A stereo camera adjustment system disposes an adjustment plate that displays an adjustment chart for adjusting deviation of image information caused by position misalignment of the stereo camera at a predetermined position relative to a vehicle mounted with a stereo camera, capture an image of the adjustment chart, and process the captured image of the adjustment chart to correct the deviation of the image information. The stereo camera adjustment system includes a plate movement device that adjusts a disposed state of the adjustment plate relative to the vehicle, a detector that detects an attitude of the vehicle stopped at a defined position, and a controller that controls, based on the detected attitude of the vehicle, the plate movement device to adjust the disposed state of the adjustment plate such that the adjustment plate is at the predetermined position relative to the vehicle.

Camera compensation methods and systems that compensate for misalignment of sensors/camera in stereoscopic camera systems. The compensation includes identifying a pitch angle offset between a first camera and a second camera, determining misalignment of the first and second cameras from the identified pitch angle offset, determining a relative compensation delay responsive to the determined misalignment, introducing the relative compensation delay to image streams produced by the cameras, and producing a stereoscopic image on a display from the first and second image streams with the introduced delay.

A computerized system of performing fish census which otherwise requires high level of domain knowledge and expertise is described. Divers with minimal knowledge of fish can obtain high quality population and species distribution measurements using a stereo camera rig and fish video analyzer software that was developed. The system has two major components: a camera rig and software for fish size, density and biomass estimation. The camera rig consists of a simple stand on which one to four pairs of stereo cameras are mounted to take videos of the benthic floor for a few minutes. The collected videos are uploaded to a server which performs stereo analysis and image recognition. The software produces video clips containing estimates of fish size, density and species biodiversity and a log report containing information about the individual fishes for further end user analysis.

Embodiments of the present invention disclose a binocular image matching method, apparatus, device, and storage medium. The method comprises: performing target detection on a first image to obtain a first bounding box of a target in the first image; determining a second bounding box corresponding to the first bounding box in a second image; and obtaining a third bounding box of the target in the second image by regressing the second bounding box. The technical solutions realize accurate matching of targets in a binocular image without requiring performing target detection on both images in the binocular image, and then use a matching algorithm to match the targets detected in the two images, thereby greatly reducing the calculation overhead of target matching in the binocular image.

A system for self-calibrating sensors includes an electronic control unit, a first image sensor and a second image sensor communicatively coupled to the electronic control unit. The electronic control unit is configured to obtain a first image and a second image, where the first image and the second image contain an overlapping portion, determine an identity of an object present within the overlapping portion, obtain parameters of the identified object, determine a miscalibration of the first image sensor or the second image sensor based on a comparison of the identified object in the overlapping portions and the parameters of the identified object, in response to determining a miscalibration of the first image sensor or the second image sensor, calibrate the first image sensor or the second image sensor based on the parameters of the identified object and the second image or the first image, respectively.

A method includes receiving, from a multiscopic image capture system, a plurality of images depicting a scene. The method includes determining, by application of a neural network based on the plurality of images, a disparity map of the scene. The neural network includes a plurality of layers, and the layers include a rectification layer. The method include determining a matching error of the disparity map based on differences between corresponding pixels of two or more images associated with the disparity map. The method includes back-propagating the matching error to the rectification layer of the neural network. Back-propagating the matching error includes updating one or more weights applied to the rectification layer.

Embodiments are directed to a sensing system that employs beams to scan paths across an object such that sensors may the beams reflected by the scanned object. Events may be provided based on the detected signals and the paths such that each event may be associated with a sensor and event metrics. Crossing points for each sensor may be determined based on where the paths intersect the scanned object such that events associated with each sensor are associated with the crossing points for each sensor. Each crossing point of each sensor may be compared to each correspondent crossing point of each other sensor. Actual crossing points may be determined based on the comparison and the crossing points for each sensor. Position information for each sensor may be determined based on the actual crossing points.

A triangulation scanner having a projection unit, at least one first image acquisition unit and one second image acquisition unit and a control and processing unit for deriving distance measured values from image information. The scanner comprises a third image acquisition unit and a fourth image acquisition unit and an acquisition zoom functionality for activating or reading out the sensors such that a respective first acquisition state and a respective second acquisition state can be provided for each sensor. The acquisition of an image corresponding to a field of view defined by the respective acquisition zoom level is provided by each such acquisition zoom level thus definable, wherein the fields of view are each different.

A computer implemented method for calibrating a camera comprises the following steps carried out by computer hardware components: activating a subset of a plurality of light sources according to a plurality of activation schemes, wherein each activation scheme indicates which of the plurality of light sources to activate; capturing an image for each activation scheme using the camera; and calibrating the camera based on the captured images.

A method of monitoring turbine blade creep in a gas turbine engine is provided. The method includes: receiving stereo images of a turbine blade of a row of turbine blades, the images having been obtained using a stereo borescope located in the engine adjacent the row of turbine blades; identifying same features of the blade in each of the stereo images; mapping each of the identified features by triangulation onto a 3D space to produce a 3D depth map of at least part of the blade; providing a 3D reference model of the blade; and comparing the 3D reference model with the 3D depth map to measure one or more deviations in shape of the blade to determine an amount of creep-induced distortion of the blade.