Ali Boyali

Real-time controller design for a parallel hybrid electric vehicle using neuro-dynamic programming method

The use of the neuro-dynamic programming method for real-time control of a parallel hybrid electric vehicle is addressed in this study. The validated model of a research prototype parallel hybrid electric light commercial vehicle, FOHEV I, is used in the numerical parts of this paper. A diesel engine and an electric motor power the front and rear axles, respectively. Due to the computational complexity and resulting burden for optimum power distribution in the hybrid electric powertrain, real-time computation using dynamic programming is not feasible. Sub-optimal optimization techniques are available for pre-defined speed profiles, however, the vehicle speed profile depends on the driver input and vehicle and road conditions and is not known a priori. A neuro-dynamic programming method is proposed here to solve this problem. The results are compared with and found to be quite close to the optimal ones computed using dynamic programming.

Spectral Collaborative Representation based Classification for hand gestures recognition on electromyography signals

In this study, we introduce a novel variant and application of the Collaborative Representation based Classification in spectral domain for recognition of the hand gestures using the raw surface Electromyography signals. The intuitive use of spectral features are explained via circulant matrices. The proposed Spectral Collaborative Representation based Classification (SCRC) is able to recognize gestures with higher levels of accuracy for a fairly rich gesture set. The worst recognition result which is the best in the literature is obtained as 97.3\% among the four sets of the experiments for each hand gestures. The recognition results are reported with a substantial number of experiments and labeling computation.

3D and 6 DOF user input platform for computer vision applications and virtual reality

In this study we describe the development of a six Degree of Freedom (6 DOF) pose estimation model of a tracked object and 3D user interface using stereo vision and Infra-Red (IR) cameras in the Matlab/Simulink and C# environments. The raw coordinate values of the IR light sources located on the tracked object are detected, digitized and Bluetooth broadcast by IR cameras and associated circuitry within Nintendo Wiimotes. Then, the signals are received by a PC and processed using pose extraction and stereo vision algorithms. The extracted motion and position parameters are used to manipulate a virtual object in the virtual reality toolbox of Matlab for 6-DOF motion tracking. We setup a stereo camera system with Wiimotes to increase the vision volume and accuracy of 3D coordinate estimation and present a 3D user input device implementation in C# with Matlab functions. The camera calibration toolbox is used for calibration of the stereo system and computation of the extrinsic and intrinsic camera parameters. We use the epipolar geometry toolbox for computation of epipolar constraints to estimate the location of the points which are not seen by both of the cameras simultaneously. Our preliminary results for stereo vision analysis indicate that the precision for pose estimation may reach to millimeter or sub-millimeter accuracy.

Real Time Six Degree of Freedom Pose Estimation Using Infrared Light Sources and Wiimote IR Camera with 3D TV Demonstration

The goal of this paper is to present the development of a tracking technology to interact with a virtual object. This paper presents the general procedures of building a simple, low cost tracking system by using Wiimote (a remote of Nintendo game console) and the Open source Computer Vision (OpenCV) software library as well as interfacing the tracking system with an immersive virtual environment (Vizard). We used an iterative position and orientation estimation (POSIT algorithm) which is optimized as an OpenCV function for extracting position parameters. We filter out the noise in the coordinate values using Kalman filters. The orientation and translation of the tracked system are then used to manipulate a virtual object created in the virtual world of Vizard. Our results indicate that it is possible to implement an inexpensive and efficient application for interacting with virtual worlds using a Wiimote and appropriate digital filters.

De-SIGN: Robust Gesture Recognition in Conceptual Design, Sensor Analysis and Synthesis

Designing in Virtual Reality systems may bring significant advantages for the preliminary exploration of the design concept in 3D. In this chapter, our purpose is to provide a design platform in VR, integrating data gloves and the sensor jacket that consists of piezo-resistive sensor threads in a sensor network. Unlike the common gesture recognition approaches, that require the assistance of expensive devices such as cameras or Precision Position Tracker (PPT) devices, our sensor network eliminates both the need for additional devices and the limitation of mobility. We developed a Gesture Recognition System (De-SIGN) in various iterations. De-SIGN decodes design gestures. In this chapter, we present the system architecture for De-SIGN, its sensor analysis and synthesis method (SenSe) and the Sparse Representation-based Classification (SRC) algorithm we have developed for gesture signals, and discussed the system’s performance providing the recognition rates. The gesture recognition algorithm presented here is highly accurate regardless of the signal acquisition method used and gives excellent results even for high dimensional signals and large gesture dictionaries. Our findings state that gestures can be recognized with over 99% accuracy rate using the Sparse Representation-based Classification (SRC) algorithm for user-independent gesture dictionaries and 100% for user-dependent.

MATRACK: block sparse Bayesian learning for a sketch recognition approach

Human-computer interaction has become increasingly easy and popular using widespread smart devices. Gestures and sketches as the trajectory of hands in 3D space are among the popular interaction media. Therefore, their recognition is essential. However, diversity of human gestures along with the lack of visual cues make the sketch recognition process challenging. This paper aims to develop an accurate sketch recognition algorithm using Block Sparse Bayesian Learning (BSBL). Sketches are acquired from three datasets using a Wii-mote in a virtual-reality environment. We evaluate the performance of the proposed sketch recognition approach (MATRACK) on diverse sketch datasets. Comparisons are drawn with three high accuracy classifiers namely, Hidden Markov Model (HMM), Principle Component Analysis (PCA) and K-Nearest Neighbour (K-NN). MATRACK, the developed BSBL based sketch recognition system, outperforms k-NN, HMM and PCA. Specifically, for the most diverse dataset, MATRACK reaches the accuracy of 93.5%, where other three classifiers approximately catches 80% accuracy.