Due to the rise of new applications in electronic appliances and pervasive devices, automated hand gesture recognition (HGR) has become an area of increasing interest. HGR developments have come a long way from the traditional sign language recognition (SLR) systems to depth and wearable sensor-based electronic devices. Where the former are more laboratory-oriented frameworks, the latter are comparatively realistic and practical systems. Based on various gestural traits, such as hand postures, gesture recognition takes different forms. Consequently, different interpretations can be associated with gestures in various application contexts. A considerable amount of research is still needed to introduce more practical gesture recognition systems and associated algorithms. Challenges and Applications for Hand Gesture Recognition highlights the state-of-the-art practices of HGR research and discusses key areas such as challenges, opportunities, and future directions. Covering a range of topics such as wearable sensors and hand kinematics, this critical reference source is ideal for researchers, academicians, scholars, industry professionals, engineers, instructors, and students.

Current motion tracking technologies fail to provide accurate wide area tracking of multiple users without interference and occlusion problems. This research proposes to overcome current limitations using nine-axis magnetic/ angular/rate/gravity (MARG) sensors combined with a quaternion-based complementary filter algorithm capable of continuously correcting for drift and following angular motion through all orientations without singularities. Primarily, this research involves the development of a prototype tracking system to demonstrate the feasibility of MARG sensor body motion tracking Mathematical analysis and computer simulation are used to validate the correctness of the complementary filter algorithm The implemented human body model utilizes the world-coordinate reference frame orientation data provided in quaternion form by the complementary filter and orients each limb segment independently. Calibration of the model and the inertial sensors is accomplished using simple but effective algorithms. Physical experiments demonstrate the utility of the proposed system by tracking of human limbs in real-time using multiple MARG sensors. The system is "sourceless" and does not suffer from range restrictions and interference problems. This new technology overcomes the limitations of motion tracking technologies currently in use. It has the potential to provide wide area tracking of multiple users in virtual environment and augmented reality applications.

This thesis describes the design and implementation of a wireless 6 degree-of-freedom inertial sensor system to be used for multiple-user, real-time gesture recognition and coordinated activity detection. Analysis is presented that shows that the data streams captured can be readily processed to detect gestures and coordinated activity. Finally, some pertinent research that can be pursued with these nodes in the areas of biomotion analysis and interactive entertainment are introduced.

Human action or gesture recognition has been extensively studied in the literature spanning a wide variety of human-computer interaction applications including gaming, surveillance, healthcare monitoring, and assistive living. Sensors used for action or gesture recognition are primarily either vision-based sensors or inertial sensors. Compared to the great majority of previous works where a single modality sensor is used for action or gesture recognition, the simultaneous utilization of a depth camera and a wearable inertial sensor is considered in this dissertation. Furthermore, compared to the great majority of previous works in which actions are assumed to be segmented actions, this dissertation addresses a more realistic and practical scenario in which actions of interest occur continuously and randomly amongst arbitrary actions of non-interest. In this dissertation, computationally efficient solutions are presented to recognize actions of interest from continuous data streams captured simultaneously by a depth camera and a wearable inertial sensor. These solutions comprise three main steps of segmentation, detection, and classification. In the segmentation step, all motion segments are extracted from continuous action streams. In the detection step, the segmented actions are separated into actions of interest and actions of non- interest. In the classification step, the detected actions of interest are classified. The features considered include skeleton joint positions, depth motion maps, and statistical attributes of acceleration and angular velocity inertial signals. The classifiers considered include maximum entropy Markov model, support vector data description, collaborative representation classifier, convolutional neural network, and long short-term memory network. These solutions are applied to the two applications of smart TV hand gestures and transition movements for home healthcare monitoring. The results obtained indicate the effectiveness of the developed solutions in detecting and recognizing actions of interest in continuous data streams. It is shown that higher recognition rates are achieved when fusing the decisions from the two sensing modalities as compared to when each sensing modality is used individually. The results also indicate that the deep learning-based solution provides the best outcome among the solutions developed.