A representation for human gesture recognition and beyond
- Resource Type
- Conference
- Authors
- Wan, Yiwen; Santiteerakul, Wasana; Cheng, Guangchun; Buckles, Bill; Parberry, Ian
- Source
- 2013 Fourth International Conference on Computing, Communications and Networking Technologies (ICCCNT) Computing, Communications and Networking Technologies (ICCCNT),2013 Fourth International Conference on. :1-6 Jul, 2013
- Subject
- Communication, Networking and Broadcast Technologies
Computing and Processing
Signal Processing and Analysis
Trajectory
Motion segmentation
Hidden Markov models
Cognition
Computer vision
Semantics
Markov processes
Gesture recognition
activity analysis
Markov logic network
cross-domain framework
- Language
A highly general and centralized reasoning framework which combines first-order-logic with Markov networks proposed to recognize both simple and complex activities. The generality and systematicity of the reasoning framework is characterized by a newly defined set of spatio-temporal and spatial semantic free low level event predicates(LLEs). With the new low level event predicates any human activity represented by trajectories can be described without domain knowledge thus can be applied across domains. High-level events (HLEs) of interest across different domains can be described by encoding the newly defined HLEs and temporal logic (Allen's interval logic) in a first-order-logic presentation. The main contribution is the proposed reasoning framework represented by a new set of semantics free LLEs which can be utilized across different domains. The human action Kinect dataset from Microsoft Research(MSR) is used to evaluate the proposed gesture representation and recognition framework. The capacity of performing across different domains is validated on both MSR dataset and one synthetic interation dataset.