Hai Tao

Publication List Details

Period

1994 - 2009

Number

50

Co-Authors

Motion Observability Analysis of the Simplified Color Correlogram for Visual Tracking (2009)

Qi Zhao, Hai Tao

Abstract. Compared with the color histogram, where the position information of each pixel is ignored, a simplified color correlogram (SCC) representation encodes the spatial information explicitly...

Differential Earth Mover’s Distance with Its Applications to Visual Tracking (2009)

Qi Zhao, Student Member, Ieee Computer Society, Hai Tao

Abstract — The Earth Mover’s Distance (EMD) is a similarity measure that captures perceptual difference between two distributions. Its computational complexity, however, prevents a direct use in...

ACCEPTED MANUSCRIPT A Motion Observable Representation Using Color Correlogram and Its Applications to Tracking (2009)

Qi Zhao, Hai Tao, Qi Zhao, Hai Tao

This is a PDF file of an unedited manuscript that has been accepted for publication. As a service to our customers we are providing this early version of the manuscript. The manuscript will undergo...

A PIECEWISE BÉZIER VOLUME DEFORMATION MODEL AND ITS APPLICATIONS IN FACIAL MOTION CAPTURE (2009)

Hai Tao, Thomas S. Huang

Capturing real facial motions from videos enables automatic creation of dynamic models for facial animation. In this paper, we propose an explanation-based facial motion tracking algorithm based on a...

University of California,Santa Cruz �ÓÒ���Ò ×Ó � Ù × ��Ù (2009)

Dan Kong, Hai Tao

In this paper, we propose a new solution to the sparse image-based rendering (IBR) problem. Given two images taken from different viewpoints, our algorithm can accurately generate images from new...

An Orientation Normalized Vector Quantizer for Flow-like Image Coding (2009)

Hai Tao, Zhaoqi Bian

A new vector quantization image coding scheme called orientation normalized vector quantizer (ONVQ) is presented in this paper. During the encoding pro-cess, the orientation freld of an image is fist...

LOSSLESS PROGRESSIVE TRANSMISSION OF SCIENTIFIC DATA USING BIORTHOGONAL WAVELET TRANSFORM (2008)

Hai Tao, Robert J. Moorhead

A new progressive transmission scheme using spline biorthogorial wavelet bases is proposed in this paper: First, several wavelet bases are compared with the spline biorthogo-nul nmvlet bases. By...

Non-orthogonal Binary Expansion of Gabor Filters with Applications in Object Tracking (2008)

Feng Tang, Hai Tao

Gabor filter response is widely used in many computer vision applications for its effectiveness in representing local image details. The major drawback of Gabor features is the high computation cost...

Visual Face Tracking and its Application to 3D Model-Based Video Coding (2008)

Thomas S. Huang, Hai Tao

The MPEG4 standard supports the transmission and composition of facial animation with natural video by including a facial animation parameter (FAP) set that is defined based on the study of minimal...

Fast Linear Discriminant Analysis Using Binary Bases (2008)

Feng Tang, Hai Tao

Linear Discriminant Analysis (LDA) is a widely used technique for pattern classification. It seeks the linear projection of the data to a low dimensional subspace where the data features can be...

Representing Images Using Nonorthogonal Haar-Like Bases (2008)

Feng Tang, Student Member, Ryan Crabb, Student Member, Hai Tao, Senior Member

Abstract—The efficient and compact representation of images is a fundamental problem in computer vision. In this paper, we propose methods that use Haar-like binary box functions to represent a...

Differential EMD Tracking (2008)

Qi Zhao, Shane Brennan, Hai Tao

Illumination changes cause object appearance to change drastically and many existing tracking algorithms lack the capability to handle this problem. The Earth Mover’s Distance (EMD) is a similarity...

A Conditional Random Field Model for Video Super-resolution (2008)

Dan Kong, Mei Han, Wei Xu, Hai Tao, Yihong Gong

In this paper, we propose a learning-based method for video super-resolution. There are two main contributions of the proposed method. First, information from cameras with different spatial-temporal...

University of California,Santa Cruz �ÓÒ���Ò ×Ó � Ù × ��Ù (2008)

Dan Kong, Hai Tao

In this paper, we propose a new solution to the sparse image-based rendering (IBR) problem. Given two images taken from different viewpoints, our algorithm can accurately generate images from new...

