Fall detection based on dynamic key points incorporating preposed attention.

Accidental falls pose a significant threat to the elderly population, and accurate fall detection from surveillance videos can significantly reduce the negative impact of falls. Although most fall detection algorithms based on video deep learning focus on training and detecting human posture or key points in pictures or videos, we have found that the human pose-based model and key points-based model can complement each other to improve fall detection accuracy. In this paper, we propose a preposed attention capture mechanism for images that will be fed into the training network, and a fall detection model based on this mechanism. We accomplish this by fusing the human dynamic key point information with the original human posture image. We first propose the concept of dynamic key points to account for incomplete pose key point information in the fall state. We then introduce an attention expectation that predicates the original attention mechanism of the depth model by automatically labeling dynamic key points. Finally, the depth model trained with human dynamic key points is used to correct the detection errors of the depth model with raw human pose images. Our experiments on the Fall Detection Dataset and the UP-Fall Detection Dataset demonstrate that our proposed fall detection algorithm can effectively improve the accuracy of fall detection and provide better support for elderly care.

TC-Net: A joint learning framework based on CNN and vision transformer for multi-lesion medical images segmentation.

BACKGROUND: With the rapid advancement of medical imaging technology, the demand for accurate segmentation of medical images is increasing. However, most existing methods are unable to capture locality and long-range dependency information in integrated ways for medical images. METHOD: In this paper, we propose an elegant segmentation framework for medical images named TC-Net, which can utilize both the locality-aware and long-range dependencies in the medical images. As for the locality-aware perspective, we employ a CNN-based encoder and decoder structure. The CNN branch uses the locality of convolution operations to dig out local information in medical images. As for the long-range dependencies, we construct a Transformer branch to focus on the global context. Additionally, we proposed a locality-aware and long-range dependency concatenation strategy (LLCS) to aggregate the feature maps obtained from the two subbranches. Finally, we present a dynamic cyclical focal loss (DCFL) to address the class imbalance problem in multi-lesion segmentation. RESULTS: Comprehensive experiments were conducted on lesion segmentation tasks using two fundus image databases and a skin image database. The TC-Net achieves scores of 0.6985 and 0.5171 in the metric of mean pixel accuracy on the IDRiD and DDR databases, respectively. Moreover, on the skin image database, the TC-Net reached mean pixel accuracy of 0.8886. The experiment results demonstrate that the proposed method achieves better performance than other deep learning segmentation schemes. Furthermore, the proposed DCFL achieves higher performance than other loss functions in multi-lesion segmentation. SIGNIFICANCE: The proposed TC-Net is a promising new framework for multi-lesion medical image segmentation and many other challenging image segmentation tasks. © 2001 Elsevier Science. All rights reserved.

PrivacyMask: Real-world privacy protection in face ID systems.

Recent works have illustrated that many facial privacy protection methods are effective in specific face recognition algorithms. However, the COVID-19 pandemic has promoted the rapid innovation of face recognition algorithms for face occlusion, especially for the face wearing a mask. It is tricky to avoid being tracked by artificial intelligence only through ordinary props because many facial feature extractors can determine the ID only through a tiny local feature. Therefore, the ubiquitous high-precision camera makes privacy protection worrying. In this paper, we establish an attack method directed against liveness detection. A mask printed with a textured pattern is proposed, which can resist the face extractor optimized for face occlusion. We focus on studying the attack efficiency in adversarial patches mapping from two-dimensional to three-dimensional space. Specifically, we investigate a projection network for the mask structure. It can convert the patches to fit perfectly on the mask. Even if it is deformed, rotated and the lighting changes, it will reduce the recognition ability of the face extractor. The experimental results show that the proposed method can integrate multiple types of face recognition algorithms without significantly reducing the training performance. If we combine it with the static protection method, people can prevent face data from being collected.

Diagnosing Diabetic Retinopathy in OCTA Images Based on Multilevel Information Fusion Using a Deep Learning Framework.

