31 results about "Stereo imaging" patented technology

Embodiments of the present disclosure relate to surface estimation using stereo imaging and surface disparities. For example, a surface disparity field representing a surface in the environment (e.g., the ground) may be estimated from stereo image data and used for various downstream tasks. For example, the difference between a stereo disparity field and a ground disparity field may be used to detect objects, a representation of a navigable space may be generated by radially casting 2D rays in the ground disparity field, the ground disparity field may be used to compensate ego-motion for high dynamic attitude changes, and / or the ground disparity field may be lifted to 3D and used to fit a surface profile to points sampled from the lifted point cloud.

Embodiments of the present disclosure relate to surface estimation using stereo imaging and surface disparities. For example, a three-dimensional (3D) surface structure may be modeled as a disparity field, and a surface disparity field representing a surface in the environment (e.g., the ground) may be generated using a constrained nonlinear hierarchical optimization to process stereo image data and iteratively refine estimated surface disparity values based on weights that guide the optimization to expected surface values (e.g., ground, road). The resulting surface (e.g., ground) disparity field may be used for a variety of downstream tasks, such as obstacle detection, segmentation of a navigable space, ego-motion refinement, and / or generation of an estimated surface profile.

Systems and methods for calibrating a stereo imaging device are disclosed herein. An example implementation includes receiving, at a processor, a plurality of image pairs from a stereo imaging device, and for each image pair of the plurality of image pairs, computing a respective line delta value indicative of a deviation along a horizontal axis between a first image captured by a first sensor and a second image captured by a second sensor. The implementation also includes determining a median line delta value based on each respective line delta value and subsequently determining a respective set of disparities in one or more features in the first image and the second image based on the median line delta value. The method also includes computing a column delta value and calibrating the stereo imaging device using the median line delta value and the column delta value.

The invention provides a stereoscopic display method for a video conference and a video conference system. The stereoscopic display method of the video conference comprises the following steps. A first electronic device generates an image. The first electronic device encodes a hidden watermark into an image. The first electronic device transmits an image to a second electronic device. The second electronic device displays the image on a window of a display picture. The second electronic device searches a rectangular frame on the display picture; the second electronic device determines whether the hidden watermark is decoded in the rectangular frame. If the hidden watermark is decoded in the rectangular frame, the second electronic device performs stereo imaging on the content of the rectangular frame.

The application is suitable for the field of optical imaging technology, and provides a stereo imaging optical system for civil small unmanned aerial vehicle, which is composed of a spherical positive lens, two groups of double cemented spherical lenses, an aperture, a convex spherical mirror and a concave parabolic mirror, wherein the two groups of double cemented spherical lenses include a first double cemented spherical lens and a second double cemented spherical lens; the application can realize high-resolution imaging at multiple wavelengths, provide rich spectral information for users, and help to more accurately analyze and judge the target area. The compact design makes the system small in size and light in weight, and is very suitable for being mounted on low-altitude civil small unmanned aerial vehicle, thereby expanding the application range and operation ability of the civil unmanned aerial vehicle. The stereo imaging function can obtain three-dimensional information of the target area, and has important application value in the fields of geographic mapping and city planning, and can provide more comprehensive and accurate data compared with the traditional imaging mode.

Systems and methods for self-calibration of a stereo system without prior knowledge of the scene are disclosed herein. For example, a method for calibrating a stereo imaging system may comprise extracting a set of feature points from a first image captured from a first view of a stereo image and a second image captured from a second view and matching the set of feature points between the two images to form a list of matched points. The method may also comprise iteratively adjusting a tilt calibration value (Rx) and a roll calibration value (Rz) based on a y-dimension parallax value in the list of matched points, determining a set of x-dimension parallax values for the set of feature points, and adjusting a convergence calibration value (Ry) of the stereo imaging system. The method may be performed while the system is in operation without the need for a special calibration setup.

