Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Learning and Matching of Dynamic & Robust Visual Tracking Recognition


Affiliations
1 P V P Siddhartha Engineering College, India
     

   Subscribe/Renew Journal


We learn explicit representations for dynamic shape manifolds of moving humans for the task of action recognition. We exploit locality preserving projections (LPP) for dimensionality reduction, leading to a low-dimensional embedding of human movements. Given a sequence of moving silhouettes associated to an action video, by LPP, we project them into a low-dimensional space to characterize the spatiotemporal property of the action, as well as to preserve much of the geometric structure. Action classification is then achieved in a nearest neighbor framework. The proposed method, extensive experiments have been carried out on a recent dataset including ten actions performed by nine different subjects. The experimental results show that the proposed method is able to not only recognize human actions effectively, but also considerably tolerate some challenging conditions, e.g. partial occlusion, low-quality videos, changes in viewpoints, scales, and clothes; within-class variations caused by different subjects with different physical build; styles of motion; etc.

Keywords

Action Recognition, Dimensionality Reduction, Human Motion Analysis, Locality Preserving Projections (LPP).
User
Subscription Login to verify subscription
Notifications
Font Size

Abstract Views: 246

PDF Views: 1




  • Learning and Matching of Dynamic & Robust Visual Tracking Recognition

Abstract Views: 246  |  PDF Views: 1

Authors

Ramesh Mande
P V P Siddhartha Engineering College, India
A. Sudhir Babu
P V P Siddhartha Engineering College, India

Abstract


We learn explicit representations for dynamic shape manifolds of moving humans for the task of action recognition. We exploit locality preserving projections (LPP) for dimensionality reduction, leading to a low-dimensional embedding of human movements. Given a sequence of moving silhouettes associated to an action video, by LPP, we project them into a low-dimensional space to characterize the spatiotemporal property of the action, as well as to preserve much of the geometric structure. Action classification is then achieved in a nearest neighbor framework. The proposed method, extensive experiments have been carried out on a recent dataset including ten actions performed by nine different subjects. The experimental results show that the proposed method is able to not only recognize human actions effectively, but also considerably tolerate some challenging conditions, e.g. partial occlusion, low-quality videos, changes in viewpoints, scales, and clothes; within-class variations caused by different subjects with different physical build; styles of motion; etc.

Keywords


Action Recognition, Dimensionality Reduction, Human Motion Analysis, Locality Preserving Projections (LPP).