Objective: As an extension of optical coherence tomography (OCT), optical coherence tomographic angiography (OCTA) provides information on the blood flow status at the microlevel and is sensitive to changes in the fundus vessels. However, due to the distinct imaging mechanism of OCTA, existing models, which are primarily used for analyzing fundus images, do not work well on OCTA images. Effectively extracting and analyzing the information in OCTA images remains challenging. To this end, a deep learning framework that fuses multilevel information in OCTA images is proposed in this study. The effectiveness of the proposed model was demonstrated in the task of diabetic retinopathy (DR) classification. Method: First, a U-Net-based segmentation model was proposed to label the boundaries of large retinal vessels and the foveal avascular zone (FAZ) in OCTA images. Then, we designed an isolated concatenated block (ICB) structure to extract and fuse information from the original OCTA images and segmentation results at different fusion levels. Results: The experiments were conducted on 301 OCTA images. Of these images, 244 were labeled by ophthalmologists as normal images, and 57 were labeled as DR images. An accuracy of 93.1% and a mean intersection over union (mIOU) of 77.1% were achieved using the proposed large vessel and FAZ segmentation model. In the ablation experiment with 6-fold validation, the proposed deep learning framework that combines the proposed isolated and concatenated convolution process significantly improved the DR diagnosis accuracy. Moreover, inputting the merged images of the original OCTA images and segmentation results further improved the model performance. Finally, a DR diagnosis accuracy of 88.1% (95%CI ± 3.6%) and an area under the curve (AUC) of 0.92 were achieved using our proposed classification model, which significantly outperforms the state-of-the-art classification models. As a comparison, an accuracy of 83.7 (95%CI ± 1.5%) and AUC of 0.76 were obtained using EfficientNet. Significance. The visualization results show that the FAZ and the vascular region close to the FAZ provide more information for the model than the farther surrounding area. Furthermore, this study demonstrates that a clinically sophisticated designed deep learning model is not only able to effectively assist in the diagnosis but also help to locate new indicators for certain illnesses.

Privacy protection generalization with adversarial fusion.

Several biometric privacy-enhancing techniques have been appraised to protect face image privacy. However, a face privacy protection algorithm is usually designed for a specific face recognition algorithm. When the structure or threshold of the face recognition algorithm is fine-tuned, the protection algorithm may be invalid. It will cause the network bloated and make the image distortion target multiple FRAs through the existing technology simultaneously. To address this problem, a fusion technology is developed to cope with the changeable face recognition algorithms via an image perturbation method. The image perturbation is performed by using a GAN-improved algorithm including generator, nozzles and validator, referred to as the Adversarial Fusion algorithm. A nozzle structure is proposed to replace the discriminator. Paralleling multiple face recognition algorithms on the nozzle can improve the compatibility of the generated image. Next, a validator is added to the training network, which takes part in the inverse back coupling of the generator. This component can make the generated graphics have no impact on human vision. Furthermore, the group hunting theory is quoted to make the network stable and up to 4.8 times faster than other models in training. The experimental results show that the Adversarial Fusion algorithm can not only change the image feature distribution by over 42% but also deal with at least 5 commercial face recognition algorithms at the same time.

Shielding facial physiological information in video.

With the recent development of non-contact physiological signal detection methods based on videos, it is possible to obtain the physiological parameters through the ordinary video only, such as heart rate and its variability of an individual. Therefore, personal physiological information may be leaked unknowingly with the spread of videos, which may cause privacy or security problems. In this paper a new method is proposed, which can shield physiological information in the video without reducing the video quality significantly. Firstly, the principle of the most widely used physiological signal detection algorithm: remote photoplethysmography (rPPG) was analyzed. Then the region of interest (ROI) of face contain physiological information with high signal to noise ratio was selected. Two physiological information forgery operation: single-channel periodic noise addition with blur filtering and brightness fine-tuning are conducted on the ROIs. Finally, the processed ROI images are merged into video frames to obtain the processed video. Experiments were performed on the VIPL-HR video dataset. The interference efficiencies of the proposed method on two mainly used rPPG methods: Independent Component Analysis (ICA) and Chrominance-based Method (CHROM) are 82.9 % and 84.6 % respectively, which demonstrated the effectiveness of the proposed method.