The invention relates to ground surface estimation using stereoscopic imaging for autonomous and semi-autonomous systems and applications. Embodiments of the present disclosure relate to surface estimation with stereoscopic imaging and surface disparity. For example, a three-dimensional (3D) surface structure may be modeled as a disparity field, and a surface disparity field representing a surface (e.g., ground) in an environment may be generated using a constrained non-linear hierarchical optimization that is used to process stereoscopic image data, such as stereoscopic image data. And iteratively refining the estimated surface disparity values based on weights that guide the optimization to expected surface values (e.g., ground, road). The resulting surface (e.g., ground) disparity field may be used for various downstream tasks, such as obstacle detection, airworthiness space segmentation, self-motion refinement, and / or generation of an estimated surface profile.

The invention discloses a naked eye stereo imaging intelligent photo frame, and relates to the technical field of intelligent photo frames, the naked eye stereo imaging intelligent photo frame comprises a shell, one side of the shell is provided with a front shell, and the other side of the shell is provided with a rear shell; the display module is mounted in the shell; the adjusting assembly is installed in the shell and located on the periphery of the display module; the adjusting frame is fixed on the adjusting assembly; and the stereo imaging module is fixed in the adjusting frame and is arranged corresponding to the display module.

The invention belongs to the technical field of remote image transmission, stereoscopic vision imaging and head-mounted display, and particularly relates to a remote real-time three-dimensional image transmission system and method based on double-camera stereoscopic imaging. And after dynamic calibration and parallax coding, the three-dimensional images are transmitted to a head-mounted display helmet through an extended communication protocol (such as Skype API), so that high-precision and low-delay remote interaction of the three-dimensional images is realized. The system solves the problem that traditional 2D transmission lacks depth information, and is suitable for scenes such as immersive remote cooperation and virtual reality social contact.

Systems and methods related to converting 3D point clouds to confidence-scored 3D grids for height mapping in stereo imaging systems are disclosed herein. A height map may be generated for a physical surface from a point cloud. The point cloud may be captured using a stereo camera system, where the point cloud comprises a list of three-dimensional coordinates for a set of points on the physical surface. A grid map may be generated from the point cloud, where the grid map comprises a set of centroid points with confidence scores for a set of voxels of the grid map. The height map may be generated from the grid map, where the height map comprises a set of height values derived using the set of confidence scores. The height map may have increased accuracy, for example by removing outliers and reducing noise.

The path planning method for a stereo imaging inspection machine for PCB boards includes the following steps: S1. First, analyze and process the dimensional data of the PCB board and the two camera lens modules, including equipment parameters and inspection board data; S2. Divide the inspection board into regions based on the two camera lens modules. Constrain the working range of the camera lens modules according to their size and travel range. Design an 8-region division method based on the hole position characteristics of the inspection board; S3. Establish an integer programming model for pairing and scheduling regional tasks of the two camera lens modules. Based on the division results of the 8 working regions, pre-allocate the inspection task groups of the two camera lens modules; S4. Use a single-region path planning algorithm, employing a variable neighborhood search algorithm to solve for the shortest path connecting all inspection holes in the current region for a single camera lens module. This solution aims to prevent collision and interference problems between the two sets of cameras when collaboratively imaging PCB boards using stereo cameras.

The invention discloses a binocular camera module calibration method and system, electronic equipment and a storage medium, and relates to the technical field of camera calibration. According to the method, a test camera module is controlled to shoot multiple groups of calibration plate images at different preset positions, and parameters such as an internal reference matrix, a rotation matrix and a translation vector of a camera are iteratively solved through processing such as image segmentation, graying, angular point extraction and accurate positioning, so that a correction transformation matrix is generated to calibrate the test camera module; high-precision calibration of the binocular camera module is achieved, it is ensured that the optical axes of the two lenses are horizontally aligned, the precision of the distance between the lenses reaches the standard, and stereo imaging matching and biological characteristic collection accuracy are ensured. By implementing the technical scheme provided by the invention, the function stability and the performance consistency of the product can be improved, and the high requirement on the product performance in batch production can be met.

Systems and methods related to volumetric estimation using a stereo camera are disclosed herein. The stereo camera, with two or more imagers, may belong to a stereo imaging system. The camera may be static. The system may determine a first height map corresponding to a reference surface, a second height map corresponding to a physical object on the reference surface, and a difference map including height differences between the first height map and the second height map. The height maps may be derived from point clouds. Based on the difference map, the system may detect the presence of the physical object. The volume of the physical object may be determined, and the object may be identified based on its volume.

