Abstract: Systems and methods for training a machine vision system create geometric models. The disclosed methods can extract one or more corresponding features and one or more differentiating features from different sets of training images. The one or more differentiating features can be used to differentiate between the different work pieces. The disclosed methods can generate an alignment model using the corresponding features and a classification model using the one or more differentiating features.

Abstract: The disclosed apparatus, systems, and methods can process height maps. For example, the disclosed computerized method of determining posture information of an object in a two-dimensional height map captured by a range sensor system can include receiving the height map of the object captured by the range sensor system, generating a plurality of one-dimensional slices of the height map and a location record indicating locations of the plurality of one-dimensional slices on the height map, identifying points of interest in the plurality of one-dimensional slices, determining locations of the identified points of interest in the height map based on the location record, and determining the posture information of the object based on the locations of the identified points of interest in the height map.

Abstract: This invention provides a system for measuring displacement of an object surface having a displacement sensor that projects a line on the object surface and receives light from the projected line at an imager in a manner defines a plurality of displacement values in a height direction. A vision system processor operates on rows of imager pixels to determine a laser line center in columns of imager pixels in each of a plurality of regions of interest. Each region of interest defines a plurality of rows that correspond with expected locations of the projected line on the object surface. A GUI can be used to establish the regions. In further embodiments, the system generates grayscale images with the imager. These grayscale images can be compared to a generated height image to compensate for contrast-induced false height readings. Imager pixels can be compared to a reference voltage to locate the line.

Abstract: Systems and methods are provided for decoding barcodes. A scan signal is acquired along a scan through a barcode. A first character unit grid for a unit width pattern within the barcode along the scan is determined. At least one set of sampling coefficients relating the unit width pattern to a portion of the scan signal is determined based on the first character unit grid. The element width pattern for the unit width pattern is determined based on the at least one set of sampling coefficients and the portion of the scan signal.

Abstract: Systems and methods are described for acquiring and decoding a plurality of images. First images are acquired and then processed to attempt to decode a symbol. Contributions of the first images to the decoding attempt are identified. An updated acquisition-settings order is determined based at least partly upon the contributions of the first images to the decoding attempt. Second images are acquired or processed based at least partly upon the updated acquisition-settings order.

Abstract: Methods and apparatus are disclosed for extracting a one-dimensional digital signal from a two-dimensional digital image along a projection line. In some embodiments a repeating sequence of pixel weight templates, and a sequence of relative positions, are selected in response to the orientation of a projection line and used to compute a sequence of weighted sums. The sequence can be selected to achieve desirable properties, for example photometric accuracy, geometric accuracy, resolution, and/or noise reduction. In some embodiments registers and multiply-accumulators are arranged and controlled so as to compute the 1D signal.

Abstract: The disclosed apparatus, systems, and methods provide for a displacement sensor with a multi-position image sensor. The displacement sensor includes an optical lens. The displacement sensor includes an image sensor configured to view an object through the lens along a plane of focus that is not parallel to an image plane of the image sensor. The displacement sensor includes a laser for illuminating the object by the displacement sensor, wherein the laser is: spaced from the lens at a fixed distance, and configured to project a line of light along the plane of focus of the image sensor. The displacement sensor comprises a first configuration wherein the image sensor is at a first location along an image plane with a first field of view along the plane of focus, and a second configuration at a second location with a different field of view.

Abstract: Vision systems including a swappable camera and methods of making and using the swappable camera are disclosed. The swappable camera can include an alignment indicator storing alignment data representative of an array-housing alignment of a sensor array relative to a camera housing. The swappable camera can have a desired sensor array position. A region of interest that is concentric with the desired sensor array position can be determined using the alignment data and an image can be acquired using only pixels of the sensor array that are located within the region of interest.

Abstract: Systems and methods reduce temperature induced drift effects on a liquid lens used in a vision system. A feedback loop receives a temperature value from a temperature sensor, and based on the received temperature value, controls a power to the heating element based on a difference between the measured temperature of the liquid lens and a predetermined control temperature to maintain the temperature value within a predetermined control temperature range to reduce the effects of drift. A processor can also control a bias signal applied to the lens or a lens actuator to control temperature variations and the associated induced drift effects. An image sharpness can also be determined over a series of images, alone or in combination with controlling the temperature of the liquid lens, to adjust a focal distance of the lens.

Abstract: This invention provides a system and method for determining the pose of shapes that are known to a vision system that undergo both affine transformation and deformation. The object image with fiducial is acquired. The fiducial has affine parameters, including degrees of freedom (DOFs), search ranges and search step sizes, and control points with associated DOFs and step sizes. Each 2D affine parameter's search range and the distortion control points' DOFs are sampled and all combinations are obtained. The coarsely specified fiducial is transformed for each combination and a match metric is computed for the transformed fiducial, generating a score surface. Peaks are computed on this surface, as potential candidates, which are refined until a match metric is maximized. The refined representation exceeding a predetermined score is returned as potential shapes in the scene. Alternately the candidate with the best score can be used as a training fiducial.

