33 results about "Blink detection" patented technology

The embodiment of the invention relates to the technical field of image processing, and discloses a blink detection method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: obtaining a plurality of frames of eye images; identifying the multiple frames of eye images to obtain eye parameters respectively corresponding to the multiple frames of eye images, the eye parameters including one or more of an eye angle parameter, a first distance ratio and a second distance ratio, the eye angle parameter is determined according to an inner angle of a quadrangle formed by the upper eyelid feature point, the lower eyelid feature point, the inner canthus feature point and the outer canthus feature point, the first distance ratio is determined according to a first distance between the upper eyelid feature point and the lower eyelid feature point and the cornea width, and the second distance ratio is determined according to the first distance and the second distance between the upper eyelid feature point and the lower eyelid feature point. And a second distance between the inner canthus feature point and the outer canthus feature point; and determining blinking information according to the eye parameters respectively corresponding to the plurality of frames of eye images. By implementing the embodiment of the invention, the accuracy of the determined blink information can be improved.

The invention discloses a living body detection method and system for a facial paralysis patient and a medium. The method comprises the following steps: acquiring a detection video of a user; face key point detection is carried out on each frame of image in the detection video, calculation is carried out based on a detection result, and an eye width-to-height ratio and a mouth width-to-height ratio corresponding to each frame of image are determined; performing independent blink detection on each eye based on a preset eye opening threshold and an eye width-to-height ratio corresponding to a plurality of frames of images in the video; performing mouth opening detection based on the mouth opening threshold and the mouth width-to-height ratio corresponding to each frame of image; the mouth opening threshold value is obtained by adjusting a preset mouth opening threshold value according to an average mouth width-to-height ratio of a plurality of previous continuous frame images in the detection video; and determining a living body detection result of the user according to the blink detection result and the mouth opening detection result. According to the embodiment of the invention, the living body detection passing rate of the facial paralysis patient can be effectively improved, and the method can be widely applied to the technical field of face recognition.

The invention relates to a data evaluation method and device based on artificial intelligence, computer equipment and a medium, and is suitable for smart televisions, laptops, projectors, tablet personal computers and the like, and the method comprises the following steps: collecting video streams related to a user, and obtaining environment illumination intensity; performing face key point detection on the video stream to obtain key point information; performing blink detection and frequency calculation based on the key point information to obtain a blink frequency; performing head posture estimation on the key point information, and calculating continuous fixation duration based on a posture estimation result; generating a watching distance of the user to the screen of the target equipment; integrating the environment illumination intensity, the continuous fixation duration, the blinking frequency and the watching distance to obtain index data; evaluating the face image of the user, and obtaining a target index threshold value based on the target age; and performing data evaluation on the index data based on the target index threshold to generate a health evaluation result. According to the invention, the accuracy of health assessment processing of eye using behaviors is improved.

Example embodiments of the present disclosure relate to a terminal device, a network device, methods, apparatuses and a computer readable storage medium for UCI transmission. In the solution, a terminal device may obtain information indicating whether a first PUSCH is capable of carrying a UCI in case the first PUSCH is overlapped with a PUCCH that is intended to carry the UCI. The terminal device may transmit the UCI being multiplexed on the first PUSCH if the first PUSCH is capable of carrying the UCI. Since the information is agreed upon at both the network side and the terminal device, the network device can determine the UCI from the first PUSCH without blink detection. As a result, the transmission efficiency of the UCI can be improved.

The invention relates to a blink detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring an initial blink detection result of a face image sequence and a target intersection point corresponding to a face image, wherein the target intersection point is used for representing the change degree of a target face key point in a blink process; determining an average distance corresponding to each face image according to the target intersection point and each target eye key point in the face key point set; performing distance dispersion degree calculation on the average distance corresponding to each face image to obtain a distance dispersion degree corresponding to the face image sequence; and obtaining a blink detection result of the face image sequence based on the initial blink detection result and the distance dispersion degree. By adopting the method, resources can be saved, and the blink detection robustness can be improved.

The invention discloses a BCI method and system based on EOG autonomous rehabilitation, and the method comprises the steps: constructing a graphical user interface comprising button flickering visual clues and corresponding upper limb motion types, enabling all buttons to flicker circularly according to a set time interval, and enabling a user to select a target motion function through synchronous blinking and then stop flickering; the method comprises the following steps: acquiring an EOG signal when a user blinking through a wearable BCI device, and synchronously marking a motion type corresponding to button flickering to form motion intention information; a decision control unit is optimized based on the threshold parameter obtained in the calibration stage, EOG signal features are extracted by using the optimized decision control unit, and a blinking event corresponding to button blinking is detected; a target button function is recognized according to the blink detection result, and a control instruction corresponding to upper limb rehabilitation exercise is generated and sent to the lower computer; the lower computer receives the instruction, drives the motor to execute rehabilitation actions, and assists the user in completing upper limb joint and muscle function training.

