Michael B. Miller

Satish Kumar, A S M Iftekhar, Michael Goebel et al.

Precise measurement of physiological signals is critical for the effective monitoring of human vital signs. Recent developments in computer vision have demonstrated that signals such as pulse rate and respiration rate can be extracted from digital video of humans, increasing the possibility of contact-less monitoring. This paper presents a novel approach to obtaining physiological signals and classifying stress states from thermal video. The proposed network--"StressNet"--features a hybrid emission representation model that models the direct emission and absorption of heat by the skin and underlying blood vessels. This results in an information-rich feature representation of the face, which is used by spatio-temporal network for reconstructing the ISTI ( Initial Systolic Time Interval: a measure of change in cardiac sympathetic activity that is considered to be a quantitative index of stress in humans ). The reconstructed ISTI signal is fed into a stress-detection model to detect and classify the individual's stress state ( i.e. stress or no stress ). A detailed evaluation demonstrates that StressNet achieves estimated the ISTI signal with 95% accuracy and detect stress with average precision of 0.842. The source code is available on Github.

Jean M. Vettel, Justin Kantner, Matthew Jaswa et al.

The development of increasingly realistic experimental stimuli and task environments is important for understanding behavior outside the laboratory. We report a process for generating 3D human model stimuli that combines commonly used graphics software and enables the flexible generation of animated human models while providing parametric control over individualized identity features. Our approach creates novel head models using FaceGen Modeller, attaches them to commercially-purchased 3D avatar bodies in 3D Studio Max, and generates Cal3D human models that are compatible with many virtual 3D environments. Stimuli produced by this method can be embedded as animated 3D avatars in interactive simulations or presented as 2D images embedded in scenes for use in traditional laboratory experiments. The inherent flexibility in this method makes the stimuli applicable to a broad range of basic and applied research questions in the domain of person perception. We describe the steps of the stimulus generation process, provide an example of their use in a recognition memory paradigm, and highlight the adaptability of the method for related avenues of research.