60 results about "Face orientation" patented technology

The invention relates to the field of vehicle control, and particularly discloses a vehicle control method and device and a vehicle, and the method comprises the steps: obtaining an ultra-wideband pulse signal sent by a target head-mounted device and inertial measurement unit data in response to the detection that the target head-mounted device is in a wearing state; based on the ultra-wideband pulse signal and inertial measurement unit data, face position information of the user is determined, and the face position information comprises a head three-dimensional coordinate, a face orientation and a pitching angle; and based on the face position information, generating a control instruction to adjust at least one controllable device in the vehicle. Through the multi-source data of the target head-mounted device, the accuracy of the face position information is ensured, so that the accuracy and the response speed of the control instruction are improved. And the vehicle equipment is intelligently controlled based on the face position information, so that the operation convenience and the driving experience of the user are improved.

This face orientation estimation device comprises: an image acquisition unit (11) that acquires a face image of an occupant of a vehicle; a feature point detection unit (12) that detects a plurality of facial feature points including eyes, nose, and mouth from the face image; an attribute estimation unit (14) that estimates a skeletal attribute of the occupant on the basis of the face image; a three-dimensional model selection unit (15) that, on the basis of the skeletal attribute of the occupant, selects an estimation three-dimensional model from among a plurality of three-dimensional models representing human faces that correspond to different skeletal attributes; a face orientation estimation unit (16) that estimates the face orientation of the occupant on the basis of the plurality of facial feature points detected by the feature point detection unit (12) and the estimation three-dimensional model selected by the three-dimensional model selection unit (15); and a three-dimensional model adjustment unit (17) that, on the basis of a face orientation estimation result relating to the face orientation of the occupant estimated by the face orientation estimation unit (16) and information about the plurality of facial feature points detected by the feature point detection unit (12), adjusts the positions of the model facial feature points in the estimation three-dimensional model that correspond to the facial feature points.

An information processing apparatus includes: a distance measuring sensor which measures a distance to an object; a memory which temporarily stores distance information indicative of the distance measured by the distance measuring sensor; and a processor which executes processing based on the distance information. The processor performs person detection processing to detect a person present within a first distance range using the distance measuring sensor, and face direction determination processing to determine a face orientation of the person when the person is detected within the first distance range by the person detection processing. In the face direction determination processing, when the person detected by the person detection processing is within a second distance range closer than the first distance range, the processor determines a face orientation of the person using the distance measuring sensor.

There is provided a method for providing a target position for a robotic speaker in an environment. The method includes receiving sensor information from one or more sensors related to the environment, obtaining at least one of initiation gesture information, position information, and face direction information based on the sensor information, the face direction information related to one or more users present in the environment, obtaining the target position of the robotic speaker in the environment by performing a calibration process based on the at least one of initiation gesture information, position information, or face direction information and one or more and acoustic properties of the environment, and positioning the robotic speaker at the target position.

The invention provides a display method and device, equipment, a storage medium and a program product. The method comprises the steps that the current face orientation of a first object in the real world is determined; determining a current watching coordinate of the first object in a pre-constructed digital twin world; acquiring a first image from the digital twin world according to the current face orientation and the current viewing coordinate; the first image comprises environment information shielded by a first object watched by the first object in the real world; and displaying the first image as a background of the main body element while displaying the preset main body element through the display surface.

Methods and devices for performing face swapping in images are disclosed. The method includes acquiring a destination and source image; detecting an individual's face in both images by generating a first bounding box with a set of pixels representing the face in the destination image and a second bounding box with a set of pixels representing the face in the source image. The method compares the face orientations between the two images. If the orientation difference exceeds a threshold, an enlarged first bounding box and second bounding box are generated, containing enlarged sets of pixels. A modified image is then generated based on the destination image and the enlarged pixels from the source image. The modified image is then displayed on a device.

An information presentation method includes: an information collection step (S12) for collecting at least one of information relating to at least one of a face orientation and a line-of-sight orientation of a subject (99) and information relating to a posture of the subject (99); an action analysis step (S12) for analyzing the action of the subject (99) on the basis of the collected information; a presentation image determination step (S15) for determining a presentation image for presenting to the subject (99) on the basis of the analysis result of the operation, the presentation image being an image acquired from a camera (20) provided at a position different from the viewpoint of the subject (99) and being an image having a range selected from within the range that can be captured by the camera (20); and a presentation step (S17) for presenting the determined presentation image to the subject (99) via a display device (60).

