Photoplethysmography and its application in clinical physiological measurement

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy. We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network. YOLOv4-large model achieves state-of-the-art results: 55.4% AP (73.3% AP50) for the MS COCO dataset at a speed of 15 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 55.8% AP (73.2 AP50). To the best of our knowledge, this is currently the highest accuracy on the COCO dataset among any published work. The YOLOv4-tiny model achieves 22.0% AP (42.0% AP50) at a speed of 443 FPS on RTX 2080Ti, while by using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.

Scaled-YOLOv4: Scaling Cross Stage Partial Network

Face anti-spoofing is crucial to prevent face recognition systems from a security breach. Previous deep learning approaches formulate face anti-spoofing as a binary classification problem. Many of them struggle to grasp adequate spoofing cues and generalize poorly. In this paper, we argue the importance of auxiliary supervision to guide the learning toward discriminative and generalizable cues. A CNN-RNN model is learned to estimate the face depth with pixel-wise supervision, and to estimate rPPG signals with sequence-wise supervision. The estimated depth and rPPG are fused to distinguish live vs. spoof faces. Further, we introduce a new face anti-spoofing database that covers a large range of illumination, subject, and pose variations. Experiments show that our model achieves the state-of-the-art results on both intra- and cross-database testing.

/pdf/learning-deep-models-for-face-anti-spoofing-binary-or-1ekom3p7fk.pdf

Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision

Photoplethysmography (PPG) is a noninvasive optical technique for detecting microvascular blood volume changes in tissues. Its ease of use, low cost and convenience make it an attractive area of research in the biomedical and clinical communities. Nevertheless, its single spot monitoring and the need to apply a PPG sensor directly to the skin limit its practicality in situations such as perfusion mapping and healing assessments or when free movement is required. The introduction of fast digital cameras into clinical imaging monitoring and diagnosis systems, the desire to reduce the physical restrictions, and the possible new insights that might come from perfusion imaging and mapping inspired the evolution of the conventional PPG technology to imaging PPG (IPPG). IPPG is a noncontact method that can detect heart-generated pulse waves by means of peripheral blood perfusion measurements. Since its inception, IPPG has attracted significant public interest and provided opportunities to improve personal healthcare. This study presents an overview of the wide range of IPPG systems currently being introduced along with examples of their application in various physiological assessments. We believe that the widespread acceptance of IPPG is happening, and it will dramatically accelerate the promotion of this healthcare model in the near future.

/pdf/photoplethysmography-revisited-from-contact-to-noncontact-2jla840amb.pdf

Photoplethysmography Revisited: From Contact to Noncontact, From Point to Imaging

We show that the YOLOv4 object detection neural network based on the CSP approach, scales both up and down and is applicable to small and large networks while maintaining optimal speed and accuracy. We propose a network scaling approach that modifies not only the depth, width, resolution, but also structure of the network. YOLOv4-large model achieves state-of-the-art results: 55.5% AP (73.4% AP 50 ) for the MS COCO dataset at a speed of ~ 16 FPS on Tesla V100, while with the test time augmentation, YOLOv4-large achieves 56.0% AP (73.3 AP 50 ). To the best of our knowledge, this is currently the highest accuracy on the COCO dataset among any published work. The YOLOv4-tiny model achieves 22.0% AP (42.0% AP 50 ) at a speed of ~443 FPS on RTX 2080Ti, while by using TensorRT, batch size = 4 and FP16-precision the YOLOv4-tiny achieves 1774 FPS.

