Papers by Keyword: Human-Computer Interaction

Abstract: An interactive visualization of the patients’ 3D medical anatomical model as guide is often helpful for doctors during complex surgery. However, there are certain limitations according to the actual requirements of building sterile operating environment. Traditional human–computer interaction tools (mouse and keyboard) must be disinfected regularly and cannot be used in the process. A noncontact gesture control medical model based on Leap Motion is proposed in this study. The gesture is recognized and localized without using mouse and keyboards through a binocular camera assembled on Leap Motion. Hence, the model is directly controlled by the gesture to complete the operation of rotation, zoom, and other functions. In this study, a 3D heart model is combined with pseudo-color processing technology to enhance the observability of its 3D structure. Gesture recognition technology is then utilized to control the rendered model as rotation and zoom. Experimental results show that our system has an absolute accuracy in recognizing circle, swipe, and other actions. Thus, rotation is proposed as a new motion that can be identified steadily. Rotation plays an essential role in usability, intuition, and interactive efficiency of future system design. The system is applicable to sterile operating environments due to its stable recognition process and small space occupation.

Abstract: Open and closed states of eyes play an important role in human-computer interaction. They can be used as communication method for people with severe disabilities providing an alternate input modality to control a computer or as detection method for a driver's drowsiness. This paper introduces a study on two eye components (i.e., iris and sclera) for robust open or closed eye classification. Evidently, the area of iris or sclera increases while a person opens an eye and decreases while an eye is closing. In particular, the distributions of these eye components, during each eye state, form a bell-like shape. Consequently, an eye state classification can be effectively achieved by Bayes classifier. Finally, the performance comparison of the proposed features against the ground truth is discussed.

Abstract: This paper describes a method for autonomous virtual hand behavior construction in virtual manufacturing environment. The new mechanism is aimed to reduce user’s cognitive and manipulation loads. Based on a realistic and accurate virtual hand model; a strategy and an algorithm for behavior simulation, as well as continuous operation simulation; an intelligent and efficient virtual hand is generated. The experimental results demonstrate the ability of the method, to create an autonomous and reliable virtual hand in virtual manufacturing environment.

Abstract: The temperature and magnetic field data acquisition system is developed for HTS Magnet of ITER. According to its working environment, the type of probes used for detection and the corresponding supporting equipment are chosen. Based on the requirements of data acquisition precision, the selection of the data acquisition instruments is completed. Optimize the number and configuration of probes and keep key monitoring on its Conduction-cooled structure. A complete set of complete data collection and human-computer interaction system is designed by using LabVIEW.

Abstract: In order to improve the speed of collision detection between objects in the large-scale and complex scene, this paper proposed an improved collision detection algorithm based on GPU, In this method, we first divided the virtual space into several grids to rule out the impossible intersecting objects rapidly using the GPU acceleration technology; secondly, we adopted parallel technology to build K - DOP bounding boxes for the objects in the same grids and then detected whether the K - DOP bounding boxes intervene or collide to conform the potential colliding primitive pairs; Finally we traveled the final triangle intersection tests on GPU. Compared to the traditional K-DOP compared bounding box collision detection, The algorithm can effectively improve the real-time collision detection.

Abstract: According to problems of deficiency guidance in the traditional virtual disassembly training, the planning method of disassembly operation process based on Petri-net is presented. By this method, Disassembly Petri-Net (DPN) model process-oriented is built. In this model, constraint relations for the process and generation rule for DPN are studied. At last, by taking the transmission of bulldozer as example, planning method and its solution aimed at timeliness are proposed. The example shows that the planning results can improve training effect significantly, which provides a practical and efficient training platform for trainees.

Abstract: Current mechanical kinematic animation can’t satisfy the requirements of Virtual Environment (VE) based design. The kinematic animation design in VE development platform does not have high level models and mechanisms, the interactive animation designs and developments are very difficult and time consuming. For these reasons, this paper proposes an innovative method for interactive kinematic animation design and development in VE, including dynamic runtime model and execution algorithm for interactive animation. A complex mechanical kinematic mechanism, that is, the engine assembly, is built to validate the animation technology introduced in this paper.

Abstract: The technologies of Web-based teleoperation and somatosensory Human-Computer Interaction have become a hot technology in recent years. Combining with these two technologies, this paper is based on the web server, using Kinect as the front-end of the robot teleoperation human-computer interaction equipment to acquire human-interactive data. Data transfer by using the WebSocket based on HTML 5 and establish the model by using WebGL to realize the remote teleoperation of robot. After the test of the function and performance of the system, indicating the practicality of the system.

Abstract: The virtual reality technology is used in the mine training simulation areas, which can overcome the limitations of traditional training methods effectively. It can also improve the quality of mine training simulation greatly, reduce training costs, and the users can achieve safe and convenient training. In this paper, a dynamic collision detection algorithm is proposed based on the prediction of the movement direction of a virtual hand, and it is the effective collision detection algorithm using data glove in the mine training simulation system. Compared with the traditional static collision detection algorithm in the performance, the dynamic algorithm is proposed to solve the collision detection between one simulation solid model and another one, and to achieve the function that a virtual hand grip and rotate virtual objects in the virtual environment. The dynamic collision detection algorithm can be extended to other simulation systems.