243results about "Physiological signal biometric patterns" patented technology

The invention relates to the field of fatigue driving behavior analysis based on image recognition, in particular to a fatigue driving behavior feature extraction and analysis method based on image recognition, which comprises the following steps of: acquiring an initial state set of a driver in real time through an IMU (Inertial Measurement Unit), an RGB (Red, Green and Blue) camera and an MEMS (Micro Electro Mechanical System) vibration sensor, converting the initial state set into four images such as a head attitude angular velocity oscillogram, extracting image features and inputting the image features into corresponding preset models to obtain fused feature data, dynamically adjusting weights through scene context features, calculating cognitive load indexes and dividing processing modes; according to the method, multi-modal data fusion and dynamic weight adjustment are realized, the cognitive load of the driver can be accurately evaluated and graded intervention can be performed, and the driving safety is improved.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for medical condition identification. One of the methods includes obtaining visual data representing at least one body part of a subject; obtaining non-visual data that corresponds to one or more biological characteristics of the subject; providing data representing (i) the visual data and (ii) the non-visual data to one or more machine learning models, wherein the one or more machine learning models are trained to predict presence of a medical condition; obtaining an output of the one or more machine learning models that is generated based on the one or more machine learning models processing the visual data and the non-visual data; and determining presence of the medical condition for the subject using the output of the one or more machine learning models.

The invention relates to the technical field of living body fingerprint detection, and particularly discloses a living body fingerprint detection method based on multispectral and micro pulse feature fusion, which comprises the steps of signal synchronous generation, time domain alignment processing, feature matrix generation, weight dynamic adjustment, cross validation analysis, abnormal region sampling, living body model verification and living body authentication output. According to the method, the verification result is generated by synchronously collecting the multi-spectral reflection intensity and the skin displacement fluctuation sequence of the fingerprint area, dynamically adjusting the spectral absorption and pulsation track feature weight, performing cross validation to output the local abnormal area and obtain the supplementary feature data, and performing physiological coupling rule matching by using the preset living body judgment model. When three consecutive results do not conform to a living body rule, activating an anti-counterfeiting attack alarm protocol; according to the method, multispectral and micro pulse features are fused, and an environment adaptive weight mechanism is combined, so that the accuracy of living body detection is effectively improved, and the environment adaptability of a detection algorithm is enhanced.

The invention relates to the technical field of skin lesion area reconstruction, in particular to a skin lesion area reconstruction system based on multi-modal image fusion. The system comprises a deep multi-scale feature extraction module, a skin thermal anomaly feature extraction module, a hemodynamic feature extraction module, a depth and boundary feature extraction module, a skin surface feature extraction module, a fluorescence intensity distribution and morphological feature extraction module, a first feature fusion module, a second feature fusion module and a lesion area reconstruction module. According to the method, appearance, heat, blood flow, structure and surface features are extracted from the multi-modal data, then the multi-modal image data are integrated, finally, comprehensive representation and reconstruction of skin lesion appearance, function and structure information are achieved according to the synergistic effect of the multi-modal information, and the accuracy and clinical reference value of lesion area reconstruction are effectively improved.

A system comprises a video capture module to acquire a video, a preprocessing module to enhance video quality and isolate regions of interest within the video, and a biometric data extraction module using remote photoplethysmography to extract heartbeat and SpO2 levels from the video. A machine learning module analyzes the extracted biometric data for liveness and deepfake detection, a verification module to compare the analyzed data against known biometric signatures, and a user interface to display analysis results and alerts.

An active chatbot system with behavioral awareness and on-demand conversation and a method thereof are disclosed. In the active chatbot system, a client-end host continuously senses a client behavior state, and transmits the sensed client behavior state and an on-demand conversation setting to a server-end host to generate a rough question message having a natural language structure, and input the rough question message to a plurality of finite state machines to generate a precise question message. The server-end host transmits the precise question message to an artificial intelligence platform to obtain a corresponding answer message, stores the answer message to an answer list, filters out an answer message matching the on-demand conversation setting as an on-demand conversation message, transmits the on-demand conversation message to the client-end host for output. Therefore, the technical effect of improving human-computer interaction and initiative of chatbot can be achieved.

