Person-specific behavioural features for automatic stress detection

Abstract

International audienceThis paper introduces behavioural features for automatic stress detection, and a person-specific normalization to enhance the performance of our system. The presented features are all visual cues automatically extracted using video processing and depth data. In order to collect the necessary data, we conducted a lab study for stress elicitation using a time constrained arithmetic mental test. Then, we propose a set of body language features for stress detection. Experimental results using a SVM show that our model can detect stress with high accuracy (77%). Moreover, person specific normalization significantly improves classification results (from 67% to 77%). Also, the performance of each of the presented features is discussed

Toward automatic detection of acute stress: Relevant nonverbal behaviors and impact of personality traits

“…Gao et al [11] propose to identify the stress levels of participants in a car driving task from the automatic detection of anger and disgust. Aigrain et al [9] propose to infer stress by combining facial and body cues. Facial features are extracted from facial Action Units related to eyebrow movements, lip movements, cheek raising, nose wrinkling, chin raising, and jaw dropping.…”

“…3e). Motion history images (MHI) have been proven to be very robust in detecting motion and is widely employed by various research groups for action recognition and motion analysis [9], [10]. Other processing techniques such as optical flow or dense face tracking will be considered in future work.…”

“…However, most of these systems require invasive sensors that may themselves induce stress in participants. Recent advances in computer vision have led to the design of noninvasive systems capable of estimating user stress from the video analysis of facial expressions, gestures, postures, gaze and blinking, and head movements [9], [10], [11], [12]. Tasks and situations commonly used for the design and evaluation of these systems include mathematical problem solving, public speaking and global overwhelming workload.…”

“…Tasks and situations commonly used for the design and evaluation of these systems include mathematical problem solving, public speaking and global overwhelming workload. However, stress recognition remains limited in these studies, mainly because all these nonverbal behaviors do not always provide useful information for stress detection during a specific task [9]. In addition, these systems and their evaluation do not always consider individual factors such as personality and individual differences, which may impact stress-coping strategies and associated behaviors [13].…”

An Empirical Study Comparing Unobtrusive Physiological Sensors for Stress Detection in Computer Work

“…The reviewed studies include research in workplace settings or computer use contexts. To narrow the scope of the review, we consider studies that use physiological signals to detect stress, and exclude studies focused on physical, facial and behavioral signals of stress (e.g., [35,36,37,38,39,40,41]). Studies approximating physiological measures with motion-based sensors such as accelerometers and gyroscopes (e.g., [42,43,44]) are also beyond the scope of this review.…”