Extended-range hybrid tracker and applications to motion and camera tracking in manufacturing systems

Abstract

Extended-or long-range tracking effectiveness is crucial for the automation of manufacturing systems. In this paper, we conceptualize and develop a prototype long-range hybrid tracker based on a combination of a laser tracker and a magnetic tracker and apply the concept to the following two applications: 1) extended-range human motion tracking on factory floors and 2) factory floor object reconstruction from camera images. The easily portable system not only utilizes the strengths of a laser tracker in tracking mobile objects over long ranges in large environments, such as a manufacturing shop floor and the strength of a magnetic tracker to compensate for violation of line-of-sight constraint, but it also reduces the overall cost by reducing the number of expensive beacons required by the laser tracker. The hybrid tracker assists in the development of two concepts: 1) real-time synchronization of human head and hand motion in a manufacturing environment with those of an avatar in a virtual manufacturing environment and 2) a mathematically simpler and practical camera self-calibration technique for the creation of three-dimensional objects in a virtual environment from camera images.

A magnetic field based technique for 3D position tracking

“…Based on the investigation of the tracking techniques and with the emphasis on developing a simple and low cost system, the magnetic sensing method was identified as a suitable and viable option for further analysis [6]. The following sections detail the proposed technique, its implementation, the results of the scaled-down prototype and its feasibility for tracking garments.…”

Fusion of the Magnetic and Optical Information for Motion Capturing

“…Optical trackers are very fast and accurate and are also immune to magnetic interference, but their use is restricted by the line-of-sight constraint. 11 In this paper, we will focus on the problem of combining magnetic and optical MoCap system. In order to solve this problem, we propose a sensor fusion technique for motion capture system.…”

“…Even though the laser trackers are violated during 26 msec, the system switches to the alternative Kalman filter, and regular Kalman filter system is resumed with the predicted error covariance given by the backup filter. 11 But, instead of estimating or predicting the motion from the motion model, the SI based techniques basically selects appropriate model from given multiple sources in our approaches. For the case of OMCS and MMCS, SI easily combines accurate aspects of two different signals while prediction based tracking need to make additional combination of motion models from those signals which could induce additional complexity and errors.…”

Intelligent health care — A Motion Analysis system for health practitioners

“…Various parameters can be assessed using motion of moving object for performance, efficiency and deterioration in the case of machines. Study conducted by Zetu et al [34] provides details about time and motion analysis to improve the process performance and adds efficiency by optimizing the actions of process workers. In the case of similar research by Balteanu [2], it is conducted for training factory workers to apply safe work practices while handling heavy loads.…”