Heartbeat Signal from Facial Video for Biometric Recognition

Haque, Mohammad A.; Nasrollahi, Kamal; Moeslund, Thomas B.

doi:10.1007/978-3-319-19665-7_14

Cited by 13 publications

(6 citation statements)

References 29 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Primitive Radon Features (PRadon) Radon transform is an integral transform that computes projections of an image matrix along specified directions and that is widely used to reconstruct images from medical computed tomography scan [25]. As our motion map was similar to a two-dimensional image and our focus is to discriminate in the motion map by the location and intensity of PA events, we employed Radon transform on the first difference of the feature map as we did for F Dif f .…”

Section: Feature Extraction For Activity Type Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Patient’s Body Motion Study Using Multimodal RGBDT Videos

Haque

Kjeldsen²,

Arguissain

et al. 2018

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

Automatic analysis of body movement to identify physical activity of patients who are at bed rest is crucial for treatment or rehabilitation purposes. Existing methods of physical activity analysis mostly focused on the detection of primitive motion/non-motion states in unimodal video data captured by either RGB or depth or thermal sensor. In this paper, we propose a multimodal visionbased approach to classify body motion of a person lying on a bed. We mimicked a real scenario of 'patient on bed' by recording multimodal video data from healthy volunteers in a hospital room in a neurorehabilitation center. We first defined a taxonomy of possible physical activities based on observations of patients with acquired brain injuries. We then investigated different motion analysis and machine learning approaches to classify physical activities automatically. A multimodal database including RGB, depth and thermal videos was collected and annotated with eight predefined physical activities. Experimental results show that we can achieve moderately high accuracy (77.68%) to classify physical activities by tracking the body motion using an optical flow-based approach. To the best of our knowledge this is the first multimodal RGBDT video analysis for such application.

show abstract

Section: Feature Extraction For Activity Type Classificationmentioning

confidence: 99%

“…Radon Distance Features (DiffRadon) we have previously showed that the pointto-point distance of a Radon image also has an effective discriminating property [25]. Thus, we employed a pairwise-distance method between every possible pairs of pixels…”

Section: Feature Extraction For Activity Type Classificationmentioning

confidence: 99%

Patient’s Body Motion Study Using Multimodal RGBDT Videos

Haque

Kjeldsen²,

Arguissain

et al. 2018

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to obtain the traces of either of the two modalities, we first select a ROI in the detected face. For the color-based approach, the ROI contains 60% of the facial area width (following [2]) detected by the automatic face detection method. We take the average of the RGB values of all pixels in the ROI in each frame instead of only either of the red, green or blue channels to defend the effect of the external lighting condition, as single color channel may prone to increased noise to specific lighting conditions.…”

Section: Facial Color and Motion Traces Extractionmentioning

confidence: 99%

“…When the human heart pumps blood, subtle chromatic changes in the facial skin and slight head motion occur periodically. These changes and motion are associated with the periodic heartbeat signal and can be detected in a facial video [2].…”

Section: Introductionmentioning

confidence: 99%