Devices and methods are provided that facilitate proximity or liveness detection of a user of a wearable device or a user interacting with a device based on ultrasonic information. In various embodiments, machine learning classifier models can be employed to generate classification predictions of a donned or a doffed state of a wearable device. Further embodiments can facilitate eye blink detection and / or classification based on machine learning classifier models of ultrasonic transceiver information, which can facilitate, among other things, user interface control of wearable devices and associated applications and systems.

A method, system, and computer readable medium for switching between motion tracking mode. The method includes detecting a significant change in confidence level for motion tracking. A change from a first tracking mode to a second tracking mode is initiated when a significant change in confidence level is detected and the change is paused until a saccade or blink is detected. by eye tracking device. After a saccade or blink is detected the tracking mode switches from the first tracking mode to the second tracking mode.

The invention relates to the technical field of computer vision processing, in particular to an online education video behavior analysis and early warning system fusing facial expression and eye movement parameters, which comprises a video data acquisition and preprocessing module, a video data processing module, a video data processing module and a video data processing module, and extracting a video frame sequence, a face key point, a head posture parameter and an eye region image. According to the invention, video data of students are collected through a camera, blink detection and original frequency calculation are carried out in sequence, a posture and image quality joint evaluation module is introduced innovatively, and multi-dimensional quality scoring is carried out on collection conditions. And performing quality correction on the blink frequency based on the score, and eliminating the individual difference influence of the user in combination with an individual baseline modeling and self-adaptive correction module. And finally, performing time sequence integration and behavior analysis on the effective data to realize accurate early warning of the fatigue state of the student. And the problem of analysis distortion caused by image quality fluctuation and individual difference is effectively solved.

The embodiment of the invention is applied to the technical field of terminals, and provides a blink detection method and electronic equipment. The electronic device collects a plurality of first image frames in a first time period. Afterwards, the electronic equipment counts the number of blinking times and the watching duration proportion in the first time period according to the multiple first image frames; wherein the watching duration proportion is used for representing the duration proportion condition of continuously watching the display screen by the user. And then, when the number of blinking times is smaller than the preset number of times and the watching time length proportion is larger than the preset time length proportion, the electronic equipment outputs blinking prompt information. Wherein the blink prompt information is used for reminding the user to blink. According to the invention, the user can be reminded to use eyes normally in time.

Provided in the embodiments of the present application are a blinking guidance method, a method for updating a screen display parameter, and an electronic device. In the blinking guidance method, after the current operating state of an electronic device is acquired, when the current operating state of the electronic device satisfies a first predetermined state, the electronic device performs blinking measurement on a user who uses the electronic device, so as to obtain a blinking frequency of the user; and when the blinking frequency of the user is less than or equal to a blinking threshold value, the electronic device performs blinking guidance on the user, such that when the blinking frequency of the user is relatively low, the user is prompted to appropriately blink, thereby improving the stability of a tear film, and relieving dry eyes and visual discomfort.

The present application belongs to the technical field of face detection. Disclosed are a blink detection method, an apparatus, a device and a medium. The method comprises: performing face key point detection on each face image frame in a face image sequence; calculating eye aspect ratios of the corresponding frames on the basis of a face key point set, and enabling the eye aspect ratios of all the frames to constitute an eye aspect ratio sequence; filtering the eye aspect ratio sequence to obtain a denoised aspect ratio sequence; normalizing the denoised aspect ratio sequence to obtain a normalized aspect ratio sequence; performing trough detection on the normalized aspect ratio sequence to obtain a trough set; calculating the gradient of the normalized aspect ratio sequence, and, on the basis of the gradient of the normalized aspect ratio sequence, filtering the trough set to obtain a plurality of target troughs; and calculating a starting moment and an ending moment corresponding to each target trough, and determining blink actions on the basis of the starting moments and the ending moments. The described method can more accurately determine blink actions, reducing the probability of missed detection and false detection.

