The Experts below are selected from a list of 282 Experts worldwide ranked by ideXlab platform
Thomas Sikora - One of the best experts on this subject based on the ideXlab platform.
-
AVSS - Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
-
Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
Michael Pätzold - One of the best experts on this subject based on the ideXlab platform.
-
AVSS - Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
-
Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
Fereidoun Sabetghadam - One of the best experts on this subject based on the ideXlab platform.
-
an immersed boundary method based on the Kinematic Relation of the velocity vorticity formulation
Journal of Mechanics, 2015Co-Authors: I. Farahbakhsh, Hassan Ghassemi, Fereidoun SabetghadamAbstract:An immersed boundary method is proposed for the simulation of the interaction of an incompressible flow with rigid bodies. The method is based on a new interpretation of velocity-vorticity formulation and no longer includes the force term which is an essential issue of common immersed boundary methods. The system is considered in an Eulerian frame and retrieving the vorticity in this formulation enforces continuity at the fluid-solid interface and rigid motion of the solid. The method focuses on the mutual Kinematic Relations between the velocity and vorticity fields and with retrieving the vorticity field and recalculating the velocities yields the solenoidal velocity field. The method is applied to the two dimensional problems and the results show that the solenoidality is satisfied acceptably. The comparisons with 2D test cases are provided to illustrate the capabilities of the proposed method.
-
An Immersed Boundary Method Based on the Kinematic Relation of the Velocity-Vorticity Formulation
Journal of Mechanics, 2015Co-Authors: I. Farahbakhsh, Hassan Ghassemi, Fereidoun SabetghadamAbstract:Copyright © The Society of Theoretical and Applied Mechanics, 2014. An immersed boundary method is proposed for the simulation of the interaction of an incompressible flow with rigid bodies. The method is based on a new interpretation of velocity-vorticity formulation and no longer includes the force term which is an essential issue of common immersed boundary methods. The system is considered in an Eulerian frame and retrieving the vorticity in this formulation enforces continuity at the fluid-solid interface and rigid motion of the solid. The method focuses on the mutual Kinematic Relations between the velocity and vorticity fields and with retrieving the vorticity field and recalculating the velocities yields the solenoidal velocity field. The method is applied to the two dimensional problems and the results show that the solenoidality is satisfied acceptably. The comparisons with 2D test cases are provided to illustrate the capabilities of the proposed method.
Y. F. Li - One of the best experts on this subject based on the ideXlab platform.
-
A new descriptor for multiple 3D motion trajectories recognition
2013 IEEE International Conference on Robotics and Automation, 2013Co-Authors: Zhanpeng Shao, Y. F. LiAbstract:Motion trajectory gives a meaningful and informative clue in characterizing the motions of human, robots or moving objects. Hence, the descriptor for motion trajectory plays an importance role in motion recognition for many robotic tasks. However, an effective and compact descriptor for multiple 3D motion trajectories under complicated situation is lacking. In this paper, we propose a novel invariant descriptor for multiple motion trajectories based on the Kinematic Relation among multiple moving parts. There are two kinds of Kinematic Relation among multiple trajectories: articulated and independent trajectories. Spherical coordinate system is introduced to get a uniform and compact representation for both kinds of trajectories, where the relative trajectory concept are firstly defined based on orientation and distance changes in favor of acquiring relative movement features of each child trajectory with respect to the root trajectory. Then, by incorporating both the differential invariants of root trajectory and orientation, distance variations of each relative trajectory respectively, the new descriptor is constructed. Finally, effectiveness and robustness of our proposed new descriptor for multiple trajectories under complex circumstance are validated by the conducted two experiments for sign language and human action recognition.
Rubén Heras Evangelio - One of the best experts on this subject based on the ideXlab platform.
-
AVSS - Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
-
Boosting Multi-hypothesis Tracking by Means of Instance-Specific Models
2012 IEEE Ninth International Conference on Advanced Video and Signal-Based Surveillance, 2012Co-Authors: Michael Pätzold, Rubén Heras Evangelio, Thomas SikoraAbstract:In this paper we present a visual person tracking-by-detection system based on on-line-learned instance-specific information along with the Kinematic Relation of measurements provided by a generic person-category detector. The proposed system is able to initialize tracks on individual persons and start learning their appearance even in crowded situations and does not require that a person enters the scene separately. For that purpose we integrate the process of learning instance-specific models into a standard MHT-framework. The capability of the system to eliminate detections-to-object association ambiguities occurring from missed detections or false ones is demonstrated by experiments for counting and tracking applications using very long video sequences on challenging outdoor scenarios.
