In variants, a method for item recognition can include: optionally calibrating a sampling system, determining visual data using the sampling system, determining a point cloud, determining region masks based on the point cloud, generating a surface reconstruction for each item, generating image segments for each item based on the surface reconstruction, and determining a class identifier for each item using the respective image segments.

A position-determining device, and a milking device, that determines a relative position of an object and includes a 3D time-of-flight camera with a 2D arrangement of pixels configured to repeatedly record an image of a space. A control unit is connected and includes an image-processing device. The 3D time-of-flight camera has a controllable light source and is configured to record a 2D image by means of reflected emitted light and collect distance information. The image-processing device is configured to recognize an object in the 2D image using image-processing criteria and determine distance information and relative position by analysing the 2D image and the distance information. Due to the fact that distance information, which is often much more noisy than 2D brightness information, can be determined with far fewer image points, the position is determined more quickly and reliably.

A method of visual odometry for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs includes instructions, which when executed by a computing device, causes the computing device to perform the following steps comprising: performing data alignment among sensors including a LiDAR, cameras and an IMU-GPS module; collecting image data and generating point clouds; processing, in the IMU-GPS module, a pair of consecutive images in the image data to recognize pixels corresponding to a same point in the point clouds; and establishing an optical flow for visual odometry.

A measurement apparatus includes an optical combining unit configured to optically combine light from a first light source and light from a second light source, a forming unit configured to form pattern light using light from the first light source, a projection optical system configured to project the optically combined light onto an object, an imaging unit configured to image the object on which the pattern light is projected to capture a first image and to image the object illuminated with light from the second light source via the projection optical system to capture a second image, and a processing unit configured to correct the first image using the second image and to obtain information on a shape of the object based on the corrected first image.

A single network encodes and decodes an image captured using a camera on a device. The single network detects if a face is in the image. If a face is detected in the image, the single network determines properties of the face in the image and outputs the properties along with the face detection output. Properties of the face may be determined by sharing the task for face detection. Properties of the face that are output along with the face detection output include the location of the face, the pose of the face, and/or the distance of the face from the camera.

The disclosure provides a stereoscopic vision three dimensional measurement method and system calculating a laser speckle as a texture. The measurement method includes that: a forming process of a laser speckle is simulated first, and calculation is performed to obtain a digitized laser speckle diagram, then the laser speckle diagram is outputted onto a film or a photographic dry plate, the laser speckle diagram on the film or the photographic dry plate is projected onto a surface of a measured object subsequently; a left view and a right view of the measured object are acquired finally, and all matching points corresponding to each other are found in the left view and the right view, and then a three dimensional point cloud of the surface of the measured object is reconstructed.

A scanning display system includes two detectors for rangefinding. Round trip times-of-flight are measured for reflections of laser pulses received at the detectors. A proportional correction factor is determined based at least in part on the geometry of the scanning display system. The proportional correction factor is applied to the measured times-of-flight to create estimates of more accurate times-of-flight.

Methods, systems, and computer programs are presented for object recognition performed by electronic devices. One method includes an operation for capturing three-dimensional (3D) images of a region over a surface using 3D cameras, the surface having a pattern and each 3D camera defining a respective camera coordinate system. For each camera, the 3D image is analyzed to identify a location of the pattern indicating an origin of a common coordinate system, and a coordinate transformation function is defined to convert data to the common coordinate system. Each 3D camera captures a 3D object image of an object on the surface that includes 3D object data. Further, the 3D object data is transformed to the common coordinate system to obtain transformed 3D object data. The 3D object data is combined to obtain a composite 3D object data, and object recognition of the object is performed based on the composite 3D object data.

A dental CAD/CAM application generates a 3D model representing a patient's dental anatomy. This model may be a 3D surface. The surface may also be textured with either a monochrome or color image superimposed. The display routine that is used to display the 3D model is enhanced to adjust the contrast in the region of a displayed mouse pointer (or other input device) as a user explores the display image. When this feature is activated and the mouse pointer positioned, preferably the texturing on the 3D model is recomputed in that local area and redisplayed showing greater contrast and detail. Preferably, the contrast is increased from a center to an edge of the area of contrast. Having the texturing of the model being improved and highlighted around the margin is desirable, as it allows the user to see more easily where the margin is located.

Apparatus and associated methods relate to ranging object(s) nearby an aircraft using triangulation of pulses of linearly-patterned light projected upon and reflected by the object(s). A light projector projects the pulses of linearly-patterned light in a controllable direction onto the scene external to the aircraft. A reflected portion of the projected pulses is focused onto a selected row or column of light-sensitive pixels of a two-dimensional array, thereby forming a row or column of image data. The direction of projected light and the row or column of pixels selected are coordinated so that the portion of the projected pulses reflected by the scene is received by the camera and focused on the selected one of the rows or columns of light-sensitive pixels. Location(s) and/or range(s) of object(s) in the scene are calculated, based on a projector location, a camera location, and the row or column of image data.