/pdf/scaled-yolov4-scaling-cross-stage-partial-network-49z1s6zwvq.pdf

Integration of image quality and motion cues for face anti-spoofing

Remote imaging photoplethysmography (RIPPG) can achieve contactless monitoring of human vital signs. However, the robustness to a subject’s motion is a challenging problem for RIPPG, especially in facial video-based RIPPG. The RIPPG signal originates from the radiant intensity variation of human skin with pulses of blood and motions can modulate the radiant intensity of the skin. Based on the optical properties of human skin, we build an optical RIPPG signal model in which the origins of the RIPPG signal and motion artifacts can be clearly described. The region of interest (ROI) of the skin is regarded as a Lambertian radiator and the effect of ROI tracking is analyzed from the perspective of radiometry. By considering a digital color camera as a simple spectrometer, we propose an adaptive color difference operation between the green and red channels to reduce motion artifacts. Based on the spectral characteristics of photoplethysmography signals, we propose an adaptive bandpass filter to remove residual motion artifacts of RIPPG. We also combine ROI selection on the subject’s cheeks with speeded-up robust features points tracking to improve the RIPPG signal quality. Experimental results show that the proposed RIPPG can obtain greatly improved performance in accessing heart rates in moving subjects, compared with the state-of-the-art facial video-based RIPPG methods.

Motion-Resistant Remote Imaging Photoplethysmography Based on the Optical Properties of Skin

In this paper, we propose an efficient general-purpose no-reference (NR) video quality assessment (VQA) framework that is based on 3D shearlet transform and convolutional neural network (CNN). Taking video blocks as input, simple and efficient primary spatiotemporal features are extracted by 3D shearlet transform, which are capable of capturing natural scene statistics properties. Then, CNN and logistic regression are concatenated to exaggerate the discriminative parts of the primary features and predict a perceptual quality score. The resulting algorithm, which we name shearlet- and CNN-based NR VQA (SACONVA), is tested on well-known VQA databases of Laboratory for Image & Video Engineering, Image & Video Processing Laboratory, and CSIQ. The testing results have demonstrated that SACONVA performs well in predicting video quality and is competitive with current state-of-the-art full-reference VQA methods and general-purpose NR-VQA algorithms. Besides, SACONVA is extended to classify different video distortion types in these three databases and achieves excellent classification accuracy. In addition, we also demonstrate that SACONVA can be directly applied in real applications such as blind video denoising.

No-Reference Video Quality Assessment With 3D Shearlet Transform and Convolutional Neural Networks

No-reference image quality assessment with shearlet transform and deep neural networks

Feature pyramid has been an efficient method to extract features at different scales. Development over this method mainly focuses on aggregating contextual information at different levels while seldom touching the inter-level correlation in the feature pyramid. Early computer vision methods extracted scale-invariant features by locating the feature extrema in both spatial and scale dimension. Inspired by this, a convolution across the pyramid level is proposed in this study, which is termed pyramid convolution and is a modified 3-D convolution. Stacked pyramid convolutions directly extract 3-D (scale and spatial) features and outperforms other meticulously designed feature fusion modules. Based on the viewpoint of 3-D convolution, an integrated batch normalization that collects statistics from the whole feature pyramid is naturally inserted after the pyramid convolution. Furthermore, we also show that the naive pyramid convolution, together with the design of RetinaNet head, actually best applies for extracting features from a Gaussian pyramid, whose properties can hardly be satisfied by a feature pyramid. In order to alleviate this discrepancy, we build a scale-equalizing pyramid convolution (SEPC) that aligns the shared pyramid convolution kernel only at high-level feature maps. Being computationally efficient and compatible with the head design of most single-stage object detectors, the SEPC module brings significant performance improvement (>4AP increase on MS-COCO2017 dataset) in state-of-the-art one-stage object detectors, and a light version of SEPC also has ~3.5AP gain with only around 7% inference time increase. The pyramid convolution also functions well as a stand-alone module in two-stage object detectors and is able to improve the performance by ~2AP. The source code can be found at https://github.com/jshilong/SEPC.

/pdf/scale-equalizing-pyramid-convolution-for-object-detection-1td1dx684h.pdf

Litong Feng

Papers

Integration of image quality and motion cues for face anti-spoofing

Motion-Resistant Remote Imaging Photoplethysmography Based on the Optical Properties of Skin

No-Reference Video Quality Assessment With 3D Shearlet Transform and Convolutional Neural Networks

No-reference image quality assessment with shearlet transform and deep neural networks

Scale-Equalizing Pyramid Convolution for Object Detection