Key technologies of human–computer interaction for immersive somatosensory interactive games using VR technology

Abstract

Virtual reality (VR) is a computer-simulated three-dimensional environment whose goal is to achieve a strong sense of being there, called immersion. This requires a variety of technologies: the most essential being input devices. At present, the non-contact Kinect somatosensory interaction approach has been widely studied. Somatosensory interactive games take body movements as input instructions, instead of the simple push-button operation mode. Hence, the operational behavior is more intuitive and the reaction of players is highly accurate and brings a better game experience to players. In terms of man–machine interaction in somatosensory interactive games, gesture interaction brings the primary operation medium into the virtual environment. This paper analyzes the problems of somatosensory games interaction in immersive virtual reality, focusing on gesture-based immersive virtual reality technology. The main work includes: First, aiming at the problem that the gesture recognition method cannot adapt to the real-time continuous gesture flow in practical application scenarios, a naive Bayes gesture recognition algorithm based on joint vector is proposed. The algorithm uses a decision support system for feature representation of bone and motion along with the joint vector. It introduces the adaptive naive Bayes algorithm, which can complete the training with fewer samples. Experimental results show that the algorithm has a high recognition rate and recognition speed, can effectively adapt to continuous data flow, has good compatibility with virtual reality applications, and significantly increases the user's sense of immersion in virtual scenes. Secondly, in view of the lack of complete visual feedback solutions for gesture interaction, a 3D user interface and interaction method combining bone animation and collision detection technology is proposed. The process interacts with the virtual environment through gesture feedback from 3DUI elements. Experimental results show that the design can effectively enhance the immersive experience through the visual feedback of gestures.