Systems and methods for operating a mobile robot is disclosed. The system can include a pair of stereo imaging devices mounted on the mobile robot, a memory storing a current baseline, and a processor. The pair of stereo imaging devices include a first and a second imaging device. The current baseline is representative of a distance between the first and the second imaging devices. The processor is operable to: autonomously navigate the mobile robot to a visual target; while the visual target is within viewing range, capture an image of the visual target; generate a plurality of depth measurements from the image; compare the plurality of depth measurements with corresponding depth estimates; and update the current baseline based on the comparisons. The mobile robot is operable to autonomously execute a mission within an environment; and while executing the mission, use the current baseline for sensing the environment.

The invention discloses a high-speed stereo imaging method and device based on monocular pulse time domain modulation, and the method comprises the steps: introducing a periodic time domain modulation signal into a light path, and printing a unique time label for an image at a specific visual angle in a mixed light intensity signal; by means of the capturing capacity of the pulse camera for high-frequency modulation signals, mixed images which are originally difficult to separate in space can be effectively distinguished in the time domain, and therefore the advantages of being compact in hardware and free of geometric distortion of a monocular system are kept, high-frame-rate and high-precision stereoscopic video reconstruction is achieved at the same time, and the high-resolution and high-precision stereoscopic video reconstruction is achieved. And the technical blank in the field of high-speed monocular stereoscopic vision is effectively filled.

When arranging two optical systems in parallel, miniaturization is achieved while avoiding interference between the image sensors. [Solution] The stereo imaging system 10 comprises two imaging devices 11 and 12, each having an optical system including a first lens group L1, arranged so that the first lens groups are in parallel. The optical system of each of the two imaging devices includes a first optical element 121 that branches the optical path from the first lens group into a first optical path extending in a direction different from the optical axis direction of the first lens group and a second optical path extending in a direction different from the first optical path, a second lens group L21 arranged on the first optical path and having a positive refractive power toward the first imaging plane, a second optical element 122 that bends the second optical path, and a third lens group L22 arranged on the second optical path bent by the second optical element and having a positive refractive power toward the second imaging plane. The bending direction of the second optical path by the second optical element in each of the two imaging devices is different from that of the other.

The defective product removing device based on the 3D machine vision comprises a conveying assembly installed on the top of a base, a third electric telescopic rod is fixed to the outer wall of the top of the base, a lifting seat is fixed to the output end of the third electric telescopic rod, and the inner wall of the lifting seat is movably connected with a mounting frame through a rotating shaft; a placement plate is fixed to the top of the mounting frame and is driven by a driving part, a connecting rod is fixed to the outer wall of one side of the placement plate, a partition plate is fixed to the end, away from the placement plate, of the connecting rod, and a 3D visual camera is fixed to the side wall of the partition plate. According to the utility model, three-dimensional data of the surface of the workpiece is obtained by the 3D visual camera by utilizing an optical projection or stereo imaging technology, high-precision quality detection is carried out by combining a geometric algorithm and a machine learning algorithm, defects of the workpiece can be accurately identified, defective products and qualified products are efficiently distinguished, and the partition plate moves downwards to isolate adjacent workpieces to avoid detection interference.

Systems and methods related to performing material density estimates are disclosed herein. A stereo imaging system may include a stereo camera and one or more processors. The stereo imaging system may capture a point cloud using the stereo camera, determine a region of interest using the point cloud, differentiate material components from a two-dimensional image to produce a filter, produce a filtered point cloud by (i) filtering the point cloud using the filter; and (ii) excluding points from the point cloud using the region of interest, and generate a material density estimate, for the material components, using the filtered point cloud. The material density estimate may allow the system to perform appropriate actions. For example, the material density estimate may allow the system to spray an appropriate amount of chemical on crops, reducing detrimental environmental effects, reducing costs, and improving yields.

The application provides a monocular endoscope stereo imaging system and a three-dimensional measurement method, and relates to the technical field of endoscope imaging. The monocular endoscope stereo imaging system comprises a monocular endoscope body and an optical prism body, the monocular endoscope body is internally provided with an imaging unit and a lens unit, first incident light and second incident light correspondingly form first image information and second image information on the imaging unit after being reflected by the optical prism body, the first image information and the second image information have horizontal parallax, and the first image information and the second image information after stereo correction have no vertical parallax. The monocular endoscope stereo imaging system provided by the application can realize stereo imaging based on a single camera structure, overcome the defects of the prior art, reduce the hardware size, reduce the development cost, and improve the image quality.

