Remote measurements of the cardiac pulse can provide comfortable physiological assessment without electrodes. However, attempts so far are non-automated, susceptible to motion artifacts and typically expensive. In this paper, we introduce a new methodology that overcomes these problems. This novel approach can be applied to color video recordings of the human face and is based on automatic face tracking along with blind source separation of the color channels into independent components. Using Bland-Altman and correlation analysis, we compared the cardiac pulse rate extracted from videos recorded by a basic webcam to an FDA-approved finger blood volume pulse (BVP) sensor and achieved high accuracy and correlation even in the presence of movement artifacts. Furthermore, we applied this technique to perform heart rate measurements from three participants simultaneously. This is the first demonstration of a low-cost accurate video-based method for contact-free heart rate measurements that is automated, motion-tolerant and capable of performing concomitant measurements on more than one person at a time.

Abstract-We present a simple, low-cost method for measuring multiple physiological parameters using a basic webcam. By applying independent component analysis on the color channels in video recordings, we extracted the blood volume pulse from the facial regions. Heart rate (HR), respiratory rate, and HR variability (HRV, an index for cardiac autonomic activity) were subsequently quantified and compared to corresponding measurements using Food and Drug Administration-approved sensors. High degrees of agreement were achieved between the measurements across all physiological parameters. This technology has significant potential for advancing personal health care and telemedicine.Index Terms-Autonomic nervous system, blood volume pulse (BVP), heart rate variability (HRV), independent component analysis (ICA), noncontact, photoplethysmography (PPG), remote sensing, respiration.

Non-contact video-based physiological measurement has many applications in health care and human-computer interaction. Practical applications require measurements to be accurate even in the presence of large head rotations. We propose the first end-to-end system for videobased measurement of heart and breathing rate using a deep convolutional network. The system features a new motion representation based on a skin reflection model and a new attention mechanism using appearance information to guide motion estimation, both of which enable robust measurement under heterogeneous lighting and major motions. Our approach significantly outperforms all current state-of-the-art methods on both RGB and infrared video datasets. Furthermore, it allows spatial-temporal distributions of physiological signals to be visualized via the attention mechanism.

Abstract-Remote measurement of the blood volume pulse via photoplethysmography (PPG) using digital cameras and ambient light has great potential for healthcare and affective computing. However, traditional RGB cameras have limited frequency resolution. We present results of PPG measurements from a novel five band camera and show that alternate frequency bands, in particular an orange band, allowed physiological measurements much more highly correlated with an FDA approved contact PPG sensor. In a study with participants (n=10) at rest and under stress, correlations of over 0.92 (p<0.01) were obtained for heart rate, breathing rate and heart rate variability measurements. In addition, the remotely measured HRV spectrograms closely matched those from the contact approach. The best results were obtained using a combination of cyan, green and orange (CGO) bands; incorporating red and blue channel observations did not improve performance. In short, RGB is not optimal for this problem: CGO is better. Incorporating alternative color channel sensors should not increase the cost of such cameras dramatically.Index Terms-heart rate variability (HRV), blood volume pulse (BVP), photoplethysmography (PPG), remote sensing.

Abstract-Remote detection of cognitive load has many powerful applications, such as measuring stress in the workplace. Cognitive tasks have an impact on breathing and heart rate variability (HRV). We show that changes in physiological parameters during cognitive stress can be captured remotely (at a distance of 3m) using a digital camera. A study (n=10) was conducted with participants at rest and under cognitive stress. A novel five band digital camera was used to capture videos of the face of the participant. Significantly higher normalized low frequency HRV components and breathing rates were measured in the stress condition when compared to the rest condition. Heart rates were not significantly different between the two conditions. We built a person-independent classifier to predict cognitive stress based on the remotely detected physiological parameters (heart rate, breathing rate and heart rate variability). The accuracy of the model was 85% (35% greater than chance).

Computer classification of facial expressions requires large amounts of data and this data needs to reflect the diversity of conditions seen in real applications. Public datasets help accelerate the progress of research by providing researchers with a benchmark resource. We present a comprehensively labeled dataset of ecologically valid spontaneous facial responses recorded in natural settings over the Internet. To collect the data, online viewers watched one of three intentionally amusing Super Bowl commercials and were simultaneously filmed using their webcam. They answered three self-report questions about their experience. A subset of viewers additionally gave consent for their data to be shared publicly with other researchers. This subset consists of 242 facial videos (168,359 frames) recorded in real world conditions. The dataset is comprehensively labeled for the following: 1) frame-by-frame labels for the presence of 10 symmetrical FACS action units, 4 asymmetric (unilateral) FACS action units, 2 head movements, smile, general expressiveness, feature tracker fails and gender; 2) the location of 22 automatically detected landmark points; 3) self-report responses of familiarity with, liking of, and desire to watch again for the stimuli videos and 4) baseline performance of detection algorithms on this dataset.

Abstract-We present a new method for measuring photoplethysmogram (PPG) signals remotely using ambient light and a digital camera that allows for accurate recovery of the waveform morphology (from a distance of 3m). In particular, we show that the peak-to-peak time between the systolic peak and diastolic peak/inflection can be automatically recovered using the second order derivative of the remotely measured waveform. We compare measurements from the face with those captured using a contact finger-tip sensor and show high agreement in peak and interval timings. Furthermore, we show that results can be significantly improved using orange, green and cyan color channels compared to the tradition red, green and blue channel combination. The absolute error in inter-beat-intervals was 26ms and the absolute error in mean systolic-diastolic peak-to-peak times was 12ms. The mean systolic-diastolic peak-to-peak times measured using the contact sensor and the camera were highly correlated, ρ = 0.94 (p<0.001). The results were obtained with a camera frame-rate of only 30Hz. This technology has significant potential for advancing healthcare.

Abstract-Billions of online video ads are viewed every month. We present a large-scale analysis of facial responses to video content measured over the Internet and their relationship to marketing effectiveness. We collected over 12,000 facial responses from 1,223 people to 170 ads from a range of markets and product categories. The facial responses were automatically coded frameby-frame. Collection and coding of these 3.7 million frames would not have been feasible with traditional research methods. We show that detected expressions are sparse but that aggregate responses reveal rich emotion trajectories. By modeling the relationship between the facial responses and ad effectiveness we show that ad liking can be predicted accurately (ROC AUC=0.85) from webcam facial responses. Furthermore, the prediction of a change in purchase intent is possible (ROC AUC=0.78). Ad liking is shown by eliciting expressions, particularly positive expressions. Driving purchase intent is more complex than just making viewers smile: peak positive responses that are immediately preceded by a brand appearance are more likely to be effective. The results presented here demonstrate a reliable and generalizable system for predicting ad effectiveness automatically from facial responses without a need to elicit self-report responses from the viewers. In addition we can gain insight into the structure of effective ads.