Action recognition using kinematics posture feature on 3D skeleton joint locations

•Motion information from skeleton can be efficiently encoded by considering the body joints as wearable kinematics sensor.•Proposed Linear Joint Position Feature (LJPF) and Angular Joint Position Feature (AJPF) from positions and bone-angles.•Proposed Kinematics Posture Feature (KPF) from LJPF and A...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Pattern recognition letters 2021-05, Vol.145, p.216-224
Hauptverfasser:	Ahad, Md Atiqur Rahman, Ahmed, Masud, Das Antar, Anindya, Makihara, Yasushi, Yagi, Yasushi
Format:	Artikel
Sprache:	eng
Schlagworte:	Action recognition Activity recognition Angular joint position feature (AJPF) Angular position Benchmark datasets Benchmarks Classification Computer Science Computer Science, Artificial Intelligence Computer vision Convrnn Datasets Deep learning Deep neural network Domains Ensemble architecture Feature extraction Joint angle Joint position Joints (anatomy) Kinematics Kinematics posture feature (KPF) Learning algorithms Linear joint position feature (LJPF) Low pass filters Machine learning Position sensing Position-based statistical feature (PSF) Posture Science & Technology Segments Sensors Skeleton Skeleton data Statistical analysis Statistics Support vector machines Technology Video data
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!