The application provides a ship precise positioning method and system based on three-dimensional depth feature extraction, comprising the following steps: S1, based on the optical stereo imaging principle, combined with the photographic pose data, a plurality of view images imaged at different angles and different distances are acquired; S2, a region of interest frame is identified in the acquired images, the ship target in the images is framed, and key point identification is performed on the target in the region of interest; S3, the key points containing semantics are identified, and the key points identified in the images photographed at different angles are paired according to semantic labels; S4, the target is classified and identified by using the three-dimensional space coordinate information of the key points, the real model in the database is virtually arranged into the body coordinate system according to the position of the key points in the space after the ship model is identified, and the false alarm and the missed detection of the ship target caused by noise interference and environmental interference are reduced; and the application can capture more feature points, and the identification accuracy is greatly improved.

[Problem] To downsize while avoiding interference between imaging elements when two optical systems are arranged in parallel. [Solution] In this stereo imaging system (10), two imaging devices (11, 12) each having an optical system including a first lens group (L1) are arranged such that the first lens groups are arranged in parallel. The optical system of each of the two imaging devices has: a first optical element (121) that splits an optical path from the first lens group into a first optical path extending in a direction different from the optical axis direction of the first lens group and a second optical path extending in a direction different from the first optical path; a second lens group (L21) disposed on the first optical path and having positive refractive power toward a first imaging surface; a second optical element (122) that bends the second optical path; and a third lens group (L22) disposed on the second optical path bent by the second optical element and having positive refractive power toward a second imaging surface. The respective bending directions in which the second optical path is bent by the second optical element in each of the two imaging devices are different from each other.

This application relates to the field of remote sensing image information processing, specifically disclosing a method for constructing a 3D urban model based on high-resolution stereo imaging satellite imagery. The method includes: extracting the top building outline of a target building from the satellite imagery; obtaining the top height information of the target building based on the corresponding Digital Surface Model (DSM) imagery; offsetting the top building outline to obtain the bottom building outline of the target building; and establishing a 3D model of the target building based on the bottom building outline and the top height information. This application utilizes satellite imagery to achieve rapid, efficient, and accurate construction of a 3D urban model at LOD 1.3.

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for detection of pixel correspondences in stereo imaging through the use of polarization data. One of the methods include: obtaining a first image from a first viewpoint of a stereo pair and a second image from a second viewpoint of the stereo pair; obtaining an angle of linear polarization (AOLP) map and a degree of linear polarization (DOLP) map having a field of view overlapping the first image and the second image; computing a surface normal map based on the AOLP map and the DOLP map; and detecting corresponding pixels between the first image and the second image by computing a disparity map that minimizes an energy function comprising a pixel matching cost term and a polarized smoothness regularization term computed based on pixels in a local neighborhood and based on the surface normal map.

Embodiments of the present disclosure relate to surface estimation using stereo imaging and surface disparities. For example, a three-dimensional (3D) surface structure can be modeled as a disparity field, and a surface disparity field representing a surface in the environment (e.g., the ground) can be generated using constrained nonlinear hierarchical optimization to process stereo image data and iteratively refine estimated surface disparity values ​​based on weights that lead the optimization to expected surface values ​​(e.g., ground, road). The resulting surface disparity field (e.g., ground) can be used for a variety of downstream tasks, such as obstacle detection, segmentation of a navigable space, self-motion refinement, and / or generation of an estimated surface profile.

Example techniques relate to stereo imaging with audio playback devices. Example playback devices described herein may include multiple speakers, such as a forward-firing audio transducer and side-firing audio transducers. Using example techniques, such playback devices may play stereo content partially directly and partially as a dipole, which may enhance (e.g., widen) a stereo image formed by the transducers. Yet further, such techniques may be combined with steering techniques to direct output of the transducers away from obstructions that may be present in proximity to the audio playback devices.

