A recording reproduction apparatus includes: a captured data acquisition unit configured to acquire first captured data captured by a first camera that captures an image of an outside of a moving body and second captured data captured by a second camera that captures an image in a direction opposed to a display surface of a display unit; an event detection unit configured to detect an event on the moving body; a recording controller configured to store, when an event has been detected, the first captured data as event recording data; a face detection unit configured to detect a human face from the second captured data; a reproduction controller configured to reproduce the event recording data when a human face has been detected within a period after storage of the event recording data; and a display controller configured to cause the display unit to display the reproduced event recording data.

An apparatus for predicting a body temperature is provided. The apparatus includes an external environment/activity estimation neural network configured to detect at least one facial region as a region of interest from an input thermal image of a target person to be measured, and estimate an environmental type including an external temperature and participation in physical activity based on a temperature of the at least one region of interest. The apparatus further includes a body temperature prediction neural network configured to predict a body temperature of the target person based on the environmental type estimated by the external environment/activity estimation neural network and the temperature of the at least one region of interest.

A terminal apparatus includes a controller configured to: transmit, to a server apparatus, a suggestion request requesting a suggestion of a function to be invoked; receive, from the server apparatus, a suggestion response that specifies a suggested function determined by the server apparatus; and invoke the suggested function. The suggestion request includes face image data of a user. The suggested function is determined by applying the face image data to a learned model. The controller is configured to: evaluate, based on face images of the user, a degree of change in facial expressions before and after invoking the suggested function; and transmit, to the server apparatus, a learning request requesting re-learning of the learned model when the evaluated degree of change in the facial expressions satisfies a predetermined condition.

Techniques are provided for generating one or more three-dimensional (3D) models. In one example, an image of an object (e.g., a face or other object) is obtained, and a 3D model of the object in the image is generated. The 3D model includes geometry information. Color information for the 3D model is determined, and a fitted 3D model of the object is generated based on a modification of the geometry information and the color information for the 3D model. In some cases, the color information (e.g., determination and/or modification of the color information) and the fitted 3D model can be based on one or more vertex-level fitting processes. A refined 3D model of the object is generated based on the fitted 3D model and depth information associated with the fitted 3D model. In some cases, the refined 3D model can be based on a pixel-level refinement or fitting process.

A three-dimensional facial shape estimating device (300) includes a face image acquiring unit (301) configured to acquire a plurality of image frames that capture a subject's face; a face information acquiring unit (302) having, preset therein, a predetermined number of facial feature points, the face information acquiring unit (302) being configured to acquire, for each of the plurality of image frames, face information that indicates a position of each of the predetermined number of facial feature points of the subject's face within the image frame; and a three-dimensional shape estimating unit (303) configured to perform mapping of each of the predetermined number of facial feature points of the subject's face between the plurality of image frames based on the face information of each of the plurality of image frames and to estimate the three-dimensional shape of the subject's face based on a result from the mapping.

A three-dimensional position estimation device includes: a feature point extracting unit for detecting an area corresponding to the face of an occupant in an image captured by a camera for imaging a vehicle interior and extracting a plurality of feature points in the detected area; an inter-feature-point distance calculating unit for calculating a first inter-feature-point distance that is a distance between distance-calculating feature points among the plurality of feature points; a face direction detecting unit for detecting the face direction of the occupant; a head position angle calculating unit for calculating a head position angle indicating the position of the head of the occupant with respect to an imaging axis of the camera; an inter-feature-point distance correcting unit for correcting the first inter-feature-point distance to a second inter-feature-point distance that is a distance between distance-calculating feature points in a state where portions of the head corresponding to the distance-calculating feature points are arranged along a plane parallel to an imaging plane of the camera using a result detected by the face direction detecting unit and the head position angle; and a three-dimensional position estimating unit for estimating the three-dimensional position of the head using the head position angle, the second inter-feature-point distance, and a reference inter-feature-point distance.

The present disclosure relates to methods and systems for identifying an individual in a crowd. The method comprises the steps of capturing a plurality of crowd-viewing images using multiple image-capturing devices. For each image, a reference point within a facial contour of a person in the image is selected. The reference point is selected based on a facial feature on the facial contour of the person. The method further comprises the step of processing the image to obtain one or more angular measurements associated with a posture displayed by the person in the image. Based on the obtained angular measurements, location data of a predetermined body point of the person relative to the reference point is extracted.

The system for in-vehicle video conferencing (200) includes:

an acquisition module (201) for acquiring data of facial characteristic points of a user (A) in the vehicle (100) during a video conference call in which said user (A) participates;
a video synthesizer (202A) for producing an artificial video of the face of the user in the vehicle (100) from the acquired data of facial characteristic points,
a communication device (203) for transmitting the artificial video of the face of the user through a communication network (300) in the video conference call.

The present invention relates to an X-ray imaging system (10). The X-ray imaging system comprises an optical camera (20), an X-ray imaging device (30), a processing unit (40), and an output unit (50). The optical camera is configured to acquire an optical image of a body part (BP) of a patient or an optical image of the head of the patient. The X-ray imaging device is configured to acquire an X-ray image of the body part of the patient. The processing unit is configured to determine an orientation of the body part, the determination comprising utilization of the optical image of the body part or utilization of the optical image of the head of the patient. The processing unit is configured to annotate the X-ray image of the body part with the orientation. The output unit is configured to output the orientation annotated X-ray image.

A neural network training method, an image processing method, and apparatuses thereof are provided. The neural network training method includes obtaining a first domain image and a second domain image, where the first domain image and the second domain image are unpaired images in different domains; obtaining a scaled first domain image by scaling, at an iteration, the first domain image; obtaining a training patch by cropping the scaled first domain image, where each training patch has a same number of pixels with different contents; inputting the training patch into the neural network at the iteration, and outputting an output patch; calculating a contrastive loss based on a query sub-patch and negative sub-patches selected from the training patch and a corresponding positive sub-patch selected from the output patch; and updating model parameters of the neural network based on the contrastive loss and a generative adversarial network loss.