The invention relates to the technical field of operator safety management, and discloses a non-contact physiological status rapid screening method and system and a medium, and the method comprises the steps: collecting an RGB three-channel space-time image sequence of a facial region of interest; carrying out illumination correction on the RGB three-channel space-time image sequence by adopting an adaptive gamma correction algorithm, carrying out end-to-end noise reduction processing on the illumination correction image sequence by utilizing a one-dimensional convolutional neural network auto-encoder noise reduction algorithm, and separating a remote photoelectric volume pulse wave tracing pulse signal; calculating physiological indexes of heart rate, heart rate variability and oxyhemoglobin saturation based on the remote photoplethysmography pulse signal; and performing grading judgment on the physiological indexes based on the physiological index grading standard, determining a final post suitability judgment grade in combination with the wooden barrel effect model, and generating a grading early warning signal. According to the method, accurate and rapid evaluation of the physiological state of the operator in a complex environment can be realized, the individual health degree can be comprehensively and objectively considered, and decision support is provided for reasonable distribution of posts and efficient configuration of personnel.

The invention relates to the technical field of automatic identification of animal behaviors, in particular to an automatic identification method for pulmonary respiration behaviors of giant salamanders, and the method comprises the steps: obtaining an initial video image of a target region; preprocessing the initial video image to obtain a standard video image; performing feature enhancement on the standard video image to obtain an enhanced feature image; performing multi-scale respiratory behavior feature extraction on the enhanced feature image to obtain depth feature maps of different scales; performing multi-level feature aggregation on the depth feature maps of different scales, and generating an aggregated feature map; and generating an identification result based on the aggregated feature map. According to the method, the problems that the omission ratio of manual monitoring of the breathing behavior in a night low-contrast scene is high and long-term efficient and objective monitoring is difficult to realize due to night walking and cave habits of the giant salamander are solved.

The invention provides a registration method and device in a cardiac surgery and computer equipment, which are used for improving the safety and accuracy of the surgery. The registration method comprises the following steps: acquiring an electrocardiosignal and multi-modal physiological data of a surgical patient, and performing cardiac time phase division on a cardiac cycle based on the electrocardiosignal and the multi-modal physiological data; collecting multi-angle image data of the heart under each cardiac time phase, and synchronously collecting physiological parameter data; performing three-dimensional reconstruction based on the multi-angle image data corresponding to each cardiac time, and mapping the physiological parameter data corresponding to each cardiac time to a corresponding three-dimensional reconstruction result to obtain a multi-temporal three-dimensional heart model library; the method comprises the following steps: acquiring real-time electrocardiosignals and real-time multi-modal physiological data of a surgical patient in a surgical process to identify a current cardiac time phase, selecting a current time phase three-dimensional heart model from a multi-time phase three-dimensional heart model library according to the current cardiac time phase, and performing surgical registration by using the current time phase three-dimensional heart model.

The invention relates to an electronic device which comprises a substrate, a pixel, a second sensing unit, a first driving unit and a second driving unit. Each pixel comprises a display unit and a first sensing unit, and the display unit comprises a self-luminous element. The second sensing unit overlaps at least one of the pixels. In the first mode, the first driving unit outputs a first signal to the display unit. In the second mode, the first driving unit outputs a second signal to the second sensing unit, receives a third signal from the second sensing unit, and outputs a fourth signal to the second driving unit according to the third signal. In the third mode, the second driving unit outputs a fifth signal to the first sensing unit according to the fourth signal, and the first sensing unit returns a sixth signal to the first driving unit.

The invention discloses a video pulse wave extraction method and system based on automatic noise recognition. The method comprises the steps that a face area is divided into a plurality of sub-areas; calculating the signal-to-noise ratio of each sub-region in the pulse frequency band, and performing weighted fusion on the original pulse signals of each sub-region according to the signal-to-noise ratio; performing ensemble empirical mode decomposition on the fusion signal; according to the peak-to-peak interval variation coefficient, the amplitude stability index and the spectrum purity, determining a noise component dominated by the motion artifact; performing adaptive filtering processing on the fused signal by using an adaptive filter and taking a reference noise signal as input; carrying out distortion detection on the filtered fusion signal, and carrying out signal restoration processing on a detected distortion region to obtain an extracted pulse signal; in order to solve the problem that in the prior art, when video pulse signals are extracted, motion artifacts and physiological signal frequency spectrums are overlapped, and consequently signal separation of a traditional frequency domain filtering method fails, effective signal separation and accurate pulse signal extraction are achieved.

In embodiments, a method for configuring an intelligent agent to do a task based on spatial-temporal magnetic imaging data of the brain of a worker is disclosed. The method includes generating a brain region parameter indicating an active neocortex region associated with visual processing during performance of the task based on the spatial-temporal magnetic imaging data. The method further includes selecting a convolutional neural network (CNN) component type in response to a match between the brain region parameter and an associated CNN component type. The method includes configuring the intelligent agent based on the selected CNN component and a neocortical processing flow parameter derived using the spatial-temporal magnetic imaging data, wherein the intelligent agent is configured to process image data using the CNN component and provide an output of the CNN to another AI component via a data connection created based on the neocortical processing flow parameter.

