Papers by Keyword: Motion Tracking

Abstract: This paper presents the design of an innovative system for the diagnosis and treatment of spine disorders, in particular, the scoliosis. The product consists in a mechatronic device that is able to measure in real time the instantaneous position of the human spine, facilitating a precise diagnosis as well as continuous monitoring for prevention and/or treatment of spine disorders.

Abstract: With the FPGA technology progressing, the speed, the internal multiplier and the internal RAM of the FPGA are increasing. Its internal resource can be allocated flexibility, and there is no limit on the pipeline stages, so it is more suitable for real-time video processing comparing with the previous DSP and PC. By this reason, the DE2 development system is selected as the real-time video processing platform, which has a core of the Cyclone II series FPGA, in which the calculation of LK-algorithm-based real-time optical flow is implemented. Finally, by the reasonable overall arrangement for the pipeline and the sub-pipeline, the system achieves the real-time video motion tracking for the 640×480 resolution 30 frames/s images.

Abstract: Optical flow is an important kind of video motion tracking algorithm, and Lucas-Kanade (LK) algorithm is an effective differential method in terms of calculating optical flow. The 3D Gaussian smoothing filter is properly introduced in the image preprocessing stage of the LK algorithm, which makes it possible to increase the correlation of the adjacent pixels in the time axis, improve the blur effect of the video image and overcome the 2D Gaussian filters disadvantage that is not suitable for the video image processing. More importantly, the optimized 3D non-Gaussian matching filter is chosen during the 3D derivative calculating, and it is capable of reducing the error rate of the velocity vector calculation and enhancing the calculation accuracy of the optical flow.

Abstract: The motive behind this research project is to devise a method for overcoming some of the challenges faced by fire fighters in Egypt while accomplishing their duties. This is achieved by utilizing robot vision technology as one of the approaches used for task automation. Based on a study of different methods of automation in human tracking and fire fighting applications, image processing techniques with the highest potential in a fire fighting environment were identified. A system has been developed which fusses the selected image processing algorithms with fuzzified readings from distance sensors, to extract the major blue areas in acquired images that is more likely to correspond to the uniform worn by fire fighters in Egypt. Subsequently the extracted blue area is used to identify a region of interest within the image in order to reduce the computations. The feature detection process constrains its search for a feature found on the back of the target fire fighter to the identified region of interest. Based on the location and area of this feature, the system will calculate the required velocity components to control the motion of the robot and the camera pan and tilt mechanism, in order to continue tracking the target along its path. The system has been validated by conducting an experiment which simulates the key influential factors in a fire fighting environment.

Abstract: This paper is mainly talking about processing, analysis and understanding of video signal in intelligent video surveillance, and we designed an efficient target detection and recognition model. Through the model to detect the target object in motion and then track the detected target. Eventually we achieved real-time monitoring of the unguarded areas. The focus of this article is about how to achieve the moving target tracking in OpenCV (Open Source Computer Vision Library) environment.

Abstract: In face lapping, the achievable material removal rate and surface quality depend strongly on the workpiece kinematics. Hence, the precise knowledge of the kinematics is an important requirement for increasing the efficiency and quality of the superfinishing process. The main focus of experiment is to identify how different workpiece geometries influence the resulting kinematics. The process kinematics in face lapping with friction drive is performed by means of motion tracking. Multi-body simulation allows extending the understanding of the process. Apart from the motion patterns of the lapping process, which were determined before, experimentally established reaction forces are used for verifying the considered rigid body model. A deviation of less than 10 % between the forces determined experimentally and by simulation verifies that it is a promising possibility to assess the kinematics by simulation.

Abstract: Motion tracking has shown promise as a powerful technique to improve interaction function in Virtual Reality (VR).Users can interact naturally with virtual environment by using body motion as the interface. This paper presents a design of a telescope-style interaction system combined with an inertial/magnetic motion tracking unit for users’ interacting with the virtual environment and a near-to-eye display system supplying visual virtual environment to users. Since the movement acceleration will cause the error of accelerometer measurement, users will feel uncomfortable and cannot interact well with the virtual environment because of pictures’ jitter. To enhance the user's immersion in the virtual environment, a Kalman filter is designed to ensure the accuracy of users’ motion information. Performance of the estimation’s precision is shown in the experiments and results.

Abstract: The recently emerged compressive sensing framework aims to acqure signals at reduced sample rates compared to the classical Shannon-Nyquist rate. This paper is concerned with the optimization problem of motion tracking driven by a sort of passive infrared sampling paradigm which springs from compressive sensing framework. In particular, a structured implementation with binary passive infrared sensor node is proposed to acquire the sparse presence state of human motion with resolution of some small cells. To calibrate the cells, a functional scalar quantizer is employed. Its optimization is used to adjust the design of sampling model to reduce the uncertainty of measurement noise. Simulation results show that the proposed optimization method benefits tracking accuracy to a certain degree.