM problem faced by a robot tasked with autonomous weeding under the corn canopy. The goal is to detect corn stalks and localize them in a global coordinate frame.  ...  In this baseline, we replace the tracking module with optical flow tracking. Unlike SORT, the optical flow tracking method will re-initialize target id every k frame.  ... 
arXiv:2109.07134v1 fatcat:stsapa3fs5cl7bea75mssvzufi

Human tracking over camera networks: a review

Li Hou, Wanggen Wan, Jenq-Neng Hwang, Rizwan Muhammad, Mingyang Yang, Kang Han
2017 EURASIP Journal on Advances in Signal Processing  
The core techniques of human tracking across non-overlapping cameras are then discussed based on the aspects of human re-identification, camera-link model-based tracking and graph model-based tracking.  ...  The core techniques of human tracking within a camera are discussed based on two aspects, i.e., generative trackers and discriminative trackers.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1186/s13634-017-0482-z fatcat:sc6y6mffn5hjzaawmnduamqpz4
« Previous Showing results 1 — 15 out of 13,243 results