Extending 3D Lucas–Kanade tracking with adaptive templates for head pose estimation

The Lucas–Kanade tracker (LKT) is a commonly used method to track target objects over 2D images. The key principle behind the object tracking of an LKT is to warp the object appearance so as to minimize the difference between the warped object’s appearance and a pre-stored template. Accordingly, the 2D pose of the tracked object in terms of translation, rotation, and scaling can be recovered from the warping. To extend the LKT for 3D pose estimation, a model-based 3D LKT assumes a 3D geometric model for the target object in the 3D space and tries to infer the 3D object motion by minimizing the difference between the projected 2D image of the 3D object and the pre-stored 2D image template. In this paper, we propose an extended model-based 3D LKT for estimating 3D head poses by tracking human heads on video sequences. In contrast to the original model-based 3D LKT, which uses a template with each pixel represented by a single intensity value, the proposed model-based 3D LKT exploits an adaptive template with each template pixel modeled by a continuously updated Gaussian distribution during head tracking. This probabilistic template modeling improves the tracker’s ability to handle temporal fluctuation of pixels caused by continuous environmental changes such as varying illumination and dynamic backgrounds. Due to the new probabilistic template modeling, we reformulate the head pose estimation as a maximum likelihood estimation problem, rather than the original difference minimization procedure. Based on the new formulation, an algorithm to estimate the best head pose is derived. The experimental results show that the proposed extended model-based 3D LKT achieves higher accuracy and reliability than the conventional one does. Particularly, the proposed LKT is very effective in handling varying illumination, which cannot be well handled in the original LKT.     

Implementation of a robust complex extended Kalman filter with LabVIEW for detection in a distorted signal

This article proposes the PC-based LabVIEW as the software to develop the algorithm of the robust complex extended Kalman filter (RCEKF) to detect the parameters of the voltage signal in power systems. The hardware used is a sample-and-hold card and a data acquisition (DAQ) card to extract the data from an outside system to the PC, and the program will compute the amplitude, frequency, and phase of the voltage signal with RCEKF. To validate the performance of RCEKF, the voltage signal from a function generator was applied to check the feasibility of the algorithm. This application was also used in the Taiwan Power Company (TPC) secondary substation in Sijhou, Taiwan.     

Gaussian radial basis function neural network controller of a synchronous reluctance motor in electric motorcycle applications

In this article, a sliding mode control (SMC) design based on a Gaussian radial basis function neural network (GRBFNN) is proposed for the synchronous reluctance motor (SynRM) system in electrical motorcycle applications. The conventional SMC assumes that the upper lumped boundaries of parameter variations and external disturbances are known, and the sign function is used. This causes high-frequency chattering and the high-gain phenomenon. In order to avoid these drawbacks, the proposed method utilizes the Lyapunov stability method and the steep descent rule to guarantee the convergence asymptotically, and reduce the magnitude of the chattering or avoid it completely. Finally, numerical simulations are shown to illustrate the good performance of our controller design.     

A virtual subnet scheme on clustering algorithms for mobile ad hoc networks

Resolving the broadcast storm problem is an important issue in mobile ad hoc networks (MANETs). In this paper, we propose an approach for constructing a virtual subnet whose nodes are logically related. The virtual subnet can be spread upon clusters of a MANET. An intelligent agent with a routing filtering table is proposed to assist the best known clustering algorithms, the original Least ID algorithm and the original Highest Connection Cluster (HCC) algorithm, to improve group communication efficiency. Our simulation covers the network factors of hop count, deprave rate, and delay time. The simulation results show that when the proposed intelligent agent is used with the HCC algorithm, the delay time was reduced by 81.84% as compared with flooding, and by 49.25% as compared with the Ad Hoc On-Demand Distance Vector (AODV) routing algorithm. The delay time for the Least ID algorithm assisted by the proposed agents reduced by 81.84% compared to that of flooding and by 50% compared to that of AODV.     

Express Virtual Channels with Capacitively Driven Global Links

Networks on chip must deliver high bandwidth at low latencies while keeping within a tight power envelope. Using express virtual channels for flow control improves energy-delay throughput by letting packets bypass intermediate routers, but EVCs have key limitations. Nochi (NoC with hybrid interconnect) overcomes these limitations by transporting data payloads and control information on separate planes, optimized for bandwidth and latency respectively.     

