Aung Min S H, Kaltwang Sebastian, Romera-Paredes Bernardino, Martinez Brais, Singh Aneesha, Cella Matteo, Valstar Michel, Meng Hongying, Kemp Andrew, Shafizadeh Moshen, Elkins Aaron C, Kanakam Natalie, de Rothschild Amschel, Tyler Nick, Watson Paul J, de C Williams Amanda C, Pantic Maja, Bianchi-Berthouze Nadia
UCL Interaction Centre, University, College London, London WC1E 6BT, Unithed Kingdom.
Department of Computing, Imperial College London, London SW7 2AZ, Unithed Kingdom.
IEEE Trans Affect Comput. 2016 Oct-Dec;7(4):435-451. doi: 10.1109/TAFFC.2015.2462830. Epub 2015 Jul 30.
Pain-related emotions are a major barrier to effective self rehabilitation in chronic pain. Automated coaching systems capable of detecting these emotions are a potential solution. This paper lays the foundation for the development of such systems by making three contributions. First, through literature reviews, an overview of how pain is expressed in chronic pain and the motivation for detecting it in physical rehabilitation is provided. Second, a fully labelled multimodal dataset (named ) containing high resolution multiple-view face videos, head mounted and room audio signals, full body 3D motion capture and electromyographic signals from back muscles is supplied. Natural unconstrained pain related facial expressions and body movement behaviours were elicited from people with chronic pain carrying out physical exercises. Both instructed and non-instructed exercises were considered to reflect traditional scenarios of physiotherapist directed therapy and home-based self-directed therapy. Two sets of labels were assigned: level of pain from facial expressions annotated by eight raters and the occurrence of six pain-related body behaviours segmented by four experts. Third, through exploratory experiments grounded in the data, the factors and challenges in the automated recognition of such expressions and behaviour are described, the paper concludes by discussing potential avenues in the context of these findings also highlighting differences for the two exercise scenarios addressed.
疼痛相关情绪是慢性疼痛患者有效自我康复的主要障碍。能够检测这些情绪的自动化指导系统是一种潜在的解决方案。本文通过三项贡献为此类系统的开发奠定了基础。首先，通过文献综述，概述了慢性疼痛中疼痛的表达方式以及在物理康复中检测疼痛的动机。其次，提供了一个完全标注的多模态数据集（名为 ），其中包含高分辨率多视角面部视频、头戴式和室内音频信号、全身三维运动捕捉以及背部肌肉的肌电信号。从进行体育锻炼的慢性疼痛患者中引出了自然无约束的与疼痛相关的面部表情和身体运动行为。有指导和无指导的锻炼都被纳入考虑，以反映物理治疗师指导治疗和家庭自我指导治疗的传统场景。分配了两组标签：由八位评估者标注的面部表情疼痛程度，以及由四位专家分割的六种与疼痛相关身体行为的发生情况。第三，通过基于数据的探索性实验，描述了自动识别此类表情和行为的因素及挑战，本文最后讨论了在这些研究结果背景下的潜在途径，同时也突出了针对两种锻炼场景的差异。
