A Robust Neural Network Approach for Determining 3D Gaze Position
نویسندگان
چکیده
This paper presents a neural-network based calibration method for measuring the 3D eye-gaze position in a stereoscopic display. The method is based on depth computation through local non-linear regression and interpolation using a parameterized self-organizing map (PSOM). A novel, efficient 3D calibration method for this application is introduced. We report an experiment in which we compare the performance of the neural-network based method with a simple geometric method. The results show that the PSOMbased method provides significantly better accuracy of measurement than the
منابع مشابه
A neural network for 3D gaze recording with binocular eye trackers
Using eye tracking for the investigation of visual attention has become increasingly popular during the last few decades. Nevertheless, only a small number of eye-tracking studies have employed three-dimensional displays, although such displays would closely resemble our natural visual environment. Besides higher cost and effort for the experimental setup, the main reason for the avoidance of t...
متن کاملA Reliability Approach on Redesigning the Warehouses in Supply Chain with Uncertain Parameters via Integrated Monte Carlo Simulation and Tuned Artificial Neural Network
In this paper, a reliability approach on reconfiguration decisions in a supply chain network is studied based on coupling the simulation concepts and artificial neural network. In other words, due to the limited budget for warehouse relocation in a supply chain, the failure probability is assessed for determining the robust decision for future supply chain configuration. Traditional solving ...
متن کاملRobust Fault Detection on Boiler-turbine Unit Actuators Using Dynamic Neural Networks
Due to the important role of the boiler-turbine units in industries and electricity generation, it is important to diagnose different types of faults in different parts of boiler-turbine system. Different parts of a boiler-turbine system like the sensor or actuator or plant can be affected by various types of faults. In this paper, the effects of the occurrence of faults on the actuators are in...
متن کاملAdaptive RBF network control for robot manipulators
TThe uncertainty estimation and compensation are challenging problems for the robust control of robot manipulators which are complex systems. This paper presents a novel decentralized model-free robust controller for electrically driven robot manipulators. As a novelty, the proposed controller employs a simple Gaussian Radial-Basis-Function Network as an uncertainty estimator. The proposed netw...
متن کاملHybrid Adaptive Neural Network AUV controller design with Sliding Mode Robust Term
This work addresses an autonomous underwater vehicle (AUV) for applying nonlinear control which is capable of disturbance rejection via intelligent estimation of uncertainties. Adaptive radial basis function neural network (RBF NN) controller is proposed to approximate unknown nonlinear dynamics. The problem of designing an adaptive RBF NN controller was augmented with sliding mode robust term ...
متن کامل