P
Pan Pan
Researcher at Fujitsu
Publications - 5
Citations - 90
Pan Pan is an academic researcher from Fujitsu. The author has contributed to research in topics: Particle filter & Directed graph. The author has an hindex of 4, co-authored 5 publications receiving 87 citations. Previous affiliations of Pan Pan include University of Illinois at Urbana–Champaign.
Papers
More filters
Journal ArticleDOI
Visual Tracking Using High-Order Particle Filtering
Pan Pan,Dan Schonfeld +1 more
TL;DR: This letter extends the first-order Markov chain model commonly used in visual tracking and presents a novel framework of visual tracking using high-order Monte Carlo MarkovChain to derive a general expression for the posterior density function of an m th-order hidden Markov model.
Journal ArticleDOI
Video Tracking Based on Sequential Particle Filtering on Graphs
Pan Pan,Dan Schonfeld +1 more
TL;DR: A novel solution for particle filtering on general graphs that relies on a partial-order relation in an antichain decomposition that forms a high-order Markov chain over the partitioned graph to derive a closed-form sequential updating scheme for conditional density propagation.
Journal ArticleDOI
Image Reconstruction and Multidimensional Field Estimation From Randomly Scattered Sensors
Pan Pan,Dan Schonfeld +1 more
TL;DR: A novel approach to the study of signal reconstruction from random samples in a multidimensional space is presented and it is demonstrated that it forms a sequence of unbiased estimates for band-limited signals, which converge to the true function in the mean-square sense.
Proceedings ArticleDOI
Sequential particle filtering for conditional density propagation on graphs
Pan Pan,Dan Schonfeld +1 more
TL;DR: Novel solutions for particle filtering on graphs by splitting the graphs with cycles into multiple directed cycle-free subgraphs and the proposed solution for distributed multiple object tracking are developed.
Proceedings ArticleDOI
Adaptive Particle-Distortion Tradeoff Control in Particle Filtering for Video Tracking
Pan Pan,Dan Schonfeld +1 more
TL;DR: This paper proposes the dynamic proposal variance and optimal particle number allocation algorithm for video tracking systems which minimizes the total tracking distortion by considering dynamic variance of proposal density and optimal number of particles for each frame.