Providing runtime power profile tuning based on eye state in a processor-based augmented reality (XR) device is disclosed herein. In this regard, in some exemplary aspects, a processor of a processor-based XR device is configured to apply a default power profile and to detect eye closing events of a user of the processor-based XR device using a blink detection circuit. In response to detecting the eye closing event, the processor selects a test power profile from a plurality of power profiles and applies the test power profile. The processor then measures an operational characteristic of the processor-based XR device and compares the operational characteristic to a corresponding reference range. Based on the comparison, the processor updates one or more of the plurality of power profiles.

The invention relates to a blink detection method and device based on continuous frames and electronic equipment, and belongs to the technical field of intelligent cabin perception, and the detection method comprises the steps: obtaining an eye state value of each frame in a preset number of continuous frames through a single-frame eye state value algorithm, obtaining an eye state change curve according to the eye state value of each frame in the preset number of continuous frames, and determining whether to blink according to the eye state change curve; according to the method, whether blinking occurs or not is judged through the eye state change curve, the blinking process from eye closing to eye opening is concerned, false detection caused by the sizes of the eyes of the driver is effectively reduced, and the accuracy of blinking detection and fatigue driving detection is improved.

To provide a patient guiding trigger of measurement for an ophthalmic diagnostic device.SOLUTION: A system and method for tracking a position and state of an eye during an ophthalmic procedure include: an ophthalmic device configured to measure characteristics of the eye; an eye tracker configured to capture a stream of images of the eye; and a logic device configured to analyze the stream of images to determine whether or not the eye is fixating on a target object, detect a predetermined blink sequence in a first stream of images, delay a predetermined tear stabilization period, initiate a stable tear film interval, and capture at least one measurement result of the eye with the ophthalmic device when the eye is fixating during the stable tear film interval. The blink sequence may include a plurality of continuous blinks, and detection of the blink sequence may include processing of the image through a neural network trained to detect open and / or closed eyes.SELECTED DRAWING: Figure 2

The embodiment of the invention provides a blink detection method, electronic equipment and a storage medium, and relates to the technical field of data processing, and the method comprises the steps: recognizing an eye region of a target object in each image contained in a target image sequence; according to the eye area in each image, a multi-modal result reflecting whether a complete blink event occurs from multiple dimensions is obtained through detection, and the complete blink event is that the target object blink in an image acquisition time period corresponding to the target image sequence; fusing each single-mode result in the multi-mode result to obtain a fusion result; and determining whether the target object blink or not according to the fusion result. By applying the scheme provided by the embodiment of the invention, the accuracy of blink detection can be improved.

The invention discloses a non-contact blink detection method and system based on a video stream, and the method comprises the steps: 1, capturing an eye video image sequence of a user in real time, calculating the average gray value of the ROI of the left eye and the right eye in each frame of image, and forming a gray value data sequence of the left eye and the right eye; step 2, maintaining a data sequence in a sliding window with a fixed length L for the gray value data sequences of the left eye and the right eye; step 3, on the basis of the threshold parameter of the selected threshold mode, traversing the data sequence in the sliding window obtained in the step 2, determining an effective blink wave crest, and calculating the normalized depth of the effective blink wave crest; and 4, for the normalized decline depth of the effective blink wave crest calculated in the step 3, carrying out joint judgment by adopting a double-threshold mechanism so as to judge a blink event. The method solves the problems that a blink detection mode is extremely sensitive to the change of ambient light, so that misjudgment is easily caused, the ability of identifying the complete form of a blink signal is lacked, and the robustness is poor.

The application discloses an eye blinking detection method and system, a wearable device, and a computer readable storage medium. The method comprises: collecting an electromyography signal of an eye region of a user; detecting an eye blinking event based on the electromyography signal; in a first detection state, when an eye blinking event meeting a first interaction judgment condition is detected, identifying the eye blinking event as an interaction eye blinking event, and outputting a corresponding human-computer interaction instruction; in a second detection state, only when an eye blinking event meeting both the first interaction judgment condition and a second interaction judgment condition is detected, identifying the eye blinking event as an interaction eye blinking event, and outputting a corresponding human-computer interaction instruction; when the first detection state is currently used, after detecting an eye blinking event not meeting the first interaction judgment condition, switching to the second detection state. The application can improve the interaction judgment threshold when natural blinking occurs frequently, inhibit the interference of natural blinking on human-computer interaction, and improve the reliability in the human-computer interaction process.

