A motion-robust contactless photoplethysmography using chrominance and adaptive filtering

Huang, Ren-You; Dung, Lan‐Rong

doi:10.1109/biocas.2015.7348451

Cited by 19 publications

(11 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Afterwards, several works [21], [22] have continued to increase the stability of CHRO with respect to facial motion in indoor scenarios. Huang and Dung [23] take facial position signal into consideration, employing ICA method to recover a cleaner HR signal when participants using indoor cycling machine. Hsu et al [24] applied Support Vector Regression (SVR) to CHRO in indoor naturalistic HCI scenario.…”

Section: Related Workmentioning

confidence: 99%

Neural Network Based Luminance Variation Resistant Remote-Photoplethysmography for Driver’s Heart Rate Monitoring

Chu

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

The driver's physiological status has enormous value to public traffic safety and cannot be ignored nowadays. In addition, heart rate (HR) is one of the most important indicators of human's health status. When detecting the driver's HR, using traditional contact-type devices might bring about the driver's distraction or discomfort. On the contrary, the remote photoplethysmography (rPPG) technique is a better way to monitor a driver's HR in vehicle applications simply by using a web-camera without interfering the driver. Most of the rPPG studies intended to reduce the interference caused by facial motion or luminance changes in the indoor or controlled scenario, but there are relatively fewer discussions on outdoor scenarios. Consequently, the purpose of this paper is to enhance the rPPG technique to make it suitable for the outdoor driving scenarios and for monitoring the driver's HR in different weather conditions, including daytime and nighttime. We first utilize artificial neural network (ANN) and train multiple personalized ANN models for each driver. For predicting the drivers' HR beat more precisely, we propose the approach, adaptive neural network model selection (ANNMS), which adaptively selects a personalized ANN model based on different noise conditions. Our algorithm eliminates the effect of noises caused by the variations of facial luminance in eight outdoor driving scenarios. The proposed driver's HR beat monitoring system has been evaluated against the state-of-the-art rPPG techniques that are Chrominance signal-based (CHRO) and k-nearest neighborsbased (kNN) algorithms. Compared with the CHRO and kNN algorithms, the ANNMS reduces the mean absolute error from 14.71 bpm (CHRO) and 9.91 (kNN) to 4.51 bpm (ANNMS) and enhances the successrate-10, the probability in which the absolute error is below 10 bpm, from 44.1% (CHRO) and 56.3% (kNN) to 91.5% (ANNMS). INDEX TERMS Advanced driver assistance systems, artificial neural network, heart rate monitoring, health and safety, remote photoplethysmography, vehicle safety.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural Network Based Luminance Variation Resistant Remote-Photoplethysmography for Driver’s Heart Rate Monitoring

Chu

Huang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

show abstract

“…From studies of still subjects [34] the top candidates are the forehead and the cheek regions. The most frequently applied approach to finding the ROI is to use OpenCV face detection [35], [36], [37], [38], [39], [40], [41], [42] which generates a face box. To extract the more relevant portions of the face box, one can simply choose to use some portion of the width and height [35], [41], or apply a skin detection algorithm to find and apply a "skin mask" to the ROI [42].…”

Section: Roi Selectionmentioning

confidence: 99%

“…The most frequently applied approach to finding the ROI is to use OpenCV face detection [35], [36], [37], [38], [39], [40], [41], [42] which generates a face box. To extract the more relevant portions of the face box, one can simply choose to use some portion of the width and height [35], [41], or apply a skin detection algorithm to find and apply a "skin mask" to the ROI [42]. The second most popular selection is the forehead rectangle [43], [44], in some cases subdivided into multiple regions [45].…”

Section: Roi Selectionmentioning

confidence: 99%

“…A common method of extracting more frequent readings from a single timedomain waveform is to use overlapping sliding windows, and perform an FFT for each window [39], [41], [35]. For example, in [39], 8-second windows with 6-second overlap are used, and a zero-padded FFT is performed once every 2 seconds giving an updated heart-rate reading.…”

Section: Figure 18: Time and Spectral Domain Bvp Signalmentioning

confidence: 99%

“…In some cases, even small involuntary motion produced when the subject's head was not placed in a chinrest was considered source of motion artifacts [58]. In another case, a very specific periodic motion which occurs while subject is using exercise equipment such as bike or stepper is considered [41].…”

Section: Motion Artifactsmentioning

confidence: 99%

See 2 more Smart Citations

Heart Rate and Heart Rate Variability Estimation in the Presence of Motion Artifacts

Nikolic-Popovic¹

View full text Add to dashboard Cite

Vital signs such as heart rate and heart rate variability can be acquired using a variety of equipment, such as ECG, pulse oximeter and even video camera. ECG using wet electrodes is considered the gold standard, but it is not suitable for long-term patient monitoring. Dry electrodes (e.g. a wearable chest-strap) could solve this problem, but the motion of the sensor relative to the skin affects measurements. Non-contact modalities (e.g. heart rate detected from a video of patient's face) could offer further advancements in patient care, but again motion artifacts, caused by changing illumination conditions, affect measurements. Mainstream processing techniques typically assume ideal conditions and fail under realistic conditions. This thesis pinpoints the failure mechanisms of a few commonly used heart rate estimation methods under realistic conditions and proposes mitigation techniques, hoping to contribute to the effort of increasing adoption rate of modern and convenient sensor technologies for patient care.iii

show abstract

A Motion Robust Remote-PPG Approach to Driver’s Health State Monitoring

Chu

Huang

et al. 2017

Computer Vision – ACCV 2016 Workshops

View full text Add to dashboard Cite

A motion-robust contactless photoplethysmography using chrominance and adaptive filtering

Cited by 19 publications

References 13 publications

Neural Network Based Luminance Variation Resistant Remote-Photoplethysmography for Driver’s Heart Rate Monitoring

Neural Network Based Luminance Variation Resistant Remote-Photoplethysmography for Driver’s Heart Rate Monitoring

Heart Rate and Heart Rate Variability Estimation in the Presence of Motion Artifacts

A Motion Robust Remote-PPG Approach to Driver’s Health State Monitoring

Contact Info

Product

Resources

About