Weakly supervised training for eye fundus lesion segmentation in patients with diabetic retinopathy.

OBJECTIVE: Diabetic retinopathy is the leading cause of vision loss in working-age adults. Early screening and diagnosis can help to facilitate subsequent treatment and prevent vision loss. Deep learning has been applied in various fields of medical identification. However, current deep learning-based lesion segmentation techniques rely on a large amount of pixel-level labeled ground truth data, which limits their performance and application. In this work, we present a weakly supervised deep learning framework for eye fundus lesion segmentation in patients with diabetic retinopathy. METHODS: First, an efficient segmentation algorithm based on grayscale and morphological features is proposed for rapid coarse segmentation of lesions. Then, a deep learning model named Residual-Attention Unet (RAUNet) is proposed for eye fundus lesion segmentation. Finally, a data sample of fundus images with labeled lesions and unlabeled images with coarse segmentation results is jointly used to train RAUNet to broaden the diversity of lesion samples and increase the robustness of the segmentation model. RESULTS: A dataset containing 582 fundus images with labels verified by doctors, including hemorrhage (HE), microaneurysm (MA), hard exudate (EX) and soft exudate (SE), and 903 images without labels was used to evaluate the model. In ablation test, the proposed RAUNet achieved the highest intersection over union (IOU) on the labeled dataset, and the proposed attention and residual modules both improved the IOU of the UNet benchmark. Using both the images labeled by doctors and the proposed coarse segmentation method, the weakly supervised framework based on RAUNet architecture significantly improved the mean segmentation accuracy by over 7% on the lesions. SIGNIFICANCE: This study demonstrates that combining unlabeled medical images with coarse segmentation results can effectively improve the robustness of the lesion segmentation model and proposes a practical framework for improving the performance of medical image segmentation given limited labeled data samples.

Heart rate prediction from facial video with masks using eye location and corrected by convolutional neural networks.

Remote photoplethysmography (rPPG), which aims at measuring heart activities without any contact, has great potential in many applications. The emergence of novel coronavirus pneumonia COVID-19 has attracted worldwide attentions. Contact photoplethysmography (cPPG) methods need to contact the detection equipment with the patient, which may accelerate the spread of the epidemic. In the future, the non-contact heart rate detection will be an urgent need. However, existing heart rate measuring methods from facial videos are vulnerable to the less-constrained scenarios (e.g., with head movement and wearing a mask). In this paper, we proposed a method of heart rate detection based on eye location of region of interest (ROI) to solve the problem of missing information when wearing masks. Besides, a model to filter outliers based on residual network was conceived first by us and the better heart rate measurement accuracy was generated. To validate our method, we also created a mask dataset. The results demonstrated that after using our method for correcting the heart rate (HR) value measured with the traditional method, the accuracy reaches 4.65 bpm, which is 0.42 bpm higher than that without correction.

Instance segmentation using semi-supervised learning for fire recognition.

Fire disaster brings enormous danger to the safety of human life and property, and it is important to identify the fire situation in time through image processing technology. The current instance segmentation algorithms suffer from problems such as inadequate fire images and annotations, low recognition accuracy, and slow inference speed for fire recognition tasks. In this paper, we propose a semi-supervised learning-based fire instance segmentation method based on deep learning image processing technology. We used a lightweight version of the SOLOv2 network and optimized the network structure to improve accuracy. We propose a semi-supervised learning method based on fire features. To reduce the negative impact of error pseudo-labels on the model training, the pseudo-labels are matched by the color and morphological features of flames and smoke at the pseudo-label generation stage, and some images are screened for strong image enhancement before entering the next round of training for the student model. We further exploit the potential of the model with a limited dataset and improve the model accuracy without affecting the inference efficiency of the model. Experiments show that our proposed algorithm can successfully improve the accuracy of fire instance segmentation with good inference speed.

Design and Implementation of a Ku-Band High-Precision Blackbody Calibration Target.

