Y
Yunfei Zheng
Researcher at Princeton University
Publications - 76
Citations - 1228
Yunfei Zheng is an academic researcher from Princeton University. The author has contributed to research in topics: Encoder & Motion estimation. The author has an hindex of 20, co-authored 66 publications receiving 1211 citations. Previous affiliations of Yunfei Zheng include InterDigital, Inc. & West Virginia University.
Papers
More filters
Journal ArticleDOI
Pedestrian detection and tracking in infrared imagery using shape and appearance
Congxia Dai,Yunfei Zheng,Xin Li +2 more
TL;DR: A layered representation is first introduced and a generalized expectation-maximization (EM) algorithm is developed to separate infrared images into background (still) and foreground (moving) layers regardless of camera panning to facilitate pedestrian tracking.
Proceedings ArticleDOI
Layered Representation for Pedestrian Detection and Tracking in Infrared Imagery
Congxia Dai,Yunfei Zheng,Xin Li +2 more
TL;DR: A hybrid (shape+appearance) algorithm for pedestrian detection, in which shape cue is first used to eliminate non-pedestrian moving objects and appearance cue is then used to pin down the location of pedestrians, is proposed.
Patent
Methods and apparatus for template matching prediction (tmp) in video encoding and decoding
TL;DR: In this article, a template matching algorithm for video encoding and decoding is presented, where an encoder is used to encode a target block in a picture by determining at least one predictor for the target block and then utilizing the at least predictor as a template to search for additional additional predictor for target block.
Journal ArticleDOI
Patch-Based Video Processing: A Variational Bayesian Approach
Xin Li,Yunfei Zheng +1 more
TL;DR: This paper proposes to embed motion-related information into the relationship among video patches and develop a nonlocal sparsity-based prior for typical video sequences and treats both patch clustering result and unobservable data as latent variables and solve the inference problem via variational EM algorithms.
Proceedings ArticleDOI
Intra prediction using template matching with adaptive illumination compensation
TL;DR: A template matching technique with locally adaptive illumination compensation, based on a linear compensation model with a scaling and an offset parameters to compensate for contrast and brightness disparities respectively, to improve intra coding efficiency compared to H.264/AVC.