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.

The present application relates to methods and apparatuses for three-dimensional reconstruction of a transparent object, computer devices, and storage mediums. The method includes acquiring silhouettes and light correspondences of a to-be-reconstructed transparent object under different viewing directions, acquiring an initial rough transparent object model of the to-be-reconstructed transparent object, and filtering out light rays involved in multiple refractions and total reflections by backward ray tracing; acquiring surface normal vectors and Snell normal vectors of the initial rough transparent object model in camera device views, and performing a first optimization on the initial rough transparent object model by constraining consistency between the surface normal vectors and the Snell normal vectors of the initial rough transparent object model in the camera device views, and acquiring a point cloud reconstruction model; acquiring Poisson sample points of the initial rough transparent object model, and updating the point cloud reconstruction model according to the Poisson sample points.

The present application relates to methods and apparatuses for three-dimensional reconstruction of a transparent object, computer devices, and storage mediums. The method includes acquiring silhouettes and light correspondences of a to-be-reconstructed transparent object under different viewing directions, acquiring an initial rough transparent object model of the to-be-reconstructed transparent object, and filtering out light rays involved in multiple refractions and total reflections by backward ray tracing; acquiring surface normal vectors and Snell normal vectors of the initial rough transparent object model in camera device views, and performing a first optimization on the initial rough transparent object model by constraining consistency between the surface normal vectors and the Snell normal vectors of the initial rough transparent object model in the camera device views, and acquiring a point cloud reconstruction model; acquiring Poisson sample points of the initial rough transparent object model, and updating the point cloud reconstruction model according to the Poisson sample points; performing a second optimization on the updated point cloud reconstruction model according to the silhouettes of the to-be-reconstructed transparent object and projections of the updated point cloud reconstruction model; and performing a three-dimensional reconstruction on the optimized point cloud reconstruction model after the second optimization, to obtain a three-dimensional model. The complete surface of the transparent object can be restored by the present method.

The invention provides a method for controlling the generation of a compound ultrasonic image. The method includes obtaining a first ultrasound image and applying adaptive beamforming to the first ultrasound image, thereby generating a second ultrasound image. A weighting is determined based on the first and second ultrasound images, wherein the weighting comprises at least one weighting component. The compound ultrasound image is then generated based on the first and second ultrasound images and the weighting component.

The invention provides a method for controlling the generation of a compound ultrasonic image. The method includes obtaining a first ultrasound image and applying adaptive beamforming to the first ultrasound image, thereby generating a second ultrasound image. A weighting is determined based on the first and second ultrasound images, wherein the weighting comprises at least one weighting component. The compound ultrasound image is then generated based on the first and second ultrasound images and the weighting component.

The present disclosure generally relates to machine vision systems, illumination sources for use in machine vision systems, and components for use in the illumination sources. More specifically, the present disclosure relates to machine vision systems incorporating multi-function illumination sources, multi-function illumination sources, and components for use in multi-function illumination sources.

The present disclosure generally relates to machine vision systems, illumination sources for use in machine vision systems, and components for use in the illumination sources. More specifically, the present disclosure relates to machine vision systems incorporating multi-function illumination sources, multi-function illumination sources, and components for use in multi-function illumination sources.

Embodiments of this application provide a method for obtaining depth information and an electronic device. The method is applied to the field of image processing technologies and can help an electronic device improve accuracy of obtaining depth information. A specific solution includes: The electronic device includes a first camera, a second camera, and an infrared projector. The electronic device receives a first instruction used to trigger the electronic device to obtain depth information of a target object; in response to the first instruction, transmits infrared light with a light spot by using an infrared projector; collects first image information of the target object by using the first camera; collects second image information of the target object by using the second camera, where the first image information and the second image information include a feature of the target object and a texture feature formed when infrared light with a light spot is irradiated onto the target object; and calculates depth information of the target object based on the first image information, the second image information, the first length, a lens focal length of the first camera, and a lens focal length of the second camera.

Embodiments of this application provide a method for obtaining depth information and an electronic device. The method is applied to the field of image processing technologies and can help an electronic device improve accuracy of obtaining depth information. A specific solution includes: The electronic device includes a first camera, a second camera, and an infrared projector. The electronic device receives a first instruction used to trigger the electronic device to obtain depth information of a target object; in response to the first instruction, transmits infrared light with a light spot by using an infrared projector; collects first image information of the target object by using the first camera; collects second image information of the target object by using the second camera, where the first image information and the second image information include a feature of the target object and a texture feature formed when infrared light with a light spot is irradiated onto the target object; and calculates depth information of the target object based on the first image information, the second image information, the first length, a lens focal length of the first camera, and a lens focal length of the second camera.

A system and method for compensating for reflections caused by light-generating objects in the scene facing a display device includes capturing images of the scene. Reflection-inducting zones corresponding to the light generating objects are identified from the captured images. The reflection effect on the display device from the reflection-inducing zones are estimated. A target image to be displayed on the display device is adjusted based on the estimated reflection effect.