An integrated artificial intelligence camera system provides multi-domain monitoring and enterprise automation from a single hardware endpoint. A camera assembly and auxiliary sensors, including at least one of depth, thermal, audio and environmental sensors, feed an edge compute module executing modular perception, identity, physiological estimation and domain-logic pipelines. The system detects and tracks persons, objects and activities; generates pseudonymous identity tokens for enrolled workers; estimates breathing rate and related wellness indicators from non-contact visual and thermal signals; and transforms these outputs into normalized event records annotated with security, inventory, workforce, payroll, physiological and compliance labels. A unified event model standardizes timestamps, device identifiers, site and zone identifiers, actor identifiers, metrics, confidence scores, policy tags and evidence references, enabling direct integration with payroll, inventory management, security incident and analytics platforms. A policy engine governs feature activation, anonymization and retention per jurisdiction and user role.

The invention relates to the technical field of image processing, and discloses a facial health state assessment method and system based on layered optical modeling. The objective of the invention is to solve the problems of poor face health state evaluation precision and robustness caused by rough optical modeling, mixed reflection components, weak environmental adaptability and insufficient multi-dimensional health index fusion capability in the prior art. The method comprises the following steps: synchronously acquiring a user face video sequence comprising at least two different spectral bands through a multispectral imaging device; constructing a multilayer optical transmission model of the skin tissue, and separating a specular reflection component and a diffuse reflection component from the face video sequence; extracting a physiological time sequence signal related to subcutaneous blood flow activity from the separated diffuse reflection component, and calculating heart rate, heart rate variability and blood oxygen saturation parameters; and fusing the physiological parameters and expression and micro-expression features extracted from the facial video sequence, and outputting quantitative evaluation results of fatigue degree, pressure level and emotional state through a pre-trained deep neural network model. The system comprises a multispectral image acquisition module, a layered optical modeling module, a reflection component separation module, a physiological parameter inversion module and a health state evaluation module. According to the technical scheme, the signal-to-noise ratio and stability of physiological signal extraction in a complex illumination environment can be remarkably improved, the adaptability to individuals with different skin colors and dynamic illumination conditions is enhanced, and more accurate and more robust judgment of the high-order health state is achieved.

This invention discloses a Tai Chi movement recognition method based on multi-rate compressive convolution. First, electromyographic (EMG) data of Tai Chi movements is collected and preprocessed. Then, temporal features of the source signals are extracted to construct a feature matrix. A multi-rate compressive convolution algorithm is used to extract cross-channel compressed feature sequences, which are then fused to obtain a multi-dimensional fused feature matrix. Temporal relationship features are then obtained through a long short-term memory (LSTM) network. Finally, a fully connected layer is used to obtain the movement recognition result, thus completing the Tai Chi movement recognition. This invention achieves multi-scale cross-channel feature extraction of EMG signals through multi-rate dilated convolution, overcoming the limitation of ordinary convolution which can only extract spatial relationships between adjacent channels. It can compress the information contained in EMG signal sequences of arbitrary sizes into a one-dimensional compressed feature sequence to extract highly fused features, reducing data redundancy, the number of parameters, and model computation, thereby improving the accuracy of Tai Chi movement recognition.

The invention relates to the technical field of artificial intelligence, and discloses a palm vein recognition method and device based on human anatomy, equipment and a medium, and the method comprises the steps: obtaining a palm vein image sequence of a user; carrying out anatomical key point positioning processing on the palm vein image sequence to obtain anatomical key point coordinates of the palm vein image sequence; according to the anatomical key point coordinates, carrying out geometric correction processing on an ROI region of the palm vein image sequence to obtain a standardized ROI region sequence; performing multi-modal feature extraction processing on the standardized ROI region sequence to obtain vein texture features and hemodynamic features; and performing cross-modal fusion processing on the vein texture features and the hemodynamic features to obtain palm vein fusion features. According to the invention, the recognition rate and safety of palm vein recognition can be improved.

