Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks

Abstract In the realm of daily human interactions, a rich tapestry of behaviors and actions is observed, encompassing a wealth of informative cues. In the era of burgeoning big data, extensive repositories of images and videos have risen to prominence as the primary conduits for disseminating inform...

Full description

Saved in:
Bibliographic Details
Main Authors: Fenglin Liu, Chenyu Wang, Zhiqiang Tian, Shaoyi Du, Wei Zeng
Format: Article
Language:English
Published: Springer 2024-12-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-024-01743-2
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1832571182750105600
author Fenglin Liu
Chenyu Wang
Zhiqiang Tian
Shaoyi Du
Wei Zeng
author_facet Fenglin Liu
Chenyu Wang
Zhiqiang Tian
Shaoyi Du
Wei Zeng
author_sort Fenglin Liu
collection DOAJ
description Abstract In the realm of daily human interactions, a rich tapestry of behaviors and actions is observed, encompassing a wealth of informative cues. In the era of burgeoning big data, extensive repositories of images and videos have risen to prominence as the primary conduits for disseminating information. Grasping the intricacies of human behaviors depicted within these multimedia contexts has evolved into a pivotal quandary within the domain of computer vision. The technology of behavior recognition finds its practical application across domains such as human-computer interaction, intelligent surveillance, and anomaly detection, exhibiting a robust blend of pragmatic utility and scholarly significance. The present study introduces an innovative human body behavior recognition framework anchored in skeleton sequences and multi-stream fused spatiotemporal graph convolutional networks. Developed upon the foundation of graph convolutional networks, this method encompasses three pivotal refinements tailored to ameliorate extant challenges. First and foremost, in response to the complex task of capturing distant interdependencies among nodes within graph convolutional networks, we incorporate a spatial attention module. This module adeptly encapsulates long-term node interdependencies via precision-laden positional information, thus engendering interconnections that span diverse temporal and spatial contexts. Subsequently, to elevate the discernment of channel information within the network and to optimize the allocation of attention across distinct channels, we introduce a channel attention mechanism. This augmentation fortifies the discernment of motion-related features. Lastly, confronting the lacuna of information gaps prevalent within single-stream data, we deploy a multi-stream fusion methodology to fortify model outputs, ultimately fostering more precise prognostications concerning action classifications. Empirical results bear testament to the efficacy of the proposed multi-stream fused spatiotemporal graph convolutional network paradigm for skeleton-centric behavior recognition, evincing a pinnacle recognition accuracy of 96.0% on the expansive NTU-RGB+D skeleton dataset, alongside a zenithal accuracy of 37.3% on the Kinetics-Skeleton dataset—emanating from RGB data and furthered through pose estimation.
format Article
id doaj-art-91cc9da8c3af413b908f2ebfe8cd11d3
institution Kabale University
issn 2199-4536
2198-6053
language English
publishDate 2024-12-01
publisher Springer
record_format Article
series Complex & Intelligent Systems
spelling doaj-art-91cc9da8c3af413b908f2ebfe8cd11d32025-02-02T12:48:58ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-12-0111112110.1007/s40747-024-01743-2Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networksFenglin Liu0Chenyu Wang1Zhiqiang Tian2Shaoyi Du3Wei Zeng4School of Physics and Mechanical and Electrical Engineering, Longyan UniversitySchool of Software Engineering, Xi’an Jiaotong UniversitySchool of Software Engineering, Xi’an Jiaotong UniversityInstitute of Artificial Intelligence and Robotics, Xi’an Jiaotong UniversitySchool of Physics and Mechanical and Electrical Engineering, Longyan UniversityAbstract In the realm of daily human interactions, a rich tapestry of behaviors and actions is observed, encompassing a wealth of informative cues. In the era of burgeoning big data, extensive repositories of images and videos have risen to prominence as the primary conduits for disseminating information. Grasping the intricacies of human behaviors depicted within these multimedia contexts has evolved into a pivotal quandary within the domain of computer vision. The technology of behavior recognition finds its practical application across domains such as human-computer interaction, intelligent surveillance, and anomaly detection, exhibiting a robust blend of pragmatic utility and scholarly significance. The present study introduces an innovative human body behavior recognition framework anchored in skeleton sequences and multi-stream fused spatiotemporal graph convolutional networks. Developed upon the foundation of graph convolutional networks, this method encompasses three pivotal refinements tailored to ameliorate extant challenges. First and foremost, in response to the complex task of capturing distant interdependencies among nodes within graph convolutional networks, we incorporate a spatial attention module. This module adeptly encapsulates long-term node interdependencies via precision-laden positional information, thus engendering interconnections that span diverse temporal and spatial contexts. Subsequently, to elevate the discernment of channel information within the network and to optimize the allocation of attention across distinct channels, we introduce a channel attention mechanism. This augmentation fortifies the discernment of motion-related features. Lastly, confronting the lacuna of information gaps prevalent within single-stream data, we deploy a multi-stream fusion methodology to fortify model outputs, ultimately fostering more precise prognostications concerning action classifications. Empirical results bear testament to the efficacy of the proposed multi-stream fused spatiotemporal graph convolutional network paradigm for skeleton-centric behavior recognition, evincing a pinnacle recognition accuracy of 96.0% on the expansive NTU-RGB+D skeleton dataset, alongside a zenithal accuracy of 37.3% on the Kinetics-Skeleton dataset—emanating from RGB data and furthered through pose estimation.https://doi.org/10.1007/s40747-024-01743-2Behavior recognitionSkeleton-based spatiotemporal graph convolutional networkMulti-stream fusionLong-range dependencies
spellingShingle Fenglin Liu
Chenyu Wang
Zhiqiang Tian
Shaoyi Du
Wei Zeng
Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
Complex & Intelligent Systems
Behavior recognition
Skeleton-based spatiotemporal graph convolutional network
Multi-stream fusion
Long-range dependencies
title Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
title_full Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
title_fullStr Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
title_full_unstemmed Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
title_short Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks
title_sort advancing skeleton based human behavior recognition multi stream fusion spatiotemporal graph convolutional networks
topic Behavior recognition
Skeleton-based spatiotemporal graph convolutional network
Multi-stream fusion
Long-range dependencies
url https://doi.org/10.1007/s40747-024-01743-2
work_keys_str_mv AT fenglinliu advancingskeletonbasedhumanbehaviorrecognitionmultistreamfusionspatiotemporalgraphconvolutionalnetworks
AT chenyuwang advancingskeletonbasedhumanbehaviorrecognitionmultistreamfusionspatiotemporalgraphconvolutionalnetworks
AT zhiqiangtian advancingskeletonbasedhumanbehaviorrecognitionmultistreamfusionspatiotemporalgraphconvolutionalnetworks
AT shaoyidu advancingskeletonbasedhumanbehaviorrecognitionmultistreamfusionspatiotemporalgraphconvolutionalnetworks
AT weizeng advancingskeletonbasedhumanbehaviorrecognitionmultistreamfusionspatiotemporalgraphconvolutionalnetworks