Counting Pedestrians in Crowds Using Viewpoint Invariant Training (2008)

Dan Kong, Doug Gray, Hai Tao

This paper describes a learning-based method for counting people in crowds from a single camera. Our method takes into account feature normalization to deal with perspective projection and different...

Background Modeling Using Time Dependent Markov Random Field With Image Pyramid (2008)

Wei Xu, Yue Zhou, Yihong Gong, Hai Tao

Background modeling is important for video surveillance. In the paper, we present a novel background modeling algorithm based on probabilistic graphic model and Gibbs Sampling. The background is...

Motion Observability Analysis of the Simplified Color Correlogram for Visual Tracking (2008)

Qi Zhao, Hai Tao

Abstract. Compared with the color histogram, where the position information of each pixel is ignored, a simplified color correlogram (SCC) representation encodes the spatial information explicitly...

Multi-Object Trajectory Tracking (2008)

Mei Han, Wei Xu, Hai Tao, Yihong Gong

The majority of existing tracking algorithms are based on the maximum a posteriori (MAP) solution of a probabilistic framework using a Hidden Markov Model, where the distribution of the object state...

University of California,Santa Cruz �ÓÒ���Ò ×Ó � Ù × ��Ù (2008)

Dan Kong, Hai Tao, Hector Gonzalez

In this paper, we propose a new solution to the sparse image-based rendering (IBR) problem. Given two images taken from different viewpoints, our algorithm can accurately generate images from new...

Lab of Neuro Imaging (2008)

Piotr Dollár, Zhuowen Tu, Hai Tao, Serge Belongie

The efficiency and robustness of a vision system is often largely determined by the quality of the image features available to it. In data mining, one typically works with immense volumes of raw...

Stereo Matching via Learning Multiple Experts Behaviors (2008)

Dan Kong, Hai Tao

Window-based matching such as normalized cross-correlation (NCC) can reliably estimate depth even when the constant brightness assumption is violated in stereo due to imaging noise or different...

Representing images using nonorthogonal Haar-like bases (2007)

Tang, Feng, Crabb, Ryan, Tao, Hai

The efficient and compact representation of images is a fundamental problem in computer vision. In this paper, we propose methods that use Haar- like binary box functions to represent a single image...

Fast linear discriminant analysis using binary bases (2007)

Tang, Feng, Tao, Hai

Linear Discriminant Analysis (LDA) is a widely used technique for pattern classification. It seeks the linear projection of the data to a low dimensional subspace where the data features can be...

Fast multi-scale template matching using binary features (2007)

Feng Tang, Hai Tao

Template matching is one of the key problems in computer vision and has been widely used in tracking, recognition and many other applications. Traditional methods are usually slow because the...

Binary principal component analysis (2006)

Feng Tang, Hai Tao

Efficient and compact representation of images is a fundamental problem in computer vision. Principal Component Analysis (PCA) has been widely used for image representation and has been successfully...

Part Based Human Tracking in A Multiple Cues Fusion Framework. ICPR (2006)

Qi Zhao, Jinman Kang, Hai Tao, Wei Hua

This paper presents a real time video surveillance system which is capable of tracking multiple humans simultaneously. To better deal with various challenging issues such as occlusions, sharp motion...

Video superresolution with scene-specific priors (2006)

Dan Kong, Mei Han, Wei Xu, Hai Tao, Yihong Gong

In this paper, we propose a method to improve the spatial resolution of video sequences. Our approach is inspired by previous image hallucination work [12]. There are two main contributions of the...

H.: Object tracking with dynamic feature graph (2005)

Feng Tang, Hai Tao

Two major problems for model-based object tracking are: 1) how to represent an object so that it can effectively be discriminated with background and other objects; 2) how to dynamically update the...

Non-orthogonal binary subspace and its applications in computer vision (2005)

Hai Tao, Ryan Crabb, Feng Tang

This paper presents a novel approach that represents an image or a set of images using a nonorthogonal binary subspace (NBS) spanned by boxlike base vectors. These base vectors possess the property...