An information processing apparatus includes: a first chassis; a second chassis; a hinge coupling the first chassis and the second chassis to bend in a direction facing a first surface of the first chassis and a second surface of the second chassis while the first surface and the second surface are open; a sensor detecting orientations of the first chassis and the second chassis; an imaging unit provided on either one of the first surface and the second surface; a first processor controlling the operating state of a system by executing a program of the system; a second processor detecting a face and an orientation of the face from an image captured by the imaging unit; and a third processor controlling the operating state of the system based on the detected orientations of the first chassis and the second chassis and the orientation of the face.

An information processing apparatus includes: a distance measuring sensor which measures a distance to an object; a memory which temporarily stores distance information indicative of the distance measured by the distance measuring sensor; and a processor which executes processing based on the distance information. The processor performs person detection processing to detect a person present within a first distance range using the distance measuring sensor, and face direction determination processing to determine a face orientation of the person when the person is detected within the first distance range by the person detection processing. In the face direction determination processing, when the person detected by the person detection processing is within a second distance range closer than the first distance range, the processor determines a face orientation of the person using the distance measuring sensor.

The invention provides an image processing method and related equipment, relates to the field of artificial intelligence, and is used for controlling details of a human face in an image when a portrait customization task is executed so as to meet the requirement of a user for customization of the details of the human face. In the method, a first device obtains a first image and a second image, the first image comprises a first face, the second image is an image of a 3D face model with target attributes, and the target attributes comprise shadow, face expression or face orientation; the first device obtains an encoding result through an encoder according to the first image and the second image, and the encoding result is fused with features of the first image and the second image; the first device obtains a third image through a generation model according to the coding result, the third image comprises a second face with the target attribute, and the second face and the first face correspond to the same person.

The embodiment of the invention relates to a touch coordinate recognition method and device, terminal equipment and a storage medium, the method can be applied to the terminal equipment, the method comprises the steps that a first image and a second image are acquired, the first image comprises hand image content, and the second image comprises face image content; fingertip coordinate identification is carried out on the first image, and a touch coordinate corresponding to a fingertip is obtained; face recognition is carried out on the second image to obtain a face recognition result, and the face recognition result is used for representing the face orientation; and if it is determined that the face faces the screen of the terminal device, not responding to the touch coordinates. According to the touch coordinate recognition method and device, the terminal equipment and the storage medium, the situation that the terminal equipment responds to the mistaken touch operation of the user can be reduced, and the mistaken touch prevention capacity of the terminal equipment is improved.

An information processing apparatus includes: a memory which temporarily stores image data of an image captured by an imaging unit; and a processor which processes the image data stored in the memory. The processor performs: face detection processing to process the image data of the image stored in the memory in order to detect a face area with a face captured therein and an orientation of the face from the image, and brightness control processing to control screen brightness of a display unit based on the orientation of the face detected by the face detection processing.

The present application provides a line-of-sight calibration system that improves the accuracy of line-of-sight calibration in a wide area including a region deviating from the optical axis of a camera. The present application is provided with: a first display portion provided at the central portion in the vehicle width direction in front of the driver's seat, a second display portion provided on the front face of the driver's seat, a camera portion provided on the outer edge upper portion of the first display portion, a display image control portion that controls the display image displayed by the first display portion and the second display portion, a calibration data generation portion that detects the face orientation and line-of-sight direction when the driver D visually recognizes the first display portion and the face orientation and line-of-sight direction when the driver D visually recognizes the second display portion based on the image captured by the camera portion and generates calibration data, and a calibration portion that calibrates the line-of-sight direction corresponding to the face orientation that becomes the reference in the case of visually recognizing the first display portion and the line-of-sight direction corresponding to the face orientation that becomes the reference in the case of visually recognizing the second display portion based on the calibration data generated.

