Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Filters








40,995 Hits in 3.2 sec

Natural interaction with virtual objects using vision-based six DOF sphere tracking

Derek Bradley, Gerhard Roth
2005 Proceedings of the 2005 ACM SIGCHI International Conference on Advances in computer entertainment technology - ACE '05  
We present a new TUI system that includes a passive optical tracking method to determine the six degree-offreedom (DOF) pose of a sphere in a real-time video stream, and then apply the pose to a virtual  ...  We demonstrate the use of our TUI system to control virtual 3D objects in an interactive way, proving to be a useful tool for computer entertainment applications.  ...  Although tracking errors do affect the usability of our method, a brief analysis of the errors can lead to a method for improving usability.  ... 
doi:10.1145/1178477.1178480 dblp:conf/ACMace/BradleyR05 fatcat:toi3a54q7zfabm2e4v2p56khiu

StereoSnakes: Contour Based Consistent Object Extraction for Stereo Images

Ran Ju, Tongwei Ren, Gangshan Wu
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
In this paper, we propose a contour based method which searches for consistent object contours instead of regions.  ...  We also demonstrate in a few applications how our method can be used as a basic tool for stereo image editing.  ...  We choose them according to a full coverage of related directions: stereo image segmentation, contour tracking, co-segmentation and video object extraction.  ... 
doi:10.1109/iccv.2015.201 dblp:conf/iccv/JuRW15 fatcat:32uiardl2rgjhb35upgocwjon4

Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy

Toshiyuki Terunuma, Aoi Tokui, Takeji Sakae
2017 Radiological Physics and Technology  
This method can be used for tumor contouring because it uses deep learning to perform image segmentation.  ...  We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control.  ...  A part of this work was supported by the Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI), Grant numbers 21611002, 25461903, and 17K09054.  ... 
doi:10.1007/s12194-017-0435-0 pmid:29285686 pmcid:PMC5840203 fatcat:f4j5ofbs7ngjxceppybky7yhtq

Marker-less tracking system for multiple mice using Mask R-CNN

Naoaki Sakamoto, Hitoshi Kakeno, Noriko Ozaki, Yusuke Miyazaki, Koji Kobayashi, Takahisa Murata
2023 Frontiers in Behavioral Neuroscience  
In this study, we aimed to develop a novel marker-less tracking method for multiple mice with top-view videos using deep-learning-based techniques.  ...  The behavior of C57BL/6 mice was recorded in an open-field arena, and the mouse contours were manually annotated for hundreds of frame images.  ...  In this study, we established a marker-less tracking system for multiple mice using Mask R-CNN and a color-correlogram-based method.  ... 
doi:10.3389/fnbeh.2022.1086242 pmid:36688129 pmcid:PMC9853548 fatcat:vla25r6hnfct3l3a7vje5m2zp4

Automatic cameraman for dynamic video acquisition of football match

Bikramjot Singh Hanzra, Romain Rossi
2013 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013)  
A system is described for dynamic video acquisition of football match. The system uses 2 cameras, a static and a dynamic camera.  ...  The tracking data is then used to control a Pan Tilt Zoom (PTZ) Camera that focuses on the area of maximum player density.  ...  We proposed a method and setup to automatically track action in a football match using a static camera for real-time player tracking and a PTZ camera for video acquisition.  ... 
doi:10.1109/iciip.2013.6707571 fatcat:nsdadsru3zdylo3vabnktizvlm

A Method of Free-Space Point-of-Regard Estimation Based on 3D Eye Model and Stereo Vision

Zijing Wan, Xiangjun Wang, Lei Yin, Kai Zhou
2018 Applied Sciences  
The gaze tracking device uses two pairs of stereo cameras to capture the left and right eye images, respectively, and then sets a pair of scene cameras to capture the scene images.  ...  This paper proposes a 3D point-of-regard estimation method based on 3D eye model and a corresponding head-mounted gaze tracking device. Firstly, a head-mounted gaze tracking system is given.  ...  2 sin α l sin β l − a 3 cos α l sin β l a 2 cos α l + a 3 sin α l a 1 sin β l − a 2 sin α l cos β l + a 3 cos α l cos β l    =    a 1 a 2 a 3    → v sri =    b 1 cos β r + b 2 sin α r sin β  ... 
doi:10.3390/app8101769 fatcat:t5yqc3jgbbbudontpq7ezkt6hi

Tracking Line Segment without Knowledge of Camera Motion

S. AitKaciAzzou, M. C Baba Hnini
2013 International Journal of Computer Applications  
In this paper, a new method for line segments matching for indoor reconstruction will be presented.  ...  The obtained results showed the feasibility of the method. General Terms Computer vision Keywords Tracking, line segment, Matching.  ...  Two main methods for tracking exist: those based on the contour and those based on the texture of the object.  ... 
doi:10.5120/12742-9650 fatcat:po5ariij7fcalc7qs2vagvlclu

Detection and Tracking of Coronal Mass Ejections [chapter]

Goussies Norberto, Mejail Marta, Jacobo Julio, Stenborg Guillermo
2008 Lecture Notes in Computer Science  
This work presents a novel method for the detection and tracking of CMEs as recorded by the LASCO instruments onboard SOHO.  ...  The algorithm we developed is based on level sets and region competition methods, the CMEs texture being characterized by their co-ocurrence matrix.  ...  Acknowledgments SOHO is a project of international cooperation between ESA and NASA.  ... 
doi:10.1007/978-3-540-85920-8_87 fatcat:fc3xkfnm7re5peb6el7zfi4o34

