Rynson W. H. Lau

Visual Tracking via Locality Sensitive Histograms

This paper presents a novel locality sensitive histogram algorithm for visual tracking. Unlike the conventional image histogram that counts the frequency of occurrences of each intensity value by adding ones to the corresponding bin, a locality sensitive histogram is computed at each pixel location and a floating-point value is added to the corresponding bin for each occurrence of an intensity value. The floating-point value declines exponentially with respect to the distance to the pixel location where the histogram is computed, thus every pixel is considered but those that are far away can be neglected due to the very small weights assigned. An efficient algorithm is proposed that enables the locality sensitive histograms to be computed in time linear in the image size and the number of bins. A robust tracking framework based on the locality sensitive histograms is proposed, which consists of two main components: a new feature for tracking that is robust to illumination changes and a novel multi-region tracking algorithm that runs in real time even with hundreds of regions. Extensive experiments demonstrate that the proposed tracking framework outperforms the state-of-the-art methods in challenging scenarios, especially when the illumination changes dramatically.

CHECK: a document plagiarism detection system

Digital documents are vulnerable to being copied. Most existing copy detection prototypes employ an exhaustive sentence-based comparison method in comparing a potential plagiarized document against a repository of legal or original documents to identify plagiarism activities. This approach is not scalable due to the potentially large number of original documents and the large number of sentences in each document . Furthermore, the security level of existing mechanisms is quite weak; a plagiarized document could simply by-pass the detection mechanisms by performing a minor modification on each sentence. In this paper, we propose a copy detection mechanism that will el iminate unnecessary comparisons. This is based on the observation that comparisons between two documents addressing different subjects are not necessary. We describe the design and implementation of our exper imental proto type called CHECK. The results of some exploratory experiments will be illust rated and the security level of our mechanism will be discussed.

Computing inverse kinematics with linear programming

Inverse Kinematics (IK) is a popular technique for synthesizing motions of virtual characters. In this paper, we propose a Linear Programming based IK solver (LPIK) for interactive control of arbitrary multibody structures. There are several advantages of using LPIK. First, inequality constraints can be handled, and therefore the ranges of the DOFs and collisions of the body with other obstacles can be handled easily. Second, the performance of LPIK is comparable or sometimes better than the IK method based on Lagrange multipliers, which is known as the best IK solver today. The computation time by LPIK increases only linearly proportional to the number of constraints or DOFs. Hence, LPIK is a suitable approach for controlling articulated systems with large DOFs and constraints for real-time applications.

A multi-server architecture for distributed virtual walkthrough

CyberWalk is a distributed virtual walkthrough system that we have developed. It allows users at different geographical locations to share information and interact within a common virtual environment (VE) via a local network or through the Internet. In this paper, we illustrate that when the number of users exploring the VE increases, the server will quickly become the bottleneck. To enable good performance, CyberWalk utilizes multiple servers and employs an adaptive data partitioning techniques to dynamically partition the whole VE into regions. All objects within each region will be managed by one server. Under normal circumstances, when a viewer is exploring a region, the server of that region will be responsible for serving all requests from the viewer. When a viewer is crossing the boundary of two or more regions, the servers of all the regions involved will be serving requests from the viewer since the viewer might be able to view objects within all those regions. We evaluate the performance of this multi-server architecture of CyberWalk via a detail simulation model.

CyberWalk: a web-based distributed virtual walkthrough environment

A distributed virtual walkthrough environment allows users connected to the geometry server to walk through a specific place of interest, without having to travel physically. This place of interest may be a virtual museum, virtual library or virtual university. There are two basic approaches to distribute the virtual environment from the geometry server to the clients, complete replication and on-demand transmission. Although the on-demand transmission approach saves waiting time and optimizes network usage, many technical issues need to be addressed in order for the system to be interactive. CyberWalk is a web-based distributed virtual walkthrough system developed based on the on-demand transmission approach. It achieves the necessary performance with a multiresolution caching mechanism. First, it reduces the model transmission and rendering times by employing a progressive multiresolution modeling technique. Second, it reduces the Internet response time by providing a caching and prefetching mechanism. Third, it allows a client to continue to operate, at least partially, when the Internet is disconnected. The caching mechanism of CyberWalk tries to maintain at least a minimum resolution of the object models in order to provide at least a coarse view of the objects to the viewer. All these features allow CyberWalk to provide sufficient interactivity to the user for virtual walkthrough over the Internet environment. In this paper, we demonstrate the design and implementation of CyberWalk. We investigate the effectiveness of the multiresolution caching mechanism of CyberWalk in supporting virtual walkthrough applications in the Internet environment through numerous experiments, both on the simulation system and on the prototype system.