Embodiments of the present disclosure disclose an eye tracking device-based attention state display method, device and equipment. A specific embodiment of the method comprises: controlling a virtual reality head-mounted display device embedded with an eye tracking device to collect an eye image sequence; performing pupil detection on the eye image sequence to obtain a pupil information sequence; inputting the eye image sequence into an attention fixation network model to obtain a fixation line of sight information sequence; generating a fixation point information sequence; performing blink detection processing on the eye image sequence to obtain a blink frequency information sequence; generating attention state information; visually displaying the attention state information; and sending and visually displaying the eye image sequence, the fixation point information sequence and a user attention image. The embodiment can improve the accuracy and real-time performance of attention state detection, prolong the service time of the device and improve the user experience by using a low-power head-mounted display device that is compatible with a large field of view and experience.

The invention discloses a blink fatigue detection method and system based on deep learning, and the method comprises the steps: obtaining an eye image data set with an eye opening and closing state label, carrying out the preprocessing, and dividing a training set, a verification set, and a calibration data set; performing training and performance verification on the convolutional neural network model by using the training set and the verification set to obtain a blink detection model; the calibration data set is used for conducting INT8 quantification processing on the blink detection model, and the blink detection model is converted into a light-weight blink detection model and then deployed to an embedded device; taking a continuous video frame sequence which is acquired by a camera in real time and contains a face image as input data of a lightweight blink detection model for detection, and obtaining an effective blink frequency; the number of effective blinking times is counted, the blinking frequency in unit time is calculated, the blinking frequency is compared with a preset multi-level fatigue level threshold value level by level to determine the corresponding fatigue level, and whether the user is in a fatigue state or not is judged. According to the invention, blink fatigue detection can be efficiently and accurately carried out on low-power-consumption equipment.

The embodiment of the invention provides a blink guiding method, a screen display parameter updating method and electronic device.In the blink guiding method, after the current running state of the electronic device is obtained, when the current running state of the electronic device conforms to a first preset state, the electronic device carries out blink detection on a user using the electronic device, and the screen display parameter updating method is used for updating the screen display parameter. And obtaining the blinking frequency of the user. When the blinking frequency of the user is smaller than or equal to the blinking threshold value, the electronic equipment guides blinking of the user, so that when the blinking frequency of the user is low, the user is prompted to blink properly, the tear film stability is improved, and eye dryness and visual discomfort are relieved.

This disclosure relates to the field of terminal control, specifically to an eye state detection method, device, wearable device, and storage medium. The eye state detection method includes: continuously collecting the wearer's periocular electromyography (EMG) signals and corresponding actual posture information during wearable device operation; determining the wearer's wearing displacement state based on a comparison of the actual signal characteristics of the periocular EMG signals with preset reference EMG signal characteristics, and / or the actual posture information; if a wearing offset is determined, correcting blink detection parameters or eye movement detection parameters based on the current periocular EMG signals; and performing eye state detection on the wearer based on the corrected blink detection parameters or eye movement detection parameters. It can autonomously trigger the correction of blink detection parameters or eye movement detection parameters without human intervention, effectively ensuring the wearable device's responsiveness and system stability.

The invention relates to the technical field of computer vision, in particular to a face recognition method and system applied to life payment. Through multiple living body detection mechanisms, including blink detection and light reflection detection, it is ensured that the system can accurately distinguish a real person from a fake face image or video, the false face image generated by AI is effectively prevented from cheating the system, and therefore the safety of the face recognition system is improved; deep feature extraction is performed on the facial image by using the convolutional neural network, so that high-dimensional facial features can be extracted from the image, and a unique identity identifier is generated. The method not only has high accuracy, but also can ensure the stable operation of the system in various environments and provide rapid and accurate identity verification. And providing personalized life payment authority for the user based on the facial recognition result. Through comparison of the user identity identifiers, the system carries out accurate matching and grants corresponding payment authority to the user according to a comparison result.

An eye blink detection method and system are disclosed. The eye blink detection method comprises: photographing a face using a DVS camera to obtain a stream of DVS pixels; integrating DVS pixels of the stream of DVS pixels to form a plurality of DVS frames, wherein each of the plurality of DVS frames comprises a plurality of first and second color pixels, each being associated with one or more DVS pixels indicating a brightening event and each of the second color pixel being associated with one or more DVS pixels indicating a darkening event; and determining whether there exists an eye blink action in a DVS frame of the plurality of DVS frames, wherein the determining comprises: determining whether there exists a pattern in which a first and second color region are distributed one above the other in an eye region of the at least one DVS frame.