The application provides a personnel mobile phone playing behavior detection method and device in a bright kitchen and bright stove scene, and belongs to the technical field of machine vision, the method comprises the following steps: detecting human body key points and target objects in a single frame image; based on the human body skeleton joint point information and the target object information, the distance between the face and the target object, the similarity of the human body posture and the target posture, and the deviation degree between the face orientation and the target object are determined; based on the distance, the similarity and the deviation degree, it is determined whether the personnel behavior is a mobile phone playing behavior. The application detects human body key points and target objects based on a single frame image, improves the system running efficiency, determines whether the personnel behavior is a mobile phone playing behavior by combining the distance, the similarity and the deviation degree, solves the problems of poor generalization performance and poor robustness, detects human body key points, and improves the recognition accuracy of situations such as crouching and side face.

A driver state detection device includes: a recognizer configured to recognize at least one of a gaze and a face direction of a driver of a mobile object; a determiner configured to determine whether a monitoring direction of the driver is appropriate on the basis of a result of recognition from the recognizer; and a lighting controller configured to perform lighting control of a direction indicator of the mobile object according to the driver's operation of an operator for lighting the direction indicator and to perform control such that lighting is maintained even when the operator returns to a neutral position. The determiner makes it more difficult to determine that the monitoring direction of the driver is not appropriate in comparison with before the operator is operated until the operator returns to the neutral position and a predetermined condition is satisfied.

The invention discloses an image generation method and device, a medium and equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: obtaining an original object image, a target face orientation feature and a target image indication text; determining a first image feature and a second image feature corresponding to the original object image and an indication text feature corresponding to the target image indication text; fusing the first image feature, the second image feature and the indication text feature to obtain a first fusion feature; fusing the target face orientation feature and the second image feature to obtain a second fusion feature; and inputting the first fusion feature and the second fusion feature into an image generation model, so that the image generation model performs image generation processing by taking the first fusion feature and the second fusion feature as control conditions to obtain a target object image corresponding to the target object. According to the invention, the image with the specified emotion and face orientation can be generated according to the image generation demand, and the personalized expression of the image is enriched.

The application discloses an automatic calibration method and device, a vehicle, a medium, equipment and a program product, and belongs to the field of data processing. The method comprises the following steps: converting the position coordinates of the nose tip point and the pupil center point of a face in a camera coordinate system into the coordinates of the nose tip point and the pupil center point of the face in an image coordinate, establishing a corresponding face orientation coordinate system and a line of sight orientation coordinate system, and obtaining a second face orientation and a second line of sight orientation in the corresponding coordinate system; and calibrating at least one of a face reference orientation and a line of sight reference orientation in the camera coordinate system by using at least one of a first face orientation and a first line of sight orientation of a predetermined number of frames of images and at least one of a second face orientation and a second line of sight orientation corresponding to the first face orientation and the first line of sight orientation. The application can achieve the purpose of automatically calibrating a driver at the initial stage of starting the vehicle, improve calibration efficiency, and calibrate a suitable coordinate system for different drivers.

This visual target estimation device comprises an angle acquisition unit that, on the basis of face image data obtained by capturing images of the face of the driver of a vehicle using a camera, acquires at least two angles from among a first face orientation angle based on the face orientation when facing the camera, a second face orientation angle based on the face orientation when facing a prescribed direction other than the camera, a first gaze angle based on the gaze when facing the camera, and a second gaze angle based on the gaze when facing the prescribed direction other than the camera, and an estimation unit. The estimation unit estimates the driver's visual target on the basis of at least: a first probability distribution and a second probability distribution which indicate the probability of the driver gazing at each of a plurality of prescribed visual targets for each first face orientation angle and each second face orientation angle, respectively; a third probability distribution and a fourth probability distribution which indicate the gaze probability for each first gaze angle and each second gaze angle, respectively; or a first probability coefficient calculated based on the first or second probability distribution and a second probability coefficient calculated based on the third or fourth probability distribution.

This invention discloses a robot human-computer interaction method and related apparatus that integrates gestures and gaze. The method detects and tracks all people in each frame of an image and separates them to obtain the bounding boxes of all people. The pixel regions of each person's bounding box are cropped and input into a human pose estimation model one by one, outputting the key points of each person's body. The face orientation is determined based on the facial key points. Based on the facial key points, the pixel regions of the face are determined and cropped, and the face orientation is used as prior information and input together with the face pixel regions into the gaze estimation model to obtain the yaw and pitch angles of the face. Based on the yaw and pitch angles of the face, gaze attention is calculated to obtain the gaze attention result. When the face orientation and gaze attention result simultaneously meet preset requirements, the hand key points from the current moment and several consecutive frames before it are input frame by frame into a gesture recognition model, outputting the gesture type. This invention can more accurately determine the user's gesture intent.

