A calibrator for a camera includes a controlling circuit, a photographing circuit, a calculating circuit, and an instructing circuit. The controlling circuit is configured to control a movable body to move into a shooting area of the camera. A marker is provided on the movable body for calibration of the camera. The photographing circuit is configured to control the camera to photograph the marker. The calculating circuit is configured to calculate at least one parameter of the camera based on the photographed marker. The instructing circuit is configured to transmit the at least one parameter to the camera to calibrate the camera.

A computer system obtains, in electronic format, a training dataset. The training dataset comprises a plurality of training images from a plurality of agricultural plots. Each training image is from a respective agricultural plot in the plurality of agricultural plots and comprises at least one identified fruit. The computer system determines, for each respective fruit in each respective training image in the plurality of training images, a corresponding contour. The computer system trains an untrained or partially trained computational model using at least the corresponding contour for each respective fruit in each respective training image in the plurality of training images, thereby obtaining a first trained computational model that is configured to identify fruit in agricultural plot images.

A method and apparatus for the automatic calibration method described in this application provides an integrated framework for performing a reliable and objective estimation of IMU-LiDAR latency and boresight angles. This method, based on the estimation of calibration parameters through the resolution of observation equations is able to deliver boresight and latency estimates as well as their precision. A new calibration method for the boresight method angles between a LiDAR and an IMU, based on an automatic data selection algorithm, followed by the adjustment of bore sight angles. This method, called LIBAC (LiDAR-IMU Boresight Automatic Calibration), takes in input overlapping survey strips following a sample line pattern over a regular slope. First, construct a boresight error observability criterion, used to select automatically the most sensitive soundings to boresight errors. From these soundings, adjust the boresight angle 3D, thus taking into account the coupling between angles. From a statistical analysis of the adjustment results, we derive the boresight precision.

A flying drone for inspecting surfaces able to reflect light has a lighting device formed of two light sources each having a shape that is elongate in a longitudinal direction of each of the light sources, two first image acquisition devices, and a second image acquisition device between the two first image acquisition devices. The two light sources are respectively between the second image acquisition device and each of the first image acquisition devices. The flying drone allows effective detection of dents in surfaces by analyzing specular reflections, by the lighting device and of the first image acquisition devices, and effective detection of superficial defects on surfaces by the second image acquisition device, with the lighting device switched off.

Systems, methods, and computer-readable media are described herein to model divergent beam ray paths between locations on a roof (e.g., of a structure) and modeled locations of the sun at different times of the day and different days during a week, month, year, or another time period. Obstructed and unobstructed divergent beam ray paths are identified. Unobstructed divergent beam ray paths contribute to the calculation of a solar irradiance value for each location on the roof. Divergent beam ray paths, such as cones or pyramid ray paths, allow for sparse or lower-resolution spatial and/or temporal sampling without sacrificing obstacle detection.

A user device may include a memory and a processor. The user device may send, via a cellular network, instructions to an unmanned aerial vehicle (UAV). The instructions may include instructions to capture a plurality of first images while the UAV is in flight. The user device may receive, while the UAV is in flight, one or more second images via a wireless wide area network. The one or more second images may be lower resolution versions of a subset of the first plurality of images. The user device may store the one or more second images at the user device.

A control method for a mobile robot includes: obtaining indication information of a target object, wherein the indication information includes position information of the target object in a reference image output by a photographic apparatus of a mobile robot; determining the position information of the target object according to the indication information; and controlling, according to the position information of the target object, the mobile robot to move around the target object. With the provided control methods and apparatuses, devices, and storage media, the mobile robot may move around the target object without needing to move to a circling center to record a position of the circling center.

A center C of a connecting portion coincides with a center U of lift generated in a body of a rotary-wing aircraft. The center C of the connecting portion is a point of action of gravitational force of a support rod and a first mounting portion with respect to the connecting portion. The center U of the lift is a point of action of the lift on the rotary-wing aircraft and is the center of rotation of the connecting portion.

Provided are a computer system and method using image analysis for controlling a flight path of a surface inspection unmanned aerial vehicle, wherein the computer system is configured to: acquire an image captured by a drone; perform image analysis on the acquired image; extract, in a result of the image analysis, a point whose an edge variation amount is equal to or greater than a predetermined threshold; acquire a position coordinate of the extracted point; in a case where there are a plurality of points, set a flight path of the drone in a manner of flying in an order of edge variation amounts of the plurality of points from large to small; and control the drone to fly towards the acquired position coordinate and perform capturing with a camera using light other than visible light.

Computerized systems and methods are disclosed, including a computer system that executes software that may receive a geographic location having one or more coordinates of a structure, receive a validation of the structure location, and generate unmanned aircraft information based on the one or more coordinates of the validated location. The unmanned aircraft information may include an offset from the walls of the structure to direct an unmanned aircraft to fly an autonomous flight path offset from the walls, and camera control information to direct a camera of the unmanned aircraft to capture images of the walls at a predetermined time interval while the unmanned aircraft is flying the flight path. The computer system may receive images of the walls captured by the camera while the unmanned aircraft is flying the autonomous flight path and generate a structure report based at least in part on the images.