Technology supports for distributed and collaborative learning over the internet

With the advent of Internet and World Wide Web (WWW) technologies, distance education (e-learning or Web-based learning) has enabled a new era of education. There are a number of issues that have significant impact on distance education, including those from educational, sociological, and psychological perspectives. Rather than attempting to cover exhaustively all the related perspectives, in this survey article, we focus on the technological issues. A number of technology issues are discussed, including distributed learning, collaborative learning, distributed content management, mobile and situated learning, and multimodal interaction and augmented devices for e-learning. Although we have tried to include the state-of-the-art technologies and systems here, it is anticipated that many new ones will emerge in the near future. As such, we point out several emerging issues and technologies that we believe are promising, for the purpose of highlighting important directions for future research.

On caching and prefetching of virtual objects in distributed virtual environments

.ld~~ces in networkg tetiology and the mtabkhtnent of the Morrnation Superhighway have rendered the virtnd Xbrary a concrete possibfi~. ?iTeze currently investigating user &\Terience in _ through a large virtual environment in the contti% of bternet. This provid~ users with the abiity to view t+ous virtual objects from tirent & t anca and angles, using common web browsers. To dtiver a good petiorrnance for such applications, we need to addr~s Several issues in Merent resemch discipbes. F&t., we must be able to modd virtual objects tiectivdy. The recently devdoped techniques for mdti-~olution object modting in computer graphics are of great Aue here, since they are capable of sintp~g the object mod& and therefore reducing the time to render them. Secon& tith the Eted bandwidth constraint of the btemet, we need to reduce the response time by reducing the amount of data requwted over the network One dtemative is to cache object mod& of high -w. Prefetching object mod~ by predicting those which ~e &dy to be used in the near fnture and dotioading them in advance wiU lead to a Mar improvement. Third, the bt.ernet often tiers from disconnection. A caching mechanism hat dews objects to be cached n?th at least the-mminimum resolution m be we~ to provide at least a coarse x<ew of the objects to a disconnected >tiewerfor improved ~hd perception. k this paper, m propose a multi-T~*oZutionaching m~hrmtim wd invG tigate its tiectiveness in supporthg virtud w~u~ apFEcations in the ktemet. environment. The caching mechanism is further complemented with severs object prefetching m echanLms for predicting future acc~ed objects. The performance of our proposed me~ and their feasibfities are qnsmtXed via s“mtdat.ed ~Terirnents.

A statistical similarity measure for aggregate crowd dynamics

We present an information-theoretic method to measure the similarity between a given set of observed, real-world data and visual simulation technique for aggregate crowd motions of a complex system consisting of many individual agents. This metric uses a two-step process to quantify a simulators ability to reproduce the collective behaviors of the whole system, as observed in the recorded real-world data. First, Bayesian inference is used to estimate the simulation states which best correspond to the observed data, then a maximum likelihood estimator is used to approximate the prediction errors. This process is iterated using the EM-algorithm to produce a robust, statistical estimate of the magnitude of the prediction error as measured by its entropy (smaller is better). This metric serves as a simulator-to-data similarity measurement. We evaluated the metric in terms of robustness to sensor noise, consistency across different datasets and simulation methods, and correlation to perceptual metrics.

Personalized courseware construction based on Web data mining

In order to adapt the teaching in accordance to an individual students ability in a distance learning environment, a method to construct personalized courseware is proposed by building a personalized Web tutor tree and mining both context and structure of the courseware. The concept of Web tutor objects and the notion of similarity are proposed. Five algorithms, including Naive Algorithm for tutor topic tree and Level-generate Algorithm to generate a Web tutor topic of K+1 levels, and the experimental results are presented.

SuperCNN: A Superpixelwise Convolutional Neural Network for Salient Object Detection

Existing computational models for salient object detection primarily rely on hand-crafted features, which are only able to capture low-level contrast information. In this paper, we learn the hierarchical contrast features by formulating salient object detection as a binary labeling problem using deep learning techniques. A novel superpixelwise convolutional neural network approach, called SuperCNN, is proposed to learn the internal representations of saliency in an efficient manner. In contrast to the classical convolutional networks, SuperCNN has four main properties. First, the proposed method is able to learn the hierarchical contrast features, as it is fed by two meaningful superpixel sequences, which is much more effective for detecting salient regions than feeding raw image pixels. Second, as SuperCNN recovers the contextual information among superpixels, it enables large context to be involved in the analysis efficiently. Third, benefiting from the superpixelwise mechanism, the required number of predictions for a densely labeled map is hugely reduced. Fourth, saliency can be detected independent of region size by utilizing a multiscale network structure. Experiments show that SuperCNN can robustly detect salient objects and outperforms the state-of-the-art methods on three benchmark datasets.