Systems, devices, and techniques related to matching features between a dynamic vision sensor and one or both of a dynamic projector or another dynamic vision sensor are discussed. Such techniques include casting a light pattern with projected features having differing temporal characteristics onto a scene and determining the correspondence(s) based on matching changes in detected luminance and temporal characteristics of the projected features.

A vehicle service system and method to determine spatial parameters of a vehicle, employing a display system under processor control, to display or project visible indicia onto surfaces in proximity to a vehicle undergoing a safety system service or inspection identifying one or more locations, relative to the determined vehicle centerline or thrust line, at which a calibration fixture, optical target, or simulated test drive imagery is visible for observation by a sensor onboard the vehicle.

A handheld device has a projector that projects a pattern of light onto an object, a first camera that captures the projected pattern of light in first images, a second camera that captures the projected pattern of light in second images, a registration camera that captures a succession of third images, one or more processors that determines three-dimensional (3D) coordinates of points on the object based at least in part on the projected pattern, the first images, and the second images, the one or more processors being further operable to register the determined 3D coordinates based at least in part on common features extracted from the succession of third images, and a mobile computing device operably connected to the handheld device and cooperating with the one or more processors, the mobile computing device operable to display the registered 3D coordinates of points.

A three-dimensional measurement system projects patterned light onto a target object, images the target object from different viewpoints to obtain a first image and a second image, obtains first depth information using the first image with a spatially encoded pattern technique, defines a search range for a corresponding point based on parallax between the first image and the second image predicted from the first depth information, and obtains second depth information by performing stereo matching for the defined search range using the first image and the second image. The second depth information has a higher spatial resolution than the first depth information. The patterned light has a combined pattern combining a spatially encoded pattern including a plurality of unit elements arranged regularly and a random pattern including a plurality of random pieces arranged randomly. Each of the plurality of unit elements is an area corresponding to a depth value.

A measurement method includes measuring a normal vector of a measured portion based on a first vector representing a direction from a measured portion to a principal point of a first lens, a second vector representing a direction from the measured portion to a principal point of a second lens, a third vector representing a direction from the measured portion to a principal point of a third lens, a first value representing luminance of the measured portion in a situation in which the first projector projects a fourth image via the first lens, a second value representing the luminance of the measured portion in a situation in which the second projector projects a fifth image via the second lens, and a third value representing the luminance of the measured portion in a situation in which the third projector projects a sixth image via the third lens.

A system includes a first light source that projects lines of light onto an object, a second light source that illuminates markers on or near the object, one or more image sensors that receive first reflected light from the projected lines of light and second reflected light from the illuminated markers, one or more processors that determine the locations of the lines of light on the image sensors based on the first reflected light and that determines the locations of the markers on the image sensors based on the second reflected light, and a frame physically coupled to the first light source, the second light source, the one or more image sensors, and the one or more processors.

A computer assisted system is disclosed that includes an optical tracking system and one or more computing devices. The optical tracking system includes an RGB sensor and is configured to capture color images of an environment in the visible light spectrum and tracking images of fiducials in the environment in a near-infrared spectrum. The computer assisted system is configured to generate a color image of the environment using the color images, identify fiducial locations using the tracking images, generate depth maps from the color images, reconstruct three-dimensional surfaces of structures based on the depth maps, and output a display comprising the reconstructed three-dimensional surface and one or more surgical objects that are associated with the tracked fiducials. The computer assisted system can further include a monitor or a head-mounted display (HMD) configured to present augmented reality (AR) images during a procedure.

A three-dimensional geometry measurement apparatus including a virtual coordinate identification part that identifies coordinates of a virtual captured pixel corresponding to a feature point in an image plane of a capturing device by virtually projecting the feature point on a reference instrument onto the image plane: correction part that generates correction information for correcting coordinates of the measurement-target captured pixel included in a measurement-target captured image; and a geometry identification part that corrects coordinates of a plurality of the measurement-target captured pixels included in the measurement-target captured image generated by capturing an object to be measured with the capturing device on the basis of geometric property information and the correction information, and identifies a geometry of the object to be measured on the basis of measurement three-dimensional coordinates to be calculated based on the coordinates of the measurement-target captured pixels.

The present invention discloses a line stripe mismatch detection and three-dimensional reconstruction method and device. The method includes: acquiring a first image of line stripes collected by a first camera and a second image of line stripes collected by a second camera, where the first image at least includes: a first line stripe and a second line stripe; the second image at least includes: a third line stripe and a fourth line stripe, the first line stripe is adjacent to the second line stripe, and the third line stripe is adjacent to the fourth line stripe; matching the first line stripe with the third line stripe, determining a first test distance between the first line stripe and the third line stripe, matching the second line stripe with the fourth line stripe, and determining a second test distance between the second line stripe and the fourth line stripe; and determining whether the line stripes are mismatched according to the first test distance and the second test distance. The present invention solves the technical problem of incapability of detecting whether the line stripes are mismatched.

A measurement apparatus, comprising: a projection apparatus configured to project a predetermined pattern on a subject; and an image capturing system configured to capture a group of images from at least two different viewpoints, wherein the distance between the viewpoints is shorter than the distances between the projection apparatus and the viewpoints, the measurement apparatus further comprising: relative position calculation means for obtaining a relative position of the projection apparatus relative to at least one of the viewpoints from pattern image positions on the group of images and a positional relationship between the viewpoints, wherein distance information regarding the subject is acquired from the relative position and a pattern image position on an image at the viewpoint.