The invention discloses a spoken English situational simulation teaching method and system based on somatosensory interaction, and belongs to the technical field of spoken English situational simulation teaching. Head rotation, limb postures, face orientation and hand actions of a learner in a teaching scene are collected to form an initial interaction feature sequence; synchronously acquiring spoken English output content, and constructing a voice feature matrix; the features are fused through time sequence alignment and a multi-channel attention mechanism, and a somatosensory-voice joint interaction feature map is generated; simulating task nodes and non-player character scripts based on atlas matching, and dynamically adjusting dialogue rhythm and context complexity; generating a capability evaluation report in combination with the completion state and the interaction performance of the learner; according to the low response index in the evaluation result, a customized training task is recommended, language + action double-channel fusion modeling, intelligent task scheduling and dynamic learning path recommendation are achieved, and the adaptability, interactivity and accurate feedback ability of a teaching system are improved.

The invention discloses a face orientation guiding method and a face diagnosis instrument, and the method comprises the steps: obtaining a real-time image data flow comprising a face image, and selecting a single-frame image in the image data flow as a face posture estimation sample at an interval of a preset sampling period; acquiring facial feature points for posture estimation from the facial posture estimation sample, and calculating to obtain a head posture; calculating the posture deviation of the head posture, and judging whether the current head posture is aligned with the target position or not according to a preset yaw angle threshold value, a preset pitch angle threshold value and a preset roll angle threshold value; if the current head posture is not aligned with the target position, the strength value of the posture deviation is calculated, a dynamic guide element is generated on a preset display interface according to the strength value, and the dynamic guide element is used for prompting the user to adjust the face orientation to the target position. According to the technical scheme, the face of the user is guided to face the correct target position in the image acquisition stage, and the accuracy of subsequent data processing is improved.

The invention relates to a face orientation detection method and device, equipment and a medium, and the method comprises the steps: carrying out the key point detection of a face in a to-be-detected image, and obtaining a first face key point; performing pose estimation on the face based on the first face key point and the second face key point to obtain a rotation angle of the face; wherein the second face key point is a preset face key point with a known rotation angle; according to the rotation angle of the face and the rotation angle threshold value corresponding to each preset orientation, carrying out calculation to obtain the probability that the face directly faces each preset orientation; and determining a face orientation detection result of the face according to the probability that the face directly faces each preset orientation. According to the technical scheme of the invention, the computing resource consumption can be reduced, and the real-time performance of face orientation detection can be improved.

This electronic device may comprise: a memory for storing instructions; and a processor. When executed by the processor, the instructions can cause the electronic device to: acquire an image that includes the face of a user; extract feature values from the acquired image by using a face recognition model to which the weight of a masked auto encoder (MAE) trained for faces including the face is transferred; identify, from among reference embedding vectors stored in the memory, a reference embedding vector corresponding to an embedding vector generated on the basis of the extracted feature values; and recognize the user corresponding to the reference embedding vector identified from the image. The face recognition model can be trained through a loss function calculated on the basis of a reference margin value and a rotation margin value, which is based on at least one rotation angle value indicating the orientation of the face.

The application provides a video playing method and device, relates to the field of virtual reality technology, and can improve the interaction when a user adjusts the visual angle of video playing. The method comprises the following steps: collecting target information, and then adjusting the visual angle of video playing according to the target information. The target information comprises user face orientation information and user movement information, the user face orientation information is used for representing the direction of the user face orientation, and the user movement information is used for representing the direction of the user movement. In the video playing method provided by the application, when the user adjusts the visual angle of video playing, the user does not need to manipulate a mouse or touch a screen, but can directly change the face orientation and move the body, so that the visual angle of video playing is adjusted according to the user action, and thus the interaction when the user adjusts the visual angle of video playing is improved.

A virtual character adjustment method and apparatus, a vehicle, an electronic device, a storage medium, and a program product. The method comprises: acquiring position information of a user performing voice interaction with a virtual character; and, on the basis of the position information, adjusting the face orientation of the virtual character. On the basis of the position information of the user performing voice interaction the virtual character, the face orientation of the virtual character is adjusted in real time, so that the virtual character turns to the speaking user in real time on the basis of a position change of the user, thereby improving the experience of conversations between people and voice assistants.