The application discloses a fatigue detection method and system based on eye aspect ratio change rate, and relates to the field of video image processing, and solves the problem that the existing fatigue detection technology excessively relies on blink detection, leading to inaccurate detection; the application comprises the following steps: S1, collecting driver video information and processing the information into pictures frame by frame; S2, removing glasses and glasses shadows in the pictures frame by frame by using a glasses removal algorithm; S3, synthesizing the pictures processed in S2 into a video frame by frame, detecting a face region in the video by using dlib, identifying key points of the face in the face region, and calculating an average value of a single frame eye; and S4, judging an eye fatigue state by using a unit time average value change rate of the eye in combination with a fatigue degree early warning index; the application continuously judges the fatigue degree by using the average value change rate of the eye changing with time, and predicts a blink frame parameter by using a regression function, so that the change rate is not affected by different blink habits of different people.

A method for recognizing blink and eye movement based on electroencephalogram (EEG) and a system thereof are disclosed. The method includes measuring a subject's EEG-based electrooculogram (EOG) signal (hereinafter referred to as “EOG signal”) using three electrodes connected to an EEG head cap. The method further includes performing potential blink detection and zero crossing detection using the EOG signal, and generating a plurality of parameters used for blink and eye movement classification using the EOG signal depending on presence or absence of the potential blink and the zero crossing. In addition, the method further includes classifying the blink and up / down / left / right eye movements of using the plurality of parameters.

The application provides an eye blinking detection method and device based on a dynamic threshold, equipment and a storage medium. The eye blinking detection method based on the dynamic threshold comprises the following steps: S1, acquiring an electromyographic signal set; the electromyographic signal set comprises electromyographic signals of an eye region of a user corresponding to a current time window and / or at least one time window before the current time window; S2, extracting an eye blinking feature parameter of each electromyographic signal in the electromyographic signal set; S3, updating an eye blinking detection threshold based on the eye blinking feature parameter; and S4, performing eye blinking detection by using the updated eye blinking detection threshold. The method can dynamically update the eye blinking detection threshold based on the electromyographic signals of the user, realize adaptive adjustment of the threshold, and help improve the accuracy of detecting eye blinking of the user.

Providing runtime power profile tuning based on eye state in processor-based Extended Reality (XR) devices is disclosed herein. In this regard, in some exemplary aspects, a processor of a processor-based XR device is configured to apply a default power profile, and detect, using an eye blink detection circuit, an eye close event of a user of the processor-based XR device. In response to detecting the eye close event, the processor selects a test power profile from a plurality of power profiles and applies the test power profile. The processor then measures an operating characteristic of the processor-based XR device and compares the operating characteristic with a corresponding reference range. Based on the comparing, the processor updates one or more power profiles of the plurality of power profiles.

A door lock control method and apparatus (200), and an electronic device (300) and a computer-readable medium. The method comprises: in response to detecting that a user enters a preset recognition range corresponding to a smart door lock, acquiring personal feature information corresponding to the user (step 101); performing blink detection on human eye feature information comprised in the personal feature information, so as to obtain blink frequency information (step 102); in response to determining that the blink frequency information meets a preset frequency condition, performing detection processing on human body feature information, so as to obtain posture feature information and facial feature information (step 103); performing matching processing on the posture feature information and pre-acquired personal posture information, so as to obtain first identity matching information (step 104); in response to determining that the first identity matching information meets a first preset identity matching condition, performing fusion processing on the facial feature information and the human eye feature information, so as to obtain fused feature information corresponding to the user (step 105); performing matching processing on the fused feature information and pre-acquired personal depth feature information, so as to obtain second identity matching information (step 106); and in response to determining that the second identity matching information meets a second preset identity matching condition, sending a preset unlocking instruction to a door lock controller corresponding to the smart door lock, so as to control the unlocking of the door lock (step 107).

The application provides a driver dry eye risk assessment method and device and electronic equipment. First, key point positioning is performed on the facial image data of the driver collected by the driver monitoring system, and then blink detection, eye rubbing detection and squeeze blinking detection are performed based on the key point positioning results. Then, core basic feature extraction is performed based on the blink detection results, eye rubbing detection results and squeeze blinking detection results, and a time sequence is constructed based on the core basic feature extraction results. Then, based on the time sequence, a dry eye risk score prediction is performed through a pre-trained deep learning model. Finally, based on the dry eye risk score prediction result, a dry eye risk level determination is performed according to a preset risk level determination rule. The driver dry eye disease risk can be quantitatively and accurately evaluated by using the application, thereby ensuring driving safety.