The invention discloses a foundation pit dual stereo imaging and detection method and device based on a laser radar and a visible light camera, and belongs to the technical field of foundation pit construction. The invention discloses a foundation pit dual stereo imaging and detection method based on a laser radar and a visible light camera. Measurement and parameter calculation are carried out on a foundation pit through a detection module provided with the laser radar and a high-definition camera; comprising the following steps: S1, data acquisition; s2, carrying out 3D SLAM real-time mapping; the method comprises the following steps: performing real-time mapping, publishing and previewing by improving a Cartograph algorithm, and storing a PCD point cloud file for subsequent foundation pit parameter calculation; s3, performing three-dimensional reconstruction on the image; performing video three-dimensional modeling by using the COLMAP and the instance-NGP; s4, calculating parameters of the foundation pit; according to the method, key parameters such as the depth, the hole diameter and the hole perpendicularity of the foundation pit can be rapidly and accurately obtained, and the quality control and safety management requirements of electric power engineering are met.

The invention discloses a 250-1800 nanometer hyperspectral ultra-wide field-of-view stereo imaging spectrometer, and belongs to the technical field of remote sensing spectral imaging, the 250-1800 nanometer hyperspectral ultra-wide field-of-view stereo imaging spectrometer comprises a front-view detection module, a front-view detection module and a rear-view detection module, and each detection module comprises a first microlens array, a plurality of optical fibers, a plurality of second microlens arrays and a plurality of spectrum detection assemblies. The first micro-lens array collects incident light of a one-dimensional ultra-wide field of view, the incident light is transmitted to the corresponding second micro-lens array through the optical fiber for collimation, and the incident light is received by the detector after being split by the optical filter and the plane transmission grating. According to the imaging spectrometer provided by the invention, the working wave band is divided into a plurality of continuous sub-wave bands, excellent spectral resolution is realized in each sub-wave band, high-resolution spectral imaging in an ultra-wide spectral range of 250-1800 nanometers is finally realized, and the imaging spectrometer is very suitable for remote sensing broad-spectrum wide-area spectrum detailed investigation and three-dimensional imaging measurement systems.

The invention discloses a low-cost real-time monocular stereo imaging method and system based on aperture modulation. A switchable half-aperture shielding mask is arranged on an aperture diaphragm at an aberration balance position of the lens or a conjugate pupil plane of the aperture diaphragm, and two images are obtained by switching between a shielding state and a full-open state and respectively exposing through a driving device. And the processing module performs difference processing on the two frames so as to obtain an image from the complementary half aperture. At the moment, parallax exists between the two half-aperture pictures, and scene parallax is directly output by using an optical flow estimation model and other algorithms and is converted into a depth map or is regarded as a pixel-by-pixel slope in sparse light field retrieval EPI to obtain the depth map. Under the condition that double lenses or a complex beam splitter prism are not introduced, a single sensor can obtain a two-view-angle image by using a cheap mask and a driving device, the image does not need to be inverted and reconstructed, and the device has the advantages of being simple in structure, capable of being shared with conventional imaging, capable of achieving real-time imaging, capable of being deployed to various embedded devices and mobile terminals with limited computing power and the like.

Example techniques relate to stereo imaging with audio playback devices. Example playback devices described herein may include multiple speakers, such as a forward-firing audio transducer and side-firing audio transducers. Using example techniques, such playback devices may play stereo content partially directly and partially as a dipole, which may enhance (e.g., widen) a stereo image formed by the transducers. Yet further, such techniques may be combined with steering techniques to direct output of the transducers away from obstructions that may be present in proximity to the audio playback devices.

Systems and methods related to performing material density estimates are disclosed herein. A stereo imaging system may include a stereo camera and one or more processors. The stereo imaging system may capture a point cloud using the stereo camera, determine a region of interest using the point cloud, differentiate material components from a two- dimensional image to produce a filter, produce a filtered point cloud by (i) filtering the point cloud using the filter; and (ii) excluding points from the point cloud using the region of interest, and generate a material density estimate, for the material components, using the filtered point cloud. The material density estimate may allow the system to perform appropriate actions. For example, the material density estimate may allow the system to spray an appropriate amount of chemical on crops, reducing detrimental environmental effects, reducing costs, and improving yields.