Direct Co-calibration of Endobronchial Ultrasound and Video [chapter]

Philipp Dressel, Marco Feuerstein, Tobias Reichl, Takayuki Kitasaka, Nassir Navab, Kensaku Mori
2010 Lecture Notes in Computer Science  
This paper for the first time presents a fast and practical approach for the co-calibration of endobronchial ultrasound (EBUS) and video images from a single image pair.  ...  At comparable accuracy, it achieves a significantly higher precision than a reference method based on combining electromagnetic tracking with two standard calibration techniques (hand-eye and single-wall  ...  Conclusion This paper for the first time presents a fast and practical method and design for the co-calibration of endobronchial ultrasound and camera frames, which only requires a single image pair to  ... 
doi:10.1007/978-3-642-15699-1_54 fatcat:o4l4ukanongk5ghzf6s77gpvim

Microtubule End-Clustering Maintains a Steady-State Spindle Shape

Christina L. Hueschen, Vahe Galstyan, Meelad Amouzgar, Rob Phillips, Sophie Dumont
2019 Current Biology  
We report that clustering of microtubule ends by dynein and NuMA is essential for mammalian spindles to hold a steady-state shape.  ...  Thus, end-clustering by dynein and NuMA is required for mammalian spindles to reach a steady-state geometry, and in their absence Eg5 powers a turbulent microtubule network inside mitotic cells.  ...  Also see Methods. (G) An example contour of a NuMA KO spindle. The red curve indicates the positional coordinate along the contour.  ... 
doi:10.1016/j.cub.2019.01.016 pmid:30744975 pmcid:PMC6383811 fatcat:ztahwdcqzbdsxjto2ifomr46z4

Real-time 6D Racket Pose Estimation and Classification for Table Tennis Robots

Yapeng Gao
2019 International Journal of Robotic Computing  
By using two monocular cameras, we can extract the racket's contours and choose some special points as feature points in image coordinates.  ...  Then, a Kalman filter is adopted to track the racket pose, and a multilayer perceptron (MLP) neural network is used to classify the pose movements.  ...  We calculate D for a sequence of images and show the comparison in Table 1 . The direct method is adopted for ellipse tting because of its performance.  ... 
doi:10.35708/rc1868-126249 fatcat:o2f4rcyrinbhvjrii3iogd52pa

Impact of Preprocessing Features on the Performance of Ultrasound Tongue Contour Tracking, via Dynamic Programming

László Czap
2021 Acta Polytechnica Hungarica  
The automated assessment of ultrasound images for speech processing is a difficult process.  ...  Tongue contour tracking is indispensable for the dynamic modelling of articulation.  ...  on their method and providing the series of images and the data set they used.  ... 
doi:10.12700/aph.18.2.2021.2.9 fatcat:2adkzy3jh5hzbil5q6n2lrbbc4

A framework for feature-based motion recovery in ground plane vehicle navigation [chapter]

J. M. Sanchiz, F. Pla, J. A. Marchant
1997 Lecture Notes in Computer Science  
The method is applied to a real application consisting of an autonomous vehicle navigating in a crop field.  ...  A transformation of the image plane is used that keeps the motion of the vehicle parallel to the transformed plane.  ...  The tracking method explained in this paper has been tested with several image sequences obtained from a camera mounted on a manually driven vehicle, Fig. 1 , undergoing a zigzag motion.  ... 
doi:10.1007/3-540-63460-6_179 fatcat:mwg3p3nwbvcr7e36pwwzsdsmq4

Graphical Model-Based Tracking of Curvilinear Structures in Bio-image Sequences

Pradeep Koulgi, Mehmet Emre Sargin, Kenneth Rose, B.S. Manjunath
2010 2010 20th International Conference on Pattern Recognition  
The state of the art HMM-based contour tracking scheme for tracking microtubules, while performing well in most scenarios, can miss the track if, during its growth, it intersects another microtubule in  ...  In this paper we present a graphical model-based tracking algorithm which propagates across frames information about the dynamics of all the microtubules.  ...  In this paper we focus on images of microtubules in live cell images, captured using fluorescence microscopy, and propose a graphical model-based open contour tracking algorithm for tracking these microtubules  ... 
doi:10.1109/icpr.2010.636 dblp:conf/icpr/KoulgiSRM10 fatcat:yjalsxfl5zg23ezotrnqb2pz4i

Fast and Accurate Registration of Visible and Infrared Videos

Socheat Sonn, Guillaume-Alexandre Bilodeau, Philippe Galinier
2013 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops  
pairs.  ...  In this work, we propose a novel fast and accurate method based on keypoints and temporal information to solve the registration problem on planar scenes with moving objects for infrared-visible stereo  ...  To improve our registration method, it would be useful to add after a first global transformation, a local transformation for each silhouette, for example, by a silhouette tracking method to get their  ... 
doi:10.1109/cvprw.2013.53 dblp:conf/cvpr/SonnBG13 fatcat:4cmlwvqjxret7ms3llsrx5lup4
« Previous Showing results 1 — 15 out of 40,995 results