Microwave radiometers can be used in human tissue temperature measurement scenarios due to the advantages of non-destructive and non-contact temperature measurement. However, their accuracy often cannot meet the needs of practical applications. In this paper, a Ku-Band high-precision blackbody calibration target is designed to provide calibration for microwave radiometers and meet the requirements of a high temperature-measurement accuracy and high temperature-measurement resolution. From a practical application point of view, the blackbody calibration target needs to have the characteristics of high emissivity and high temperature uniformity. However, previous studies on blackbody calibration targets often focused on the scattering characteristics or temperature uniformity of the calibration target separately, and thus lack a comprehensive consideration of the two characteristics. In this paper, the electromagnetic scattering model and the temperature-distribution model of the calibration target are established through the multi-physical simulation combined with the Finite Element Method. Then, according to the simulation results of the two characteristic models, the structural parameters and composition of the coated cone array are continuously optimized. In addition, to achieve high-precision temperature control of the blackbody calibration target, this paper studies three PID controller parameter self-tuning algorithms, namely, BP-PID, PSO-PID and Fuzzy-PID for the optimal parameter tuning problem of traditional PID algorithms and determines the optimal temperature-control algorithm by comparing the performance of heating and cooling processes. Then, the blackbody calibration target is processed and manufactured. The arch test system is used to validate the reflectance of the calibration target, the emissivity is calculated indirectly, and the temperature-distribution uniformity of the temperature-control panel of the calibration target is tested by a multi-point distribution method. Finally, the uncertainty of the brightness temperature of the blackbody calibration target is analyzed.

Design and Implementation of Multiband Noncontact Temperature-Measuring Microwave Radiometer.

In this paper, a multiband noncontact temperature-measuring microwave radiometer system is developed. The system can passively receive the microwave signal of the core temperature field of the human body without removing the clothes of the measured person. In order to accurately measure the actual temperature of multilayer tissue in human core temperature field, four frequency bands of 4-6 GHz, 8-12 GHz, 12-16 GHz, and 14-18 GHz were selected for multifrequency design according to the internal tissue depth model of human body and the relationship between skin depth and electromagnetic frequency. Used to measure the actual temperature of human epidermis, dermis, and subcutaneous tissue, a small and highly directional multiband angular horn antenna was designed for the radiometer front end. After the error analysis of the full-power microwave radiometer, a novel hardware architecture of the microwave interferometric temperature-measuring radiometer is proposed, and it is proven that the novel interferometric microwave radiometer has less error uncertainty through theoretical deduction. The experimental results show that the maximum detection sensitivity of the novel interferometric microwave temperature-measuring radiometer is 215 mV/dBm, and the temperature sensitivity is 0.047 K/mV. Compared with the scheme of the full-power radiometer, the detection sensitivity is increased 7.45-fold, and the temperature sensitivity is increased 13.89-fold.

Design and Implementation of a Novel Interferometric Microwave Radiometer for Human Body Temperature Measurement.

In this paper, the key technology of interferometric microwave thermometer is studied, the research can be applied to the temperature measurement of human body and subcutaneous tissue. This paper proposes a hardware architecture of interferometric microwave thermometer with 2 GHz bandwidth, in which the phase shifter is used to correct phase error and the quadrature demodulator is used to realize autocorrelation detection function. The results show that when input power is 7 dBm, the detection sensitivity can reach 176.54 mV/dBm and the temperature resolution of the microwave radiometer can reach 0.4 K. Correction algorithm is designed to improve the accuracy of temperature measurement. After correction, the phase error is reduced from 40° to 1.4° and when temperature changes 0.1 °C, the voltage value changes obviously. Step-by-step calibration and overall calibration are used to calibrate the device. Inversion algorithm can determine the relationship between physical temperature and output voltage. The mean square error of water temperature inversion by multiple linear regression algorithm is 0.607 and that of BP neural network algorithm is 0.334. The inversion accuracy can be improved by reducing the temperature range. Our work provides a promising realization of accurate, rapid and non-contact detection device of human body temperature.