Dynamic Probabilistic Network Based Human Action Recognition

TL;DR

This paper explores the use of dynamic probabilistic networks to recognize human actions by modeling the dynamic relationships between different body regions and their time series events, achieving indoor accuracy but lower outdoor performance.

Contribution

It introduces a DPN-based model for indoor human activity recognition that considers dynamic interrelations between body regions and their events.

Findings

Indoor recognition accuracy is high under controlled lighting.

Outdoor recognition accuracy decreases with variable lighting.

Dynamic interrelations improve activity classification.

Abstract

This paper examines use of dynamic probabilistic networks (DPN) for human action recognition. The actions of lifting objects and walking in the room, sitting in the room and neutral standing pose were used for testing the classification. The research used the dynamic interrelation between various different regions of interest (ROI) on the human body (face, body, arms, legs) and the time series based events related to the these ROIs. This dynamic links are then used to recognize the human behavioral aspects in the scene. First a model is developed to identify the human activities in an indoor scene and this model is dependent on the key features and interlinks between the various dynamic events using DPNs. The sub ROI are classified with DPN to associate the combined interlink with a specific human activity. The recognition accuracy performance between indoor (controlled lighting conditions) is compared with the outdoor lighting conditions. The accuracy in outdoor scenes was lower than the controlled environment.