R. Rosales and S. Sclaroff. Trajectory guided tracking and recognition actions. TR BU-CS- 99-002, Boston U., 1999. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Unknown - (1998) Self-citation (Rosales Sclaroff) (Correct)
No context found.
R. Rosales and S. Sclaroff. Trajectory guided tracking and recognition actions. TR BU-CS- 99-002, Boston U., 1999.
Extraction and Clustering of Motion Trajectories in Video - Buzan, Sclaroff, Kollios (2004) Self-citation (Sclaroff) (Correct)
No context found.
R. Rosales, S. Sclaroff. "Trajectory Guided Tracking and Recognition of Actions" TR-CS-1999-002, Boston Univ.
Robust Tracking of Human Motion - Buzan (2004) Self-citation (Sclaroff) (Correct)
No context found.
Rmer Rosales, Stan Sclaroff. "Trajectory Guided Tracking and Recognition of Actions" Technical Report TR BU-CS- 1999-002, Boston University, September, 1999
3D Trajectory Recovery for Tracking Multiple Objects and.. - Rosales, Sclaroff (1999) Self-citation (Rosales Sclaroff) (Correct)
....to be used via MDL principle: prqtsBuwvyxMzE v, z n Pl o m 3 J zE (10) where is the number of parameters in the model (defining the Gaussian mixture) and is the number of samples in the training data. For further details about the model estimation module, see [25]. 5.1 Trajectory Guided Recognition In theory it is necessary to learn representations of every action from all possible directions. We denote to be the set of PDF s used to represent actions under direction . Each action 5 has its own PDF, n ;m N 3 o l ( Acquiring such a ....
....directly the appropriate PDF, instead of exhaustively searching over all possible directions and all possible actions. Finally, it is possible to adapt the partioning of the direction space based on distribution of data [17] For a complete description of the TGR approach, readers are directed to [25]. TGR is performed at every time step as follows: For each moving object Compute EKF trajectory estimate 4 and error covariance If y, and object is not occluded then 1. Compute stabilized MEI and MHI 2. Compute PCA feature vector 3. Find whose orientation is closest to ....
R. Rosales and S. Sclaroff. Trajectory guided tracking and recognition actions. TR BU-CS- 99-002, Boston U., 1999.
3D Trajectory Recovery for Tracking Multiple Objects and.. - Rosales, Sclaroff (1999) Self-citation (Rosales Sclaroff) (Correct)
....be used via MDL principle: MDL : arg max Theta i ;k (log P (OEj Theta i ) Gamma k 2 log n) 10) where k is the number of parameters in the model (defining the Gaussian mixture) and n is the number of samples in the training data. For further details about the model estimation module, see [25]. 5.1 Trajectory Guided Recognition In theory it is necessary to learn representations of every action from all possible directions. We denote P j to be the set of PDF s used to represent m actions under direction j. Each action i has its own PDF, P ( Theta (j) i jOE k ) 2 P j . Acquiring ....
....directly the appropriate PDF, instead of exhaustively searching over all possible directions and all possible actions. Finally, it is possible to adapt the partioning of the direction space based on distribution of data [17] For a complete description of the TGR approach, readers are directed to [25]. TGR is performed at every time step k as follows: For each moving object l Compute EKF trajectory estimate xk and error covariance Pk If T race(Pk ) ffl and object l is not occluded then 1. Compute stabilized MEI and MHI 2. Compute PCA feature vector OE k 3. Find P j whose orientation ....
R. Rosales and S. Sclaroff. Trajectory guided tracking and recognition actions. TR BU-CS- 99-002, Boston U., 1999.
On the use of Anthropometry in the Invariant Analysis of.. - Gritai, Sheikh, Shah (2004) (Correct)
No context found.
R. Rosales and S. Sclaroff. Trajectory guided tracking and recognition of actions. PAMI Special Issue on Video Surveillance and Monitoring, 1999.
Image Processing and Behaviour Planning for.. - Bücher, Curio.. (Correct)
No context found.
R. Rosales and S. Sclaro#, "Trajectory guided tracking and recognition actions," Tech. Rep., BU-CS- 99-002, Boston University, 1999.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC