66 Result(s)
within
Computer Imaging, Vision, Pattern Recognition and Graphics
Han**g Wang
-
Article
MDPE: A Very Robust Estimator for Model Fitting and Range Image Segmentation
In this paper, we propose a novel and highly robust estimator, called MDPE1 (Maximum Density Power Estimator). This estimator applies nonparametric density estimation and density gradient estimation techniques in...
-
Chapter and Conference Paper
Smooth Foreground-Background Segmentation for Video Processing
We propose an efficient way to account for spatial smoothness in foreground-background segmentation of video sequences. Most statistical background modeling techniques regard the pixels in an image as independ...
-
Chapter and Conference Paper
A Novel Robust Statistical Method for Background Initialization and Visual Surveillance
In many visual tracking and surveillance systems, it is important to initialize a background model using a training video sequence which may include foreground objects. In such a case, robust statistical metho...
-
Chapter and Conference Paper
Stochastic Modeling and Quality Evaluation of Workflow Systems Based on QWF-Nets
Quality (QOS) prediction is one of the most important research topics of workflow management system. In this paper, we propose the SWQ approach to analytically evaluate QOS of workflow systems based on QWF-net...
-
Chapter and Conference Paper
Analyzing Data Dependence Based on Workflow Net
Workflow management systems (WfMSs) frequently use data to coordinate the execution of workflow instances. A WfMS makes routing decisions according to data constraints. This paper presents an extended workflow...
-
Chapter and Conference Paper
Isotropic Design of Stewart Platform-Based Force Sensor
The modified isotropy indices of Stewart platform-based force sensor are proposed by introducing the orthogonality condition, the physical meanings of the modified isotropy indices, the orthogonality condition...
-
Article
A Model-Selection Framework for Multibody Structure-and-Motion of Image Sequences
Given an image sequence of a scene consisting of multiple rigidly moving objects, multi-body structure-and-motion (MSaM) is the task to segment the image feature tracks into the different rigid objects and co...
-
Chapter and Conference Paper
Toward Video-Based Navigation for Endoscopic Endonasal Skull Base Surgery
Endoscopic endonasal skull base surgery (ESBS) requires high accuracy to ensure safe navigation of the critical anatomy at the anterior skull base. Current navigation systems provide approximately 2mm accuracy. T...
-
Chapter and Conference Paper
Learning Group Activity in Soccer Videos from Local Motion
This paper proposes a local motion-based approach for recognizing group activities in soccer videos. Given the SIFT keypoint matches on two successive frames, we propose a simple but effective method to group ...
-
Chapter and Conference Paper
Human Action Recognition Using Pyramid Vocabulary Tree
The bag-of-visual-words (BOVW) approaches are widely used in human action recognition. Usually, large vocabulary size of the BOVW is more discriminative for inter-class action classification while small one is...
-
Chapter and Conference Paper
Class-Specified Segmentation with Multi-scale Superpixels
This paper proposes a class-specified segmentation method, which can not only segment foreground objects from background at pixel level, but also parse images. Such class-specified segmentation is very helpful...
-
Article
Evolutionary Extreme Learning Machine and Its Application to Image Analysis
Extreme learning machine (ELM) and evolutionary ELM (E-ELM) were proposed as a new class of learning algorithm for single-hidden layer feedforward neural network (SLFN). In order to achieve good generalizatio...
-
Chapter and Conference Paper
Robust Maximum Margin Correlation Tracking
Recent decade has seen great interest in the use of discriminative classifiers for tracking. Most trackers, however, focus on correct classification between the target and background. Though it achieves good g...
-
Article
GPS/odometry/map fusion for vehicle positioning using potential function
In this paper, we present a fusion approach to localize urban vehicles by integrating a visual odometry, a low-cost GPS, and a two-dimensional digital road map. Distinguished from conventional sensor fusion me...
-
Article
Mixed \({L}_{1}\) norm and \({L}_{2}\) norm regularized sparsity adaptive matching pursuit algorithm
The sparsity adaptive matching pursuit (SAMP) algorithm has an advantage of reconstructing signals without the prior information of the sparsity level. However, the required computational power is high and the...
-
Article
A Modeling Language for MapReduce Programing in a Storage System Perspective
MapReduce is a powerful distributed data analysis programming model. It runs on big data storage systems and processes data in a parallel way. An appropriate way to ensure the correctness of MapReduce programs...
-
Article
Open AccessPerson Re-identification in Identity Regression Space
Most existing person re-identification (re-id) methods are unsuitable for real-world deployment due to two reasons: Unscalability to large population size, and Inadaptability over time. In this work, we present a...
-
Article
Superpixel-Guided Two-View Deterministic Geometric Model Fitting
Geometric model fitting is a fundamental research topic in computer vision and it aims to fit and segment multiple-structure data. In this paper, we propose a novel superpixel-guided two-view geometric model f...
-
Article
Performance Analysis of Mobile Multiuser Cooperative Networks with TAS Schemes
In this paper, the outage probability (OP) performance of mobile multiuser networks with transmit antenna selection (TAS) and selection combing(SC) is investigated. The exact closed-form OP expressions of the ...
-
Article
Detonator coded character spotting based on convolutional neural networks
To facilitate the management of detonators, an automatic spotting system is proposed for detonator coded characters based on convolutional neural networks. The system contains a multi-scale detection network, ...
