Search For:

Displaying 1-18 out of 18 total
Joint Segmentation and Pose Tracking of Human in Natural Videos
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Taegyu Lim,Seunghoon Hong,Bohyung Han,Joon Hee Han
Issue Date:December 2013
pp. 833-840
We propose an on-line algorithm to extract a human by foreground/background segmentation and estimate pose of the human from the videos captured by moving cameras. We claim that a virtuous cycle can be created by appropriate interactions between the two mo...
 
Generalized background subtraction based on hybrid inference by belief propagation and Bayesian filtering
Found in: Computer Vision, IEEE International Conference on
By Suha Kwak, Taegyu Lim, Woonhyun Nam, Bohyung Han, Joon Hee Han
Issue Date:November 2011
pp. 2174-2181
We propose a novel background subtraction algorithm for the videos captured by a moving camera. In our technique, foreground and background appearance models in each frame are constructed and propagated sequentially by Bayesian filtering. We estimate the p...
 
Learning occlusion with likelihoods for visual tracking
Found in: Computer Vision, IEEE International Conference on
By Suha Kwak, Woonhyun Nam, Bohyung Han, Joon Hee Han
Issue Date:November 2011
pp. 1551-1558
We propose a novel algorithm to detect occlusion for visual tracking through learning with observation likelihoods. In our technique, target is divided into regular grid cells and the state of occlusion is determined for each cell using a classifier. Each ...
 
Scenario-based video event recognition by constraint flow
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Suha Kwak, Bohyung Han, Joon Hee Han
Issue Date:June 2011
pp. 3345-3352
We present a novel approach to representing and recognizing composite video events. A composite event is specified by a scenario, which is based on primitive events and their temporal-logical relations, to constrain the arrangements of the primitive events...
 
Orderless Tracking through Model-Averaged Posterior Estimation
Found in: 2013 IEEE International Conference on Computer Vision (ICCV)
By Seunghoon Hong,Suha Kwak,Bohyung Han
Issue Date:December 2013
pp. 2296-2303
We propose a novel offline tracking algorithm based on model-averaged posterior estimation through patch matching across frames. Contrary to existing online and offline tracking methods, our algorithm is not based on temporally-ordered estimates of target ...
 
A fast nearest neighbor search algorithm by nonlinear embedding
Found in: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Yoonho Hwang, Bohyung Han, Hee-Kap Ahn
Issue Date:June 2012
pp. 3053-3060
We propose an efficient algorithm to find the exact nearest neighbor based on the Euclidean distance for large-scale computer vision problems. We embed data points nonlinearly onto a low-dimensional space by simple computations and prove that the distance ...
 
Density-Based Multifeature Background Subtraction with Support Vector Machine
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bohyung Han,Larry S. Davis
Issue Date:May 2012
pp. 1017-1023
Background modeling and subtraction is a natural technique for object detection in videos captured by a static camera, and also a critical preprocessing step in various high-level computer vision applications. However, there have not been many studies conc...
 
Efficient extraction of human motion volumes by tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Juan Carlos Niebles, Bohyung Han, Li Fei-Fei
Issue Date:June 2010
pp. 655-662
We present an automatic and efficient method to extract spatio-temporal human volumes from video, which combines top-down model-based and bottom-up appearance-based approaches. From the top-down perspective, our algorithm applies shape priors probabilistic...
 
Visual Tracking by Continuous Density Propagation in Sequential Bayesian Filtering Framework
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bohyung Han, Ying Zhu, Dorin Comaniciu, Larry S. Davis
Issue Date:May 2009
pp. 919-930
Particle filtering is frequently used for visual tracking problems since it provides a general framework for estimating and propagating probability density functions for nonlinear and non-Gaussian dynamic systems. However, this algorithm is based on a Mont...
 
Probabilistic Fusion Tracking Using Mixture Kernel-Based Bayesian Filtering
Found in: Computer Vision, IEEE International Conference on
By Bohyung Han, Seong-Wook Joo, Larry S. Davis
Issue Date:October 2007
pp. 1-8
Even though sensor fusion techniques based on particle filters have been applied to object tracking, their implementations have been limited to combining measurements from multiple sensors by the simple product of individual likelihoods. Therefore, the num...
 
Sequential Kernel Density Approximation and Its Application to Real-Time Visual Tracking
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Bohyung Han, Dorin Comaniciu, Ying Zhu, Larry S. Davis
Issue Date:July 2008
pp. 1186-1197
Visual features are commonly modeled with probability density functions in computer vision problems, but current methods such as a mixture of Gaussians and kernel density estimation suffer from either the lack of flexibility, by fixing or limiting the numb...
 
Semi-Parametric Model-Based Clustering for DNA Microarray Data
Found in: Pattern Recognition, International Conference on
By Bohyung Han, Larry S. Davis
Issue Date:August 2006
pp. 324-327
Various clustering methods have been proposed for the analysis of gene expression data, but conventional clustering algorithms have several critical limitations; how to set parameters such as number of clusters, initial cluster centers, and so on. In this ...
 
On-Line Density-Based Appearance Modeling for Object Tracking
Found in: Computer Vision, IEEE International Conference on
By Bohyung Han, Larry Davis
Issue Date:October 2005
pp. 1492-1499
Object tracking is a challenging problems in real-time computer vision due to variations of lighting condition, pose, scale, and view-point over time. However, it is exceptionally difficult to model appearance with respect to all of those variations in adv...
 
Kernel-Based Bayesian Filtering for Object Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bohyung Han, Ying Zhu, Dorin Comaniciu, Larry Davis
Issue Date:June 2005
pp. 227-234
Particle filtering provides a general framework for propagating probability density functions in non-linear and non-Gaussian systems. However, the algorithm is based on a Monte Carlo approach and sampling is a problematic issue, especially for high dimensi...
 
Robust Routing in Wireless Ad Hoc Networks
Found in: Parallel Processing Workshops, International Conference on
By Seungjoon Lee, Bohyung Han, Minho Shin
Issue Date:August 2002
pp. 73
A wireless ad hoc network is a collection of mobile nodes with no fixed infrastructure. The absence of central authorization facility in dynamic and distributed environment requires collaboration among nodes. When a source searches for a route to a destina...
 
On-line Video Event Detection by Constraint Flow
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Suha Kwak,Bohyung Han,Joon Hee Han
Issue Date:December 2013
pp. 1
We present a novel approach to describing and detecting composite video events based on scenarios, which constrain the configurations of target events by temporal-logical structures of primitive events. We propose a new scenario description method to repre...
 
Multi-agent Event Detection: Localization and Role Assignment
Found in: 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
By Suha Kwak,Bohyung Han,Joon Hee Han
Issue Date:June 2013
pp. 2682-2689
We present a joint estimation technique of event localization and role assignment when the target video event is described by a scenario. Specifically, to detect multi-agent events from video, our algorithm identifies agents involved in an event and assign...
 
Incremental Density Approximation and Kernel-Based Bayesian Filtering for Object Tracking
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Bohyung Han, Dorin Comaniciu, Ying Zhu, Larry Davis
Issue Date:July 2004
pp. 638-644
Statistical density estimation techniques are used in many computer vision appications such as object tracking, background subtraction, motion estimation and segmentation. The particle filter (Condensation) algorithm provides a general framework for estima...
 
 1