Abstract
A framework of imitating real human gait in 3D from monocular video of an uncalibrated camera directly and automatically is proposed. It firstly combines polygon‐approximation with deformable template‐matching, using knowledge of human anatomy to achieve the characteristics including static and dynamic parameters of real human gait. Then, these characteristics are processed in regularization and normalization. Finally, they are imposed on a 3D human motion model with prior constrains and universal gait knowledge to realize imitating human gait. In recognition based on this human gait imitation, firstly, the dimensionality of time‐sequences corresponding to motion curves is reduced by NPE. Then, we use the essential features acquired from human gait imitation as input and integrate HCRF with SVM as a whole classifier, realizing identification recognition on human gait. In associated experiment, this imitation framework is robust for the object’s clothes and backpacks to a certain extent. It does not need any manual assist and any camera model information. And it is fitting for straight indoors and the viewing angle for target is between 60° and 120°. In recognition testing, this kind of integrated classifier HCRF/SVM has comparatively higher recognition rate than the sole HCRF, SVM and typical baseline method.
Highlights
The investigation on human gait is receiving more and more attention
As an important branch of human gait study, human gait imitation does help to investigate deeply in real motion—it can acquire the valuable cue of sight characteristic that is hard to get from the raw images directly, making the results more clear. e.g., some characteristics on human body cannot be detected continually because of the sheltering or by themselves as human is motioning
This paper mainly proposes a framework of human gait imitation, analogous with human cognitive process, which integrates individual gait characteristics in reality with general prior knowledge of human motion to realize the reconstruction of human gait in 3D from monocular video of an uncalibrated camera directly and automatically
Summary
The investigation on human gait is receiving more and more attention. Especially, in monitoring, human gait is the only one characteristic that can be recognized in long distance without contacting. We can see that most motion imitations, whether using multicamera or using single camera, based on numerous continuous characteristics at the cost of expensive accurate instruments or accurate camera model information or manual assist or other extra demands. The method is robust for detecting subject’s clothes and backpack to a certain extent at 60◦ ∼120◦ angle of view in stable straight walking in test of CAISIA gait database It does not need any manual assist and any camera model information.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.