According to various embodiments, there is provided an operation method of an electronic device including: acquiring a plurality of images of a user, captured by an RGB camera of the electronic device, acquiring a specific area on a specific body part of the user from the plurality of images, generating a plurality of first data associated with an RGB color model on the specific area associated with the plurality of images, generating a plurality of second data associated with a YCrCb color model based on the plurality of first data, generating first time-series data associated with a green channel based on the plurality of first data; generating third time-series data based on combining the first time-series data and the second time-series data; and estimating a pulse of the user based on conversion of the third time-series data into a frequency domain.

The invention discloses a target state parameter determination method and device, a storage medium and an electronic device, and relates to the technical field of smart home, and the target state parameter determination method comprises the steps: obtaining a target face video stream of a target object outputted by an image collection module, obtaining a light supplementing state signal output after the light supplementing module supplements light to the space where the target object is located; determining a light supplement condition corresponding to each frame of image in the target face video stream according to the light supplement state signal, and determining a reference light intensity offset of a forehead area and a nose root area in each frame of image according to the light supplement condition corresponding to each frame of image; and according to the reference light intensity offset of the forehead region and the nose root region in each frame of image, pixel-by-pixel correction is performed on the pixel brightness value of each frame of image to obtain a corrected video stream, and a target state parameter of the target object is determined according to the corrected video. By adopting the technical scheme, the problem that the state parameters of the target object cannot be accurately determined is solved.

An electronic device includes a substrate, pixels, a second sensing unit, a first driving unit and a second driving unit. Each pixel includes a display unit including a self-luminous element and a first sensing unit. The second sensing unit overlaps at least one of the pixels. In a first mode, the first driving unit outputs a first signal to the display unit. In a second mode, the first driving unit outputs a second signal to the second sensing unit, receives a third signal from the second sensing unit, and outputs a fourth signal to the second driving unit according to the third signal. In a third mode, the second driving unit outputs a fifth signal to the first sensing unit according to the fourth signal, and the first sensing unit transmits a sixth signal to the first driving unit.

A contactless patient monitoring system (10) includes a first imager (12) configured to capture first image data (14) of a target area (16) within a first field of view (18). A second imager (20) is operably coupled to the first imager (12). The second imager (20) is configured to capture second image data (22) of the target area (16) within a second field of view (24). An emitter (26) is operably coupled to at least one of the first imager (12) and the second imager (20). The emitter (26) is configured to emit light (28) within a predetermined wavelength range. A controller (30) is communicatively coupled to the first imager (12), the second imager (20), and the emitter (26). The controller (30) is configured to determine a facial region (32) of a person in the first image data (14), determine a region of interest (34) in the second image data (22) that coincides with the facial region (32) in the first image data (14), and determine a coordinate (X, Y) of a head position (36) within the facial region (32).

The application discloses a kind of vehicle biological invasion intelligent monitoring methods based on multi-sensor fusion, it is related to vehicle-mounted intelligent safety monitoring and response technical field, including the multi-modal data of vehicle key area is synchronously collected by sensor, and pretreatment is carried out, obtain the multi-modal data after pretreatment;Feature extraction is carried out to the multi-modal data after pretreatment, extract frequency domain feature vector, voiceprint matching degree and vibration energy increment, and the confidence index of biological invasion is comprehensively calculated;According to confidence index stratified trigger response strategy, complete the vehicle biological invasion intelligent monitoring and response based on multi-modal perception.The application significantly improves the detection sensitivity and identification accuracy of small biological invasion in vehicle key area;Give consideration to low-power on-line operation and real-time protection needs, and reduce false alarm and miss risk by stratified response.

According to a first aspect of the present disclosure, there is provided a user authentication apparatus comprising: a face recognition unit configured to receive a visual input and extract a biometric marker from the visual input, the biometric marker being a face; a user identification unit configured to identify a user based on the biometric marker extracted by the face recognition unit; and an activity detection unit configured to detect whether the user identified by the user identification unit is a living person by extracting one or more additional biometric markers from the visual input received by the face recognition unit. According to other aspects of the present disclosure, a corresponding method of operation is conceived and a computer program for performing the method is provided.

There is provided a device for acquiring biometric electrical signals comprising at least two electrodes. The device also comprises a current supply comprising a direct current supply, an alternating current supply, and a switch actuatable to switch selectively between the direct current supply and the alternating current supply. The device further comprises a capacitive coupling to couple each electrode to the current supply, a direct coupling to couple each electrode to the current supply, and a switch actuatable to switch selectively between the direct coupling and the capacitive coupling. The device also comprises a data acquisition module.

