Real time markerless motion tracking using linked kinematic chains
| DWPI Title: Subject e.g. human, motion tracking method for use in three-dimensional workspace, involves providing video imaging system which includes video cameras simultaneously viewing subject, and aligning model to volumetric data set |
| Abstract: A markerless method is described for tracking the motion of subjects in a three dimensional environment using a model based on linked kinematic chains. The invention is suitable for tracking robotic, animal or human subjects in real-time using a single computer with inexpensive video equipment, and does not require the use of markers or specialized clothing. A simple model of rigid linked segments is constructed of the subject and tracked using three dimensional volumetric data collected by a multiple camera video imaging system. A physics based method is then used to compute forces to align the model with subsequent volumetric data sets in real-time. The method is able to handle occlusion of segments and accommodates joint limits, velocity constraints, and collision constraints and provides for error recovery. The method further provides for elimination of singularities in Jacobian based calculations, which has been problematic in alternative methods. |
| Use: Used for tracking a motion of a subject e.g. human, robot, laboratory animal, construction crane and mechanical arm, in a three-dimensional (3D) workspace by using a video imaging system, and in an application such as surveillance situation such as access control, parking lot monitoring, automatic teller machine (ATM) monitoring, or monitoring of publicly displayed valuables, motion analysis useful in medical and biomechanical application for analysis of both injuries and the rehabilitation of injuries and in sport application, virtual reality and video game, teleconferencing and human robot interaction. |
| Advantage: The method enables to track the subject in real-time using a single computer with inexpensive video equipment, and does not require the use of markers or specialized clothing. The method enables to remove singularities in Jacobian based calculations of forces acting on the model. The method provides a novel iterative optimization scheme to pull the model from alignment with a previous data set into alignment with a current data set, such that an adjustment between the data sets is very small, thus allowing the method to work effectively and reliably. |
| Novelty: The method involves providing a video imaging system which includes video cameras simultaneously viewing a subject e.g. human, in a workspace. A model template is provided for the subject. A volumetric data set is acquired from the system. Rigid segments of the template are dimensioned by fitting the segments to the data set. Another data set is acquired from the system. A model is aligned to the latter data set, where aligning includes calculating in three dimensions a set of forces acting on the model and applying the forces to the model, where the forces cause displacement of the model. |
| Filed: 3/4/2004 |
| Application Number: US2004794331A |
| Tech ID: SD 6998.1 |
| This invention was made with Government support under Contract No. DE-NA0003525 awarded by the United States Department of Energy/National Nuclear Security Administration. The Government has certain rights in the invention. |
| Data from Derwent World Patents Index, provided by Clarivate All rights reserved. Republication or redistribution of Clarivate content, including by framing or similar means, is prohibited without the prior written consent of Clarivate. Clarivate and its logo, as well as all other trademarks used herein are trademarks of their respective owners and used under license. |