The present disclosure relates to a face orientation detection method and apparatus, and a device, a vehicle, a medium and a program product. The method comprises: performing key point detection on a face in an image to be subjected to detection, so as to obtain a first facial key point; performing pose estimation on the face on the basis of the first facial key point and a second facial key point, so as to obtain the turning angle of the face, wherein the second facial key point is a preset facial key point with a known turning angle; performing calculation on the basis of the turning angle of the face and a turning angle threshold value corresponding to each preset orientation, so as to obtain the probability of the face directly in each preset orientation, wherein the probability decreases along with the increase of the difference between the turning angle of the face and the turning angle threshold value; and on the basis of the probability of the face directly in each preset orientation, determining a facial orientation detection result for the face. On the basis of the technical solution of the present disclosure, the consumption of computing resources can be reduced, and the real-time performance of face orientation detection is improved.

The invention provides a software application control method and system based on big data analysis, and relates to the technical field of application control, and the method comprises the steps: obtaining a historical playing record of a tourist, a playing region of the tourist, and a historical playing photographing image of the tourist; determining a plurality of primarily selected photographing areas based on the historical travel record of the tourist and the travel area of the tourist; constructing a photographing map; processing the photographing map based on a graph neural network to determine a plurality of target photographing points and target face orientations of the target photographing points; determining a target hotel based on the plurality of target photographing points; and respectively sending the plurality of target photographing points, the target face orientations of the plurality of target photographing points and the target hotel to a digital RMB terminal and displaying on navigation software and hotel reservation software. According to the method, the face orientations of the photographing points can be accurately determined in combination with tourist preferences, and an appropriate target hotel can be determined for tourists.

Attention direction assessment device (200) comprising an image acquisition section (1) for acquiring an image of occupants in a vehicle taken by a camera (9), a facial feature inference section (2) which infers facial features of an inmate based on the image acquired through the image acquisition section (1), a physis inference section (5) which, based on the image acquired by the image acquisition section (1), infers a direction in which an inmate's hand is extended, a face direction detection section (6) which detects a face direction of the occupant based on the facial features inferred by the face feature inference section (2), a seat information acquisition section (21) for acquiring seat information of the occupants in the vehicle, and an attention direction assessment section (7) which, based on the direction in which the occupant's hand is extended as inferred by the physis inference section (5), the face direction of the occupant detected by the face direction detection section (6) and seat information acquired by the seat information acquisition section (21), assesses the direction in which the occupant's attention is directed, where, if the direction inferred by the physique inference section (5) in which the occupant's hand is extended is a neighboring seat direction, the direction of the occupant's face detected by the face direction detection section (6) is the neighboring seat direction, and furthermore, the seat information acquired by the seat information acquisition section (21) shows that there is no occupant in the neighboring seat, the attention direction assessment section (7) judges that the direction in which the occupant's attention is directed is the neighboring seat direction.

The application discloses a face orientation recognition method and device, and the method comprises the following steps: obtaining a face gray image by performing thermal imaging on a user's face; obtaining gray gradient data of the face gray image based on gray data of each calculation region in the face gray image; wherein the gray gradient data is used for representing the gray difference between adjacent calculation regions; determining a target face orientation matched with the gray gradient data from preset face orientation data; wherein the face orientation data comprises a corresponding relationship between different face orientations of the user's face and the gray gradient data. When the application is used for face recognition and positioning, the data processing amount is small, the fast positioning and recognition can be realized, and the recognition precision is good.

A driver state detection device includes a recognizer configured to recognize at least one of a gaze and a face direction of a driver of a mobile object and a determiner configured to determine whether the driver is performing sideways-glance driving based on a result of recognition and a sideways-glance determination condition. The determiner performs the determination of sideways-glance driving using a first sideways-glance determination condition when a swing of the mobile object is not predicted and when the mobile object is not swinging, performs the determination of sideways-glance driving using a second sideways-glance determination condition when a swing of the mobile object is predicted or when the mobile object is swinging, and changes a swing determination condition for determining whether the mobile object is swinging according to whether a swinging direction of the mobile object is right or left when it is determined whether the mobile object is swinging.