We propose an automatic method to estimate self-reported pain intensity based on facial landmarks extracted from videos. For each video sequence, we decompose the face into four different regions and pain intensity is measured by modeling the dynamics of facial movement using the landmarks of these regions. A formulation based on Gram matrices is used to represent the trajectory of facial landmarks on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. A curve fitting algorithm is then used to smooth the trajectories and a temporal alignment is performed to compute the similarity between the trajectories on the manifold. A Support Vector Regression classifier is then trained to encode the extracted trajectories into pain intensity levels consistent with the self-reported pain intensity measurement. Finally, a late fusion of the estimation for each region is performed to obtain the final predicted pain intensity level. The proposed approach is evaluated on two publicly available databases, the UNBCMcMaster Shoulder Pain Archive and the Biovid Heat Pain database. We compared our method to the state-of-the-art on both databases using different testing protocols, showing the competitiveness of the proposed approach.

Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matrices / Szczapa, Benjamin; Daoudi, Mohamed; Berretti, Stefano; Pala, Pietro; Bimbo, Alberto Del; Hammal, Zakia. - In: IEEE TRANSACTIONS ON AFFECTIVE COMPUTING. - ISSN 1949-3045. - STAMPA. - 13:(2022), pp. 4.1813-4.1826. [10.1109/TAFFC.2022.3207001]

Automatic Estimation of Self-Reported Pain by Trajectory Analysis in the Manifold of Fixed Rank Positive Semi-Definite Matrices

Szczapa, Benjamin;Berretti, Stefano;Pala, Pietro;Bimbo, Alberto Del;
2022

Abstract

We propose an automatic method to estimate self-reported pain intensity based on facial landmarks extracted from videos. For each video sequence, we decompose the face into four different regions and pain intensity is measured by modeling the dynamics of facial movement using the landmarks of these regions. A formulation based on Gram matrices is used to represent the trajectory of facial landmarks on the Riemannian manifold of symmetric positive semi-definite matrices of fixed rank. A curve fitting algorithm is then used to smooth the trajectories and a temporal alignment is performed to compute the similarity between the trajectories on the manifold. A Support Vector Regression classifier is then trained to encode the extracted trajectories into pain intensity levels consistent with the self-reported pain intensity measurement. Finally, a late fusion of the estimation for each region is performed to obtain the final predicted pain intensity level. The proposed approach is evaluated on two publicly available databases, the UNBCMcMaster Shoulder Pain Archive and the Biovid Heat Pain database. We compared our method to the state-of-the-art on both databases using different testing protocols, showing the competitiveness of the proposed approach.
2022
13
1813
1826
Goal 9: Industry, Innovation, and Infrastructure
Szczapa, Benjamin; Daoudi, Mohamed; Berretti, Stefano; Pala, Pietro; Bimbo, Alberto Del; Hammal, Zakia
File in questo prodotto:
File Dimensione Formato  
taffc2022.pdf

Accesso chiuso

Descrizione: Documento finale
Tipologia: Versione finale referata (Postprint, Accepted manuscript)
Licenza: DRM non definito
Dimensione 4.32 MB
Formato Adobe PDF
4.32 MB Adobe PDF   Richiedi una copia

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1288905
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 2
  • ???jsp.display-item.citation.isi??? 1
social impact