A new network-based algorithm for human activity recognition in video

TL;DR

This paper introduces a novel network-based algorithm for human activity recognition in videos, modeling scenes as networks and activities as package transmissions, which effectively detects various human activities.

Contribution

The paper presents a new network-transmission-based algorithm that models scene patches as network nodes and activities as package transmissions for activity recognition.

Findings

Effective detection of various activities

Successful implementation in abnormal activity detection

Demonstrated robustness in experimental results

Abstract

In this paper, a new network-transmission-based (NTB) algorithm is proposed for human activity recognition in videos. The proposed NTB algorithm models the entire scene as an error-free network. In this network, each node corresponds to a patch of the scene and each edge represents the activity correlation between the corresponding patches. Based on this network, we further model people in the scene as packages while human activities can be modeled as the process of package transmission in the network. By analyzing these specific "package transmission" processes, various activities can be effectively detected. The implementation of our NTB algorithm into abnormal activity detection and group activity recognition are described in detail in the paper. Experimental results demonstrate the effectiveness of our proposed algorithm.