Matrix games with interval data

The conventional game theory is concerned with how rational individuals make decisions when they are faced with known payoffs. In the real world, sometimes the payoffs are not known and have to be estimated, and sometimes the payoffs are only approximately known. This paper develops a solution method for the two-person zero-sum game where the payoffs are imprecise and are represented by interval data. Since the payoffs are imprecise, the value of the game should be imprecise as well. A pair of two-level mathematical programs is formulated to obtain the upper bound and lower bound of the value of the game. Based on the duality theorem and by applying a variable substitution technique, the pair of two-level mathematical programs is transformed to a pair of ordinary one-level linear programs. Solving the pair of linear programs produces the interval of the value of the game. It is shown that the two players in the game have the same upper bound and lower bound for the value of the imprecise game. An example illustrates the whole idea and sheds some light on imprecise game.     

A knowledge-based decision support system to analyze the debris-flow problems at Chen-Yu-Lan River, Taiwan

Decision-making for the debris-flow management involves multiple decision-makers often with concerning geomorphological and hydraulic conditions. Spatial decision support systems (SDSS) can be developed to improve our understanding of the relations among the natural and socio-economic variables to the occurrence/non-occurrence samples of debris-flow. Accordingly, the goal of this study is to development a debris-flow decision support system to manage and monitor the debris-flows in Nan-Tou County, Taiwan. The present study, more specifically, combines a spatial information system with an advanced Data Mining technique to investigate the debris-flow problem. In the first stage, our spatial information system integrates remote sensing, DEM, and aerial photos as three different resources to generate our spatial database. Each of the geomorphological and hydraulic attributes are obtained automatically through our spatial database. Then, a Data Mining classifier (hybrid model of decision tree (D.T.) + support vector machine (S.V.M.)) will be used to analyze and resolve the classification of occurrence of debris-flow. The contribution of this study has found that watershed area and NDVI (Normalized Difference Vegetation Index) are the crucial factors governing debris-flow by means of decision tree analysis. Further, the performance of prediction accuracy on testing samples through support vector machine is 73% which could be helpful for us to have better understanding of debris-flow problem.     

Effect of plasma chemistry on the simulation of helium atmospheric-pressure plasmas

The effect on the selection of different plasma chemistries for simulating a typical dielectric barrier discharge (DBD) driven by quasi-pulsed power source (20 kHz) is investigated. The numerical simulation was performed by using the one-dimensional self-consistent fluid modeling solver. Our simulation result indicates that the computed temporal current density can be significantly improved by using a complex version of plasma chemistry module rather than the simple one and demonstrates an excellent agreement with the experimental data. The result suggests the metastable, excited and ionic helium related reaction channels, which are important in simulating a DBD, should be taken into account. Furthermore, it also reveals that the power absorption of ions is considerably higher than that of the electron.     

A time-efficient pattern reduction algorithm for k-means clustering

This paper presents an efficient algorithm, called pattern reduction (PR), for reducing the computation time of k-means and k-means-based clustering algorithms. The proposed algorithm works by compressing and removing at each iteration patterns that are unlikely to change their membership thereafter. Not only is the proposed algorithm simple and easy to implement, but it can also be applied to many other iterative clustering algorithms such as kernel-based and population-based clustering algorithms. Our experiments—from 2 to 1000 dimensions and 150 to 10,000,000 patterns—indicate that with a small loss of quality, the proposed algorithm can significantly reduce the computation time of all state-of-the-art clustering algorithms evaluated in this paper, especially for large and high-dimensional data sets.     

A graph-theoretic model for optimizing queries involving methods

Traditional algorithms for optimizing the execution order of joins are no more valid when selections and projections involve methods and become very expensive operations. Selections and projections could be even more costly than joins such that they are pulled above joins, rather than pushed down in a query tree. In this paper, we take a fundamental look at how to approach query optimization from a top-down design perspective, rather than trying to force one model to fit into another. We present a graph model which is designed to characterize execution plans. Each edge and each vertex of the graph is assigned a weight to model execution plans. We also design algorithms that use these weights to optimize the execution order of operations. A cost model of these algorithms is developed. Experiments are conducted on the basis of this cost model. The results show that our algorithms are superior to similar work proposed in the literature. Received 20 April 1999 / Accepted 9 August 2000 Published online 20 April 2001