H
Hanzi Wang
Researcher at Xiamen University
Publications - 236
Citations - 4270
Hanzi Wang is an academic researcher from Xiamen University. The author has contributed to research in topics: Convolutional neural network & Video tracking. The author has an hindex of 33, co-authored 225 publications receiving 3444 citations. Previous affiliations of Hanzi Wang include Johns Hopkins University & University of Adelaide.
Papers
More filters
Journal ArticleDOI
Adaptive Object Tracking Based on an Effective Appearance Filter
TL;DR: A similarity measure based on a spatial-color mixture of Gaussians (SMOG) appearance model for particle filters that can successfully track objects in many difficult situations is proposed and a new technique with which the computational time is greatly reduced is proposed.
Journal ArticleDOI
A consensus-based method for tracking: Modelling background scenario and foreground appearance
Hanzi Wang,David Suter +1 more
TL;DR: The proposed method computes SAmple CONsensus (SACON) of the background samples and estimates a statistical model of thebackground, per pixel, which is employed to segment and track people through occlusions.
Journal ArticleDOI
Robust adaptive-scale parametric model estimation for computer vision
Hanzi Wang,David Suter +1 more
TL;DR: ASSC can simultaneously estimate the parameters of a model and the scale of the inliers belonging to that model and this work proposes two novel robust techniques: the two-step scale estimator (TSSE) and the adaptive scale sample consensus (ASSC) estimator.
Journal ArticleDOI
Simultaneously Fitting and Segmenting Multiple-Structure Data with Outliers
TL;DR: A robust fitting framework, called Adaptive Kernel-Scale Weighted Hypotheses (AKSWH), to segment multiple-structure data even in the presence of a large number of outliers, which contains a novel scale estimator called Iterative Kth Ordered Scale Estimator (IKOSE).
Proceedings ArticleDOI
Robust fitting of multiple structures: The statistical learning approach
TL;DR: A novel Mercer kernel is designed for the robust estimation problem which elicits the potential of two points to have emerged from the same underlying structure and permits the application of well-grounded statistical learning methods for robust fitting.