ACA-Net: adaptive context-aware network for basketball action recognition

The advancements in intelligent action recognition can be instrumental in developing autonomous robotic systems capable of analyzing complex human activities in real-time, contributing to the growing field of robotics that operates in dynamic environments. The precise recognition of basketball playe...

Full description

Saved in:
Bibliographic Details
Main Authors: Yaolei Zhang, Fei Zhang, Yuanli Zhou, Xiao Xu
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-09-01
Series:Frontiers in Neurorobotics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fnbot.2024.1471327/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850264156274425856
author Yaolei Zhang
Fei Zhang
Yuanli Zhou
Xiao Xu
author_facet Yaolei Zhang
Fei Zhang
Yuanli Zhou
Xiao Xu
author_sort Yaolei Zhang
collection DOAJ
description The advancements in intelligent action recognition can be instrumental in developing autonomous robotic systems capable of analyzing complex human activities in real-time, contributing to the growing field of robotics that operates in dynamic environments. The precise recognition of basketball players' actions using artificial intelligence technology can provide valuable assistance and guidance to athletes, coaches, and analysts, and can help referees make fairer decisions during games. However, unlike action recognition in simpler scenarios, the background in basketball is similar and complex, the differences between various actions are subtle, and lighting conditions are inconsistent, making action recognition in basketball a challenging task. To address this problem, an Adaptive Context-Aware Network (ACA-Net) for basketball player action recognition is proposed in this paper. It contains a Long Short-term Adaptive (LSTA) module and a Triplet Spatial-Channel Interaction (TSCI) module to extract effective features at the temporal, spatial, and channel levels. The LSTA module adaptively learns global and local temporal features of the video. The TSCI module enhances the feature representation by learning the interaction features between space and channels. We conducted extensive experiments on the popular basketball action recognition datasets SpaceJam and Basketball-51. The results show that ACA-Net outperforms the current mainstream methods, achieving 89.26% and 92.05% in terms of classification accuracy on the two datasets, respectively. ACA-Net's adaptable architecture also holds potential for real-world applications in autonomous robotics, where accurate recognition of complex human actions in unstructured environments is crucial for tasks such as automated game analysis, player performance evaluation, and enhanced interactive broadcasting experiences.
format Article
id doaj-art-3b8fffe39af84f96903d4cea079e1171
institution OA Journals
issn 1662-5218
language English
publishDate 2024-09-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Neurorobotics
spelling doaj-art-3b8fffe39af84f96903d4cea079e11712025-08-20T01:54:46ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182024-09-011810.3389/fnbot.2024.14713271471327ACA-Net: adaptive context-aware network for basketball action recognitionYaolei Zhang0Fei Zhang1Yuanli Zhou2Xiao Xu3China Basketball College, Beijing Sport University, Beijing, ChinaCollege of Physical Education, Hangzhou Normal University, Hangzhou, Zhejiang, ChinaRadar Non-Commissioned Officers' School, Air Force Early Warning Academy, Wuhan, Hubei, ChinaCollege of Physical Education, Dalian University, Dalian, Liaoning, ChinaThe advancements in intelligent action recognition can be instrumental in developing autonomous robotic systems capable of analyzing complex human activities in real-time, contributing to the growing field of robotics that operates in dynamic environments. The precise recognition of basketball players' actions using artificial intelligence technology can provide valuable assistance and guidance to athletes, coaches, and analysts, and can help referees make fairer decisions during games. However, unlike action recognition in simpler scenarios, the background in basketball is similar and complex, the differences between various actions are subtle, and lighting conditions are inconsistent, making action recognition in basketball a challenging task. To address this problem, an Adaptive Context-Aware Network (ACA-Net) for basketball player action recognition is proposed in this paper. It contains a Long Short-term Adaptive (LSTA) module and a Triplet Spatial-Channel Interaction (TSCI) module to extract effective features at the temporal, spatial, and channel levels. The LSTA module adaptively learns global and local temporal features of the video. The TSCI module enhances the feature representation by learning the interaction features between space and channels. We conducted extensive experiments on the popular basketball action recognition datasets SpaceJam and Basketball-51. The results show that ACA-Net outperforms the current mainstream methods, achieving 89.26% and 92.05% in terms of classification accuracy on the two datasets, respectively. ACA-Net's adaptable architecture also holds potential for real-world applications in autonomous robotics, where accurate recognition of complex human actions in unstructured environments is crucial for tasks such as automated game analysis, player performance evaluation, and enhanced interactive broadcasting experiences.https://www.frontiersin.org/articles/10.3389/fnbot.2024.1471327/fullbasketballaction recognitionadaptive context-awarenesslong short-term informationspace-channel information interaction
spellingShingle Yaolei Zhang
Fei Zhang
Yuanli Zhou
Xiao Xu
ACA-Net: adaptive context-aware network for basketball action recognition
Frontiers in Neurorobotics
basketball
action recognition
adaptive context-awareness
long short-term information
space-channel information interaction
title ACA-Net: adaptive context-aware network for basketball action recognition
title_full ACA-Net: adaptive context-aware network for basketball action recognition
title_fullStr ACA-Net: adaptive context-aware network for basketball action recognition
title_full_unstemmed ACA-Net: adaptive context-aware network for basketball action recognition
title_short ACA-Net: adaptive context-aware network for basketball action recognition
title_sort aca net adaptive context aware network for basketball action recognition
topic basketball
action recognition
adaptive context-awareness
long short-term information
space-channel information interaction
url https://www.frontiersin.org/articles/10.3389/fnbot.2024.1471327/full
work_keys_str_mv AT yaoleizhang acanetadaptivecontextawarenetworkforbasketballactionrecognition
AT feizhang acanetadaptivecontextawarenetworkforbasketballactionrecognition
AT yuanlizhou acanetadaptivecontextawarenetworkforbasketballactionrecognition
AT xiaoxu acanetadaptivecontextawarenetworkforbasketballactionrecognition