Dynamic depth recovery from unsynchronized video streams (2003)

Chunxiao Zhou, Hai Tao

In this paper, we propose an algorithm for estimating dense depth information of dynamic scenes from multiple video streams captured using unsynchronized stationary cameras. We solve this problem by...

Image hallucination with primal sketch priors (2003)

Jian Sun, Nan-ning Zheng, Hai Tao, Heung-yeung Shum

In this paper, we propose a Bayesian approach to image hallucination. Given a generic low resolution image, we hallucinate a high resolution image using a set of training images. Our work is inspired...

Object tracking with Bayesian estimation of dynamic layer representations (2002)

Hai Tao, Harpreet S. Sawhney, Rakesh Kumar

Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that enables applications...

Compression and transmission of depth maps for image-based rendering (2001)

Ravi Krishnamurthy, Bing-bing Chai, Hai Tao, Sriram Sethuraman

We consider applications using depth-based Imagebased rendering (IBR), where the synthesis of arbitrary views occur at a remote location, necessitating the compression and transmission of depth-maps....

Dynamic depth recovery from multiple synchronized video streams (2001)

Hai Tao, Harpreet S. Sawhney, Rakesh Kumar

This paper addresses the problem of extracting depth information of non-rigid dynamic 3D scenes from multiple synchronized video streams. Three main issues are discussed in this context: (i)...

Global matching criterion and color segmentation based stereo (2000)

Hai Tao, Harpreet S. Sawhney

In this paper, we present a new analysis by synthesis computational framework for stereo vision. It is designed to achieve the following goals: (1) enforcing global visibility constraints, (2)...

Global matching criterion and color segmentation based stereo (2000)

Hai Tao, Harpreet S. Sawhney

In this paper, we present a new analysis by synthesis computational framework for stereo vision. It is designed to achieve the following goals: (1) enforcing global visibility constraints, (2)...

Frequency translating bandpass sigma-delta modulation for analog-to-digital conversion (1999)

Tao, Hai

Bandpass Sigma-Delta analog-to-digital (A/D) converters have shown great potential for digitizing intermediate frequency (IF) signals in wireless communication systems. Current implementations of...

Compression of MPEG-4 Facial Animation Parameters for Transmission of Talking Heads (1999)

Hai Tao, Homer H. Chen, Wei Wu, Thomas S. Huang

Abstract—The emerging MPEG-4 standard supports the transmission and composition of facial animation with natural video. The new standard will include a facial animation parameter (FAP) set that is...

A Sampling Algorithm for Tracking Multiple Objects (1999)

Hai Tao, Harpreet Sawhney, Rakesh Kumar

Tracking unknown number of moving objects in cluttered scenes is an important yet difficult research issue in computer vision. Two fundamental problems encountered are high-dimensional parameter...

Bimodal Emotion Recognition by Man and Machine (1998)

Thomas S. Huang, Lawrence S. Chen, Hai Tao, Tsutomu Miyasato, Ryohei Nakatsu

In this paper, we report preliminary results of recognizing emotions using both speech and video by machine. We applied automatic feature analysis and extraction algorithms to the same data used by...

Connected Vibrations: A Modal Analysis Approach for Non-rigid Motion Tracking (1998)

Hai Tao, Thomas S. Huang

A new framework is presented in this paper for tracking non-rigid motion in image sequences. This method models non-rigid motions as the deformations of connected 2D membrane patches. Local...

Facial Modeling (1997)

Hai Tao

This report summarize the progress of our research work in human face modeling for model-based video compression purpose. The second chapter introduce our static model, which is not completely...

Color Image Edge Detection Using Cluster Analysis (1997)

Hai Tao, Thomas S. Huang

A color image edge detection algorithm is proposed in this paper based on the idea that use global color information to guide local gradient computation. Major chromatic components of an image are...

Lossless Progressive Transmission of Scientific Data Using Biorthogonal Wavelet Transform (1994)

Hai Tao

A new progressive transmission scheme using spline biorthogonal wavelet bases is proposed in this paper. First, several wavelet bases are compared with the spline biorthogonal wavelet bases. By...

Progressive Transmission of Scientific Data Using Biorthogonal Wavelet Transform (1994)

Hai Tao

An important issue in scientific visualization systems is the management of data sets. Most data sets in scientific visualization, whether created by measurement or simulation, are usually...