The application discloses a kind of based on face video's space-time field weighting photoelectric volume pulse wave recovery method, the model involved mainly includes signal extraction, signal quality score and signal enhancement three modules.First face video is detected and cut to face, obtain only containing face video as input;Signal extraction module calculates the frame difference graph of input, to extract spatial domain weight from input feature with weighting, from spatial domain attention face non-motion area, and further from the weighted signal, preliminary extraction is carried out to pulse wave signal;Signal quality score module is segmented to pulse wave signal score;Signal enhancement module assigns higher attention weight value to the signal section with low score, from time domain attention signal quality poor part, output recovered high-quality pulse wave signal.The application can alleviate the motion interference in imaging photoelectric volume pulse wave tracing method, extract effective signal from time domain and spatial domain, provide high-quality pulse wave signal for subsequent physiological parameter estimation.

The invention discloses a heart multi-modal image feature extraction method and device, equipment, a medium and a product, and relates to the technical field of medical image processing, and the method comprises the steps: obtaining multi-modal heart image data, patient information and case information in a multi-center imaging department and an ultrasound department; labeling the multi-modal heart image data, and constructing a multi-modal iconography feature database; establishing a database platform comprising a server storage control terminal and a data screening and uploading terminal; opening a communication link after verifying the identity of the requester; training is carried out based on the marked multi-mode heart data and a deep learning algorithm so as to obtain heart structure features of heart ultrasound and nuclear magnetic images through coronary angiography (CCTA) image data; finally, the system is deployed and applied clinically. According to the method, the heart structure features of the other two modal images are predicted based on the single-modal CCTA image data, the diagnosis range based on the CCTA image data is expanded, the medical overhead is saved, and the diagnosis and treatment efficiency and accuracy are improved.

A device of the subject technology comprises a extra-reality (XR) headset including a processor configured to execute machine-learning (ML) instructions, memory configured to store a first set of data and a communications module configured to access a cloud storage including a second set of data. The ML instructions are configured to train an artificial-intelligence (AI) model to infer facial expressions based on at least one of the first set of data or the second set of data.

The embodiment of the invention relates to the technical field of pulse diagnosis, and discloses a pulse analysis method based on a pulse diagnosis instrument, which comprises the following steps: processing a pressure change signal within a set time to obtain an original pulse waveform signal associated with a user; performing high-frequency denoising processing on the first pulse frequency signal according to a set noise threshold value; acquiring all wavelet coefficients associated with the high-frequency detail signal, traversing all the wavelet coefficients, determining that the absolute value of the wavelet coefficient at a certain point is greater than the absolute value of the wavelet coefficient adjacent to the wavelet coefficient, and taking the wavelet coefficient as a signal abrupt change point; generating a corresponding pulse image of the user based on the pulse condition data of the user within a set time range; and inputting the obtained pulse condition graph of the user into a pre-constructed standard pulse condition model to determine a pulse condition type result of the user, and outputting the pulse condition type result of the user. According to the scheme provided by the embodiment of the invention, the user can conveniently, quickly and accurately know the pulse condition and the physique state of the user, and the use convenience is improved.

The present disclosure presents a Multi-Input, Multi-Output artificial intelligence system that jointly processes video with other physiological signals during training to uncover shared representations across modalities and prevent the mislearning observed in existing methods. Once trained, the system requires video input at inference, yet remains capable of reconstructing physiological signals learned during training. By leveraging these crossmodal patterns, the system can use video alone to estimate complex signals such as blood pressure. This integration of video with complementary vital features during training therefore provides a pathway toward accurate, contactless estimation of a broad range of vital signs. A method for estimating vital features of a patient is provided. The method includes receiving a video segment showing a skin-exposed region of the patient, cropping the video segment, and estimating vital features by providing the crops as input to a neural network.

The invention discloses a feature fusion method for intelligent identification of a pulmonary valve stenosis echocardiogram, and belongs to the technical field of medical image analysis and artificial intelligence, and the method comprises the steps: obtaining an echocardiogram video of a pulmonary valve, carrying out the automatic identification of a standard section, and obtaining a key frame sequence corresponding to a target anatomical structure; acquiring a Doppler spectrum image of the pulmonary valve, and obtaining a target spectrum image through target screening processing; according to the key frame sequence and the target spectrum image, obtaining fusion features through cross-modal joint feature extraction and feature fusion; and according to the fusion features, obtaining an identification result of the pulmonary valve stenosis, and generating a corresponding key region attention heat map to be displayed on the original Doppler spectrum image. The method provided by the invention provides objective and consistent quantitative analysis support for ultrasonic inspection, and is beneficial to improving the efficiency of the whole working process and the standardization level of an analysis result.