Abstract: Methods, systems, and devices involving patterned radiation are provided in accordance with various embodiments. Some embodiments include a device for projecting pattern radiation. Some embodiments include a method for estimating coordinates of a location on an object in a 3D scene. Some embodiments include a system for estimating the coordinates of a location on an object in a 3D scene. A variety of radiation patterns are provided in accordance with various embodiments. Some embodiments may relate to the use of patterned illumination to identify the angular information that may be utilized to measure depth by triangulation.

Abstract: A handheld device and method using the device, the device comprising a sensor receiving light from within a field of view (FOV) to generate a plurality of consecutive images of the FOV, a structured light source that is controllable to generate a plurality of light patterns, the source arranged to project at least one light patterns into the FOV where at least a portion of a pattern reflects from an object and is captured by the sensor and a processor to receive images, the processor programmed to control the source to project a pattern into the FOV, locate the pattern in at least one of the generated images, locate discontinuities in the pattern and use the discontinuities to measure at least one dimension.

Abstract: This invention provides a tool for tightening and loosening lenses with respect to camera bodies. The tool includes a body that defines a cavity that is slightly larger in diameter than the sidewalls of the lens adjacent the lens face. Within the cavity is a thin, high-friction, elastomeric material that resides between the edges of the lens when the cavity is pressurably engaged over the lens face. The material frictionally couples the tool body to the lens face and adjacent side walls, thereby allowing a predetermined level of torque to be applied to tighten or loosen the lens. The tool can be adapted for attachment to a handle, such as a torque wrench or can include a handle specifically adapted/contoured for grasping by a user's hand.

Abstract: A system and method for detecting and/or determining the existence of displacement of a substrate with respect to a surrounding object uses a laser line that is free of contact with the object and that is received by an image sensor. A processor reads the line information in a series of image frames, and generates a range image with height information. The height information is provided to a 2D map. Differences between adjacent height measurements, and averages, are computed. Vision system tools are used to accurately locate features in the image and these are aligned with the height information. The height differences are interpreted, with missing height data due, for example, to specularity in the image being approximated. The height differences are compared to predetermined height parameters relative to identified locations, for example, wells, in the object to determine whether a substrate is displaced.

Abstract: The present disclosure provides a multi-stage image mapping mechanism for mapping a distorted image to a rectified image. For example, the multi-stage image mapping mechanism can remove homography from a distorted image to reconstruct a rectified image in two-stages: (1) a first stage in which distortion is partially removed from a distorted image to generate an intermediate image, and (2) a second stage in which residual distortion is removed from the intermediate image to recover the rectified image.

Abstract: Systems and methods provide an illumination assembly for a mark reader. A light transmitter is arranged in a surrounding relationship to an interior area, with the light transmitter having a proximal end and a distal end. An illumination source provides a light for transmission into the light transmitter. The light transmitter distal end allows the light from within the light transmitter to pass through and out of the distal end to provide bright field illumination and dark field illumination. The light transmitter distal end may include a first portion and a second portion, where light from within the light transmitter passes through and out of the first portion to provide bright field illumination, and light from within the light transmitter passes through and out of the second portion to provide dark field illumination.

Abstract: A method and system for specifying an area of interest in a 3D imaging system including a plurality of cameras that include at least first and second cameras wherein each camera has a field of view arranged along a camera distinct trajectory, the method comprising the steps of presenting a part at a location within the fields of view of the plurality of cameras, indicating on the part an area of interest that is within the field of view of each of the plurality of cameras, for each of the plurality of cameras: (i) acquiring at least one image of the part including the area of interest, (ii) identifying a camera specific field of interest within the field of view of the camera associated with the area of interest in the at least one image and (iii) storing the field of interest for subsequent use.

Abstract: An electronic device includes a threaded spacer and a biasing element to reduce backlash. The threaded spacer includes a thread end point that is offset from the thread start point of the carrier frame. The offset thread ending and starting points create a gap between the threaded spacer and the carrier frame. The biasing element applies a force to the threaded spacer, thereby reducing the backlash between the lens and the carrier frame, while at the same time allowing the lens to be rotated for focus adjustments.

Abstract: This invention provides a system and method for the high-accuracy measurement of an object's surface displacement at a plurality of measurement points using a laser displacement sensor and a sensor process that corrects for noise and other accuracy-reducing factors. A camera assembly with an imager and optics package acquires images of an object surface, and a laser assembly projects a line on the object surface. These tasks can include (a) defining patches of the surface based upon a grid; (b) registering the object and aligning the grid with respect to the object; (c) excluding from the analysis of the image, irregular surface features; (d) oversampling one or more patches to improve overall accuracy; (e) specifying measurement resolution (i.e. in the (x, y z) dimensions), including choosing appropriate pixel sizes and number of measurements per measurement point; and (f) selecting optimal acquisition/image formation parameters.

Abstract: A method and camera assembly for use in a machine vision system, the assembly comprising a support structure forming a mounting flange that is configured for coupling with any of a plurality of exchangeable electrically controllable adjustable focal length lens assemblies, a two dimensional image sensor supported by the support structure and forming a sensor plane spaced from the mounting flange by a flange focal distance and a processor programmed with a flange focal distance error and to use the flange focal distance error to generate lens control signals to compensate for the flange focal distance error when a lens is mounted to the mounting flange.