Perfusion assessment via local remote photoplethysmography (rPPG)

Kossack, Benjamin; Wisotzky, Eric L.; Eisert, Peter; Schraven, Sebastian P.; Globke, Brigitta; Hilsmann, Anna

doi:10.1109/cvprw56347.2022.00238

Cited by 13 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also applied our approach to intraoperative image data, as HSI can be used in intraoperative settings in order to differentiate between different tissue types [35] or to extract vital information [24,18]. Fig.…”

Section: Intraoperative Image Demosaicingmentioning

confidence: 99%

Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning

Wisotzky

Daudkane

Hilsmann

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Spectral imaging technologies have rapidly evolved during the past decades. The recent development of single-camera-one-shot techniques for hyperspectral imaging allows multiple spectral bands to be captured simultaneously (3 × 3, 4 × 4 or 5 × 5 mosaic), opening up a wide range of applications. Examples include intraoperative imaging, agricultural field inspection and food quality assessment. To capture images across a wide spectrum range, i.e. to achieve high spectral resolution, the sensor design sacrifices spatial resolution. With increasing mosaic size, this effect becomes increasingly detrimental. Furthermore, demosaicing is challenging. Without incorporating edge, shape, and object information during interpolation, chromatic artifacts are likely to appear in the obtained images. Recent approaches use neural networks for demosaicing, enabling direct information extraction from image data. However, obtaining training data for these approaches poses a challenge as well. This work proposes a parallel neural network based demosaicing procedure trained on a new ground truth dataset captured in a controlled environment by a hyperspectral snapshot camera with a 4 × 4 mosaic pattern. The dataset is a combination of real captured scenes with images from publicly available data adapted to the 4 × 4 mosaic pattern. To obtain real world ground-truth data, we performed multiple camera captures with 1-pixel shifts in order to compose the entire data cube. Experiments show that the proposed network outperforms state-of-art networks.

show abstract

Section: Intraoperative Image Demosaicingmentioning

confidence: 99%

Hyperspectral Demosaicing of Snapshot Camera Images Using Deep Learning

Wisotzky

Daudkane

Hilsmann

et al. 2022

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Contact-based methods are uncomfortable to wear, have a higher cost, and are not user-friendly for individuals with fragile skin. Due to these shortcomings of contact-based heart rate detection methods, non-contact methods for heart rate detection have received increasing attention [3][4][5] .…”

Section: Introductionmentioning

confidence: 99%

Facial video heart rate detection based on fast-ICA and LA-Res2Net

Xiao¹,

Zhang²,

Chen³

et al. 2023

International Conference on Image, Signal Processing, and Pattern Recognition (ISPP 2023)

View full text Add to dashboard Cite

The majority of non-contact heart rate detection are based on pure traditional or pure deep learning methods, which struggle with high noise interference and low accuracy in complex scenes or with insufficient training data. Therefore, this paper proposes a hybrid method that combines traditional signal processing with deep learning, leveraging the complementary advantages of both, to enhance heart rate detection accuracy and robustness. First, Gaussian heatmaps are used to predict the facial keypoints for Region of Interest (ROI) localization, from which the skin color change signals of RGB channels are extracted. After using Fast-ICA to demix the pixel averages of the three channels, three independent source signals are obtained, and the signal with the highest signal-to-noise ratio is selected as the remote photoplethysmography (rPPG) signal. Then Gramian angular field method (GAF) is used to encode the feature image of rPPG signal as the input of LA-Res2Net, and finally the model can infer the heart rate after training. The effectiveness of the proposed method is verified using the VIPL-HR-V2 dataset. Experimental results show that compared with traditional image processing methods and other advanced models, the proposed method reduces the mean absolute error (MAE) from 15.2 BPM to 6.2 BPM, the root mean square error (RMSE) from 19.5 BPM to 9.1 BPM, and increases the Pearson correlation coefficient (R) from 0.22 to 0.62. This indicates that the proposed method provides a reliable solution for remote non-contact human heart rate detection.

show abstract