An information processing device includes a camera interface and a processor, the camera interface acquiring a moving image from a first camera that is installed at a production site and that images a worker and surroundings of the worker and from a second camera that is installed at the production site and that images a face of the worker. The processor detects an operation section of work performed by the worker from a predetermined number of consecutive frames included in the moving image acquired from the first camera using an inference model. The processor detects the emotion and the line-of-sight direction of the worker included in each frame of the moving image acquired from the second camera. Further, the processor provides a detection result.

An image processing device includes: a light emitting unit that emits a near-infrared ray to a target; a light emission controlling unit that controls a light emission amount of the light emitting unit on a basis of a distance value between the target and the light emitting unit; and a detecting unit that detects a feature point on the basis of a captured image of the target irradiated with the near-infrared ray.

A display controlling device includes a position detecting unit for detecting a position of the head of a driver and a position of an eye of the driver; a region adjusting unit for adjusting the position of a region, to be displayed on a display, in an outside image, depending on the detection result by the position detecting unit; and a display controlling unit for displaying, on the display, a region corresponding to the region of the position adjusted by the region adjusting unit. When there is a change in the position of the head so as to move in both the vertical direction in the crosswise direction of the vehicle, the region adjusting unit prevents adjustment of the position of the region to a position corresponding to the change, in the vertical direction, of the position of the eye, and adjusts the position of the region to a position corresponding to a change in the position of the eye in the crosswise direction and/or the front/rear direction.

A gaze monitoring system comprising: an eye tracker comprising; a camera having an optical axis; a first IR source configured to illuminate a user's eyes; the first IR source located relatively near the optical axis of the camera; and at least one second IR source configured to illuminate the user's eyes, the at least one second IR source located relatively far from the camera's optical axis, in a position such that when the gaze angle is too large to get corneal reflection images of the first IR source, the image reflection of the at least one second IR source is visible by the camera, as a corneal reflection.

Systems and methods for iris authentication are disclosed. In one aspect, a deep neural network (DNN) with a triplet network architecture can be trained to learn an embedding (e.g., another DNN) that maps from the higher dimensional eye image space to a lower dimensional embedding space. The DNN can be trained with segmented iris images or images of the periocular region of the eye (including the eye and portions around the eye such as eyelids, eyebrows, eyelashes, and skin surrounding the eye). With the triplet network architecture, an embedding space representation (ESR) of a person's eye image can be closer to the ESRs of the person's other eye images than it is to the ESR of another person's eye image. In another aspect, to authenticate a user as an authorized user, an ESR of the user's eye image can be sufficiently close to an ESR of the authorized user's eye image.

An image segmentation method according to an embodiment of the present invention is performed in a computing device having one or more processors and memory for storing one or more programs executed by means of the one or more processors, and includes the steps of: (a) receiving the input of an image; (b) generating a first-generation image segment set by dividing the input image in an overlapped manner; and (c) generating a second or higher-generation image segment set from the first-generation image segment set, wherein a subsequent-generation image segment set is generated by dividing in an overlapped manner at least one of a plurality of image segments included in the previous-generation image segment set.

There is provided a method, system, and non-transitory computer-readable storage medium for controlling an eye tracking system (200) to obtain a first image (500) captured under active illumination by at least one infrared, IR, illuminator (112, 113) associated with the eye tracking system (200) and at a current exposure setting, using the image sensor device (110); and, if at least one eye (100, 120) is depicted in the first image (500): define at least one region of interest, ROI, (501, 502, 503, 504) from the first image (500) comprising a group of pixels in the first image (500) representing at least a part of the depicted at least one eye (100, 120); determine a respective intensity value for each of the at least one ROI (501, 502, 503, 504); determine a second exposure setting by adjusting at least one exposure parameter of the image sensor device (110) based on the determined intensity value, or values, for the at least one ROI (501, 502, 503, 504); and set the current exposure setting to the second exposure setting.

Related methods are provided for establishing a baseline value to represent an eyelid opening dimension for a person engaged in an activity, where the activity may be driving a vehicle, operating industrial equipment, or performing a monitoring or control function; and for operating a system for monitoring eyelid opening values with real time video data.

Related methods are provided for establishing a baseline value to represent an eyelid opening dimension for a person engaged in an activity, where the activity may be driving a vehicle, operating industrial equipment, or performing a monitoring or control function; and for operating a system for monitoring eyelid opening values with real time video data.

Processing for judging whether a face is included in a frame is performed, in a predetermined interval, on each of frames included in a moving image of a subject, displayed on a monitor, until the judgment becomes positive. If it is judged that a face is included in a frame, the facial position is detected in the frame, and stored. Then, judgment is made as to whether a face is included in the next frame after predetermined time. If the judgment is positive, the facial position is detected. The previously stored facial position is replaced by the newly detected facial position, and the newly detected facial position is stored. These processes are repeated until photographing operation is performed by operating a release unit.