Human Action Recognition Using Laban Movement Analysis and Dynamic Time Warping

Zahra Ramezanpanah (1) , Malik Mallem (1) , Frédéric Davesne (1)

1 IBISC - Informatique, BioInformatique, Systèmes Complexes

Bilateral interaction between humans and robots is one of the areas that has attracted much attention in recent years.Automation of human behavior recognition is one of the main steps in achieving this goal. In this regard, in this paperwe have designed a process for automatic identification of human gestures. The process consists of two main parts. Inthe first part, by using the Laban Movement Analysis method, we define a robust descriptor, and in the second part, wedetermine the robustness of the descriptor using the Dynamic Time Warping algorithm. The method proposed in thispaper has been tested on four public data-sets namely MSR Action 3D, Florence 3D actions, UTKinect-Action3D andSYSU 3D HUMAN-OBJECT INTERACTION data-sets. Given the results obtained from previous work, the efficiencyof the proposed method can be more accurately understood. The results obtained confirm the effectiveness and theperformance of our model which outperforms results presented in similar works on action recognition.

Mots clés: Laban Movement Analysis; Human Gesture Recognition; Dynamic Time Warping

Domaines: Traitement du signal et de l'image [eess.SP]

Zahra Ramezanpanah, Malik Mallem, Frédéric Davesne. Human Action Recognition Using Laban Movement Analysis and Dynamic Time Warping. 24th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES 2020), Sep 2020, Verona (virtual), Italy. ⟨10.1016/j.procs.2020.08.040⟩. ⟨hal-02613751⟩