Fangpo He

Fractal face representation and recognition

This paper presents a face representation and recognition scheme based on the theory of fractals. Each face image is represented by its fractal model which is a small collection of transformation parameters. The transformation is carried out once for known face images. For recognition, the input face image is transformed and its fractal model is then compared against the database of fractal models of known faces. Feedforward neural networks are utilised to implement the compression and recognition parts. Some experimental results are presented. The maximum compression ratio obtained for the successful recognition of known faces was observed to be 89:1 (for a compression threshold of 0.002).

Shape optimization of an autonomous underwater vehicle with a ducted propeller using computational fluid dynamics analysis

ABSTRACT Autonomous Underwater Vehicles (AUVs) provide a useful means of collecting detailed oceano-graphic information. The hull resistance of an AUV is an important factor in determining the power requirements and range of the vehicle. This paper describes a procedure using Computational Fluid Dynamics (CFD) for determining the hull resistance of an AUV under development, for a given propeller rotation speed and within a given range of AUV velocities. The CFD analysis results reveal the distribution of the hydrodynamic values (velocity, pressure, etc.) around the AUV hull and its ducted propeller. The paper then proceeds to present a methodology for optimizing the AUV profile in order to reduce the total resistance. This paper demonstrates that shape optimization of conceptual designs is possible using the commercial CFD package contained in Ansys™. The optimum design to minimize the drag force of the AUV was identified for a given object function and a set of constrained design parameters

Multi-mode vibration control of a flexible cantilever beam using adaptive resonant control

In this paper, an adaptive resonant controller is used to attenuate multi-mode vibrations in a flexible cantilever beam structure with varying loading conditions. This controller is particularly designed for structures that are exposed to previously unmodelled dynamics. On-line estimation of the structures natural frequencies is used to update the adaptive resonant controllers parameters. The estimation of the natural frequencies is achieved using a parallel set of second-order recursive least squares estimators, each of which is designed for a specific vibration mode of concern. To achieve the desired estimation accuracy for each mode frequency, a different sampling rate suitable for that mode is used for the corresponding estimator. Experiment results show that the proposed adaptive strategy can achieve better performance, as measured by attenuation level, over its fixed-parameter counterpart for a range of unmodelled dynamics.

Wavelet packet face representation and recognition

A human face representation and recognition system, based on the wavelet packet method and the best basis selection algorithm, is proposed. Through conducting a set of experiments on three groups of training sets, the optimal transform basis (called the face basis), the best filter, and the best decomposition level are identified for the face image class. A face image is represented in a compressed form by its wavelet packet coefficients. For recognition, the compressed input face image is then compared against a database of compressed images of the known faces. The recognition results are presented.

Efficient Path Re-planning for AUVs Operating in Spatiotemporal Currents

This paper presents an on-line dynamic path re-planning system for an autonomous underwater vehicle (AUV) to enable it to operate efficiently in a spatiotemporal, cluttered, and uncertain environment. The proposed strategy combines path re-planning with an evolutionary algorithm to adapt and regenerate the trajectory during the course of the mission using continuously updated current profiles from on-board sensors, such as a Horizontal Acoustic Doppler Velocity Logger. A quantum-behaved particle swarm optimization (QPSO) algorithm is used with a cost function which is based on the total time required to travel along the path segments accounting for the effect of space-time variable currents. The proposed path planner is designed to generate an optimal trajectory for an AUV navigating through a spatiotemporal ocean environment in the presence of irregularly shaped terrains as well as obstacles whose position coordinates are uncertain. Simulation results show that using the same on-board computation resources, the proposed path re-planning methodology with reuse of information gained from the previous planning history is able to obtain a more optimized trajectory than one relying on reactive path planning. Subsets of representative Monte Carlo simulations were run to analyse the performance of these dynamic planning systems. The results demonstrate the inherent robustness and superiority of the proposed planner based on path re-planning scheme when compared with the reactive path planning scheme.

Vibration Suppression of a Principal Parametric Resonance

In this paper, a control method that combines linear and nonlinear-velocity feedback control is proposed to suppress the principal parametric resonance in a flexible cantilever beam structure. Linear-velocity feedback is employed for bifurcation control, and cubic-velocity feedback is employed to suppress high-amplitude vibration. A unified bifurcation parameter 2 that includes both the excitation frequency and amplitude is defined for the stability analysis, so that bifurcations under quasi-stationary frequency-response and quasi-stationary force-response can be treated uniformly when 2 is quasi-statically varied. This unified bifurcation parameter simplifies the system stability analysis as well as the controller design procedure. Numerical simulation and experimental results show that the combined bifurcation control and nonlinear feedback control strategy performs better than linear-velocity or cubic-velocity feedback control alone, and is less susceptible to actuator saturation.

Multiresolution eigenface-components

This paper presents a face recognition system that imitates the multiresolution processing technique employed by the human visual system. In the proposed system, a different degree of importance is assigned to each part of a face image, and each region of the face image is processed with a different resolution. This proposed system reduces the computational complexity of the eigenface method, and achieves higher compression ratios and higher recognition rates in comparison with the eigenface method. Experimental results are presented and discussed.

Commonsense knowledge-based face detection

A connectionist model is presented for commonsense knowledge representation and reasoning. The representation and reasoning ability of the model is described through examples. The commonsense knowledge base is employed to develop a human face detection system. The system consists of three stages: preprocessing, face-components extraction, and final decision-making. A neural network-based algorithm is utilised to extract face components. Five networks are trained to detect mouth, nose, eyes, and full face. The detected face components and their corresponding possibility degrees allow the knowledge base to locate faces in the image and generate a membership degree for the detected faces within the face class. The experimental results obtained using this method are presented.

Face image matching using fractal dimension

A new method is presented in this paper for calculating the correspondence between two face images on a pixel by pixel basis. The concept of fractal dimension is used to develop the proposed non-parametric area-based image matching method which achieves a higher proportion of matched pixels for face images than some well-known methods.

Path Planning for Rendezvous of Multiple AUVs Operating in a Variable Ocean

This paper presents a path planner for rendezvous of multiple autonomous underwater vehicles (AUVs) in turbulent, cluttered, and uncertain environments. The proposed strategy combines an Optimized Mass-center rendezvous point selection scheme with an evolutionary path planner to find trajectories for multiple AUVs with minimal time usage over all participating vehicles and simultaneous arrival of the vehicles at their selected rendezvous destination. A quantum-behaved particle swarm optimization (QPSO) algorithm is used with a cost function which is determined by the sum of time usage over all participating vehicles accounting for the effect of space-time variable currents and the sum of the waiting time of every vehicle. The proposed path planner is tested to generate optimal trajectories for rendezvous of multiple AUVs navigating through a variable ocean environment in the presence of irregularly shaped terrains as well as obstacles whose position coordinates are uncertain. Simulation results show that with integration of the Optimized Mass-center rendezvous point selection scheme, the proposed methodology is able to obtain more optimized trajectories for multiple AUVs than the ones relying on centroid, mass-center or optimized full-scale rendezvous point selection schemes.