In general, the disclosure describes techniques for joint spatiotemporal Artificial Intelligence (AI) models that can encompass multiple space and time resolutions through self-supervised learning. In an example, a method includes for each of a plurality of multimodal data, generating, by a computing system, using a first machine learning model, a respective modality feature vector representative of content of the multimodal data, wherein each of the generated modality feature vectors has a different modality; processing, by the computing system, each of generated modality feature vectors with a second machine learning model comprising an encoder model to generate event data comprising a plurality of events and/or activities of interest; and analyzing, by the computing system, the event data to generate anomaly data indicative of detected anomalies in the multimodal data.

A system for respiration monitoring includes a garment, which is configured to be fitted snugly around a body of a human subject, and which includes, on at least a portion of the garment that fits around a thorax of the subject, a pattern of light and dark pigments having a high contrast at a near infrared wavelength. A camera head is configured to be mounted in proximity to a bed in which the subject is to be placed, and includes an image sensor and an infrared illumination source, which is configured to illuminate the bed with radiation at the near infrared wavelength, and is configured to transmit a video stream of images of the subject in the bed captured by the image sensor to a processor, which analyzes movement of the pattern in the images in order to detect a respiratory motion of the thorax.

A camera attachment apparatus for attaching to a mobile computing device having an integrated camera includes a house, a slide plate, an aperture, and an illumination system. The housing has a shape to mount on the mobile computing device. The slide plate is disposed within the housing and has a stowed position and a deployed position. The aperture is disposed in the slide plate. The illumination system is disposed on the slide plate. The slide plate is configured to align the aperture over the integrated camera when moved to the deployed position and does not obstruct the integrated camera in the stowed position.

Reception of the invisible light wavelength band in an incident luminous flux has not been considered. In view of this, an image sensor is provided, the image sensor including: a visible parallax pixel that is associated with a visible range light-receiving photoelectric conversion pixel having any of a plurality of types of aperture mask each including an aperture that is positioned to allow passage, to a photoelectric converting element, of a mutually different partial luminous flux of an incident luminous flux in a visible light wavelength band; and an invisible parallax pixel that is associated with an invisible range light-receiving photoelectric conversion pixel having any of a plurality of types of aperture mask each including an aperture positioned to allow passage, to the photoelectric converting element, of a mutually different partial luminous flux in an incident luminous flux in an invisible light wavelength band.

The present invention relates to a system in the form of a multi-view occlusion preventive optical system having an image capturing device in cooperation with a passive screen. The system is intended to be used as an image capturing device for wide angle panoramic imaging and occlusion prevention. The present invention more particularly relates to a multi-view optical system comprising an image capturing device (14) and a passive screen (11), said image capturing device (14) capturing a plurality of images being reflected from said passive screen (11) in optical communication therewith.

An imaging apparatus includes: a light source that emits a light pulse onto an object, and a light detector that detects a reflected light pulse returning from the object. The light detector detects a first part of the reflected light pulse in a first period, and detects a second part of the reflected light pulse in a second period that starts after the first period. The first period includes at least a part of a rising period, the rising period being a period from start to end of increase of intensity of the reflected light pulse. The second period includes a part of a falling period, starts after start of the falling period and does not include the start of the falling period, the falling period being a period from start to end of decrease of the intensity.

The invention concerns an image sensor comprising: a depth pixel (PZ) having: a detection zone (PD); a first memory (mem.sub.1) electrically coupled to the detection zone by a first gate (310); a second memory (mem.sub.2) electrically coupled to the detection zone by a second gate (314); and a third memory (mem.sub.3) electrically coupled to the detection zone by a third gate (316), wherein the first, second and third memories are each formed by a doped region sandwiched between first and second parallel straight walls (404, 406), the first and second walls of each memory having a conductive core adapted to receive a biasing voltage; and a plurality of 2D image pixels (P1 to P8) positioned adjacent to the depth pixel, wherein the first, second and third memories extend to form at least partial isolation walls between corresponding adjacent pairs of the 2D image pixels.

A system mountable in a motor vehicle. The system includes a camera and a processor configured to receive image data from the camera. The camera includes a rolling shutter configured to capture the image data during a frame period and to scan and to read the image data into multiple image frames. A near infra-red illuminator may be configured to provide a near infra-red illumination cone in the field of view of the camera. The near infra-red illumination oscillates with an illumination period. A synchronization mechanism may be configured to synchronize the illumination period to the frame period of the rolling shutter. The frame period may be selected so that the synchronization mechanism provides a spatial profile of the near infra-red illumination cone which may be substantially aligned vertically to a specific region, e.g. near the center of the image frame.

An electronic device (100) includes a modulated light projector (119) and an electronic rolling shutter (ERS) imaging camera (1302) having a sensor array (1306) with a set of pixel rows. The electronic device includes a controller (1304) to control the modulated light projector (119) to project a modulated light flash (1608, 1810, 2010) during capture of a first image frame (1606, 1806, 2006) by the sensor array. The controller is to initiate the modulated light flash while each pixel row of the set is exposed for gathering light and to terminate the modulated light flash before a pixel row of the set is exposed for capture of a next image frame by the sensor array. The electronic device further includes a processor (802) to determine modulated light image data (1320) based on the first image frame. The controller also may control the modulated light projector to refrain from projecting the modulated light flash during capture of a second image frame (1602, 1612, 1802, 1816, 2002, 2018), adjacent to the first image frame.

The present invention discloses an expression recognition apparatus and methods using a head mounted display thereof. A head mounted display apparatus for performing expression recognition according to an embodiment of the present invention comprises a sensing unit including at least one of expression detection sensing units installed inside of said apparatus for sensing expression information around eyes by at least one of a contact or a non-contact manner; an image acquiring unit installed outside of said apparatus for collecting expression information around a mouth; and an acquisition unit for information of expressions for collecting expression information around the eyes and expression information around the mouth.