35 results about "Stereoscopic depth" patented technology

Aspects relate to stereo depth estimation utilizing asymmetric down-sampling in different directions. A device may include one or more memories configured to store a plurality of images and a plurality of cameras. The plurality of cameras may be configured to capture a left and right image, in which, each of the images includes one or more patches, each patch including plurality of pixels. The device may include one or more processors coupled to one or more memories, in which, the one or more processors are configured to: down-sample in a first direction on a first set of pixels in a first patch of a first image to generate a first down-sample; and down-sample in a second direction on a second set of pixels in a second patch of a second image to generate a second down-sample, the second down-sample including a greater number of pixels.

The invention discloses a three-dimensional scene reconstruction method driven by monocular implicit depth features. The method comprises the following steps: extracting multi-view monocular depth features through a frozen monocular depth encoder; realizing cross-view feature alignment by using a geometry-vision similarity fusion module; generating a multi-scale monocular implicit depth feature through a multi-scale feature adaptive and processing module; a context modeling module and a feature pyramid network are adopted to extract multi-view context features; carrying out one-stage fusion with a monocular implicit depth feature to obtain a fusion feature; generating a depth map through the multi-view stereo depth estimation network; under the constraint of a depth map, generating spatial point features through multi-source feature projection sampling; performing two-stage fusion with the fusion features to generate point-level implicit features; optimizing the features through a frequency-space local-global gating mechanism; respectively inputting the optimization features into a Gaussian sputtering explicit rendering branch and a volume implicit rendering branch; and carrying out weighted fusion on the rendering result to generate a new view image.

The invention relates to a three-dimensional model reconstruction method and device based on a Gaussian sputtering model. The method comprises the following steps: acquiring a scene image of a sparse view angle of a target scene, and determining initialization parameter information of a Gaussian ellipsoid according to the scene image through a motion recovery structure technology and a Gaussian sputtering model; determining a priori depth, a color loss function and a gradient smoothing loss function through a monocular depth model according to a scene image; determining a reference depth according to the scene image through a multi-view three-dimensional depth estimation algorithm; determining a depth consistency loss function according to the prior depth and the reference depth; and updating the initialization parameter information through a Gaussian sputtering model based on a depth consistency loss function, a color loss function and a gradient smooth loss function, determining updated parameter information, and generating a three-dimensional model of the target scene according to the updated parameter information. The reliability and robustness of the three-dimensional model can be improved through depth prior constraint information and a dynamic gradient control method.

The application discloses a kind of super visual field 3D stereoscopic double camera technology systems (referred to as "super 3D"), belong to 3D image double camera technical field.Aiming at the problem of insufficient stereoscopic depth caused by fixed baseline parameter (6-6.5cm) in traditional 3D double camera, the parallax distortion and dizziness caused by 2D to 3D technology, this scheme proposes a kind of technical system based on double camera unit cooperative displacement and post parameter control.Through left camera unit horizontal transverse displacement (12-30cm) and angle rotation (1°-3°), combined with forced focal length ≥50mm optical parameter control module, expand double camera visual field 20%-50%, and use post reverse displacement compensation algorithm (close range 1-3%, medium 3-5%, long distance 5-10%), the main body of picture is aligned to natural focusing position of human eye, realize stereoscopic level enhancement 2-3 times, no distortion high immersive imaging effect.This scheme technical parameter is independent, and cannot be converted with traditional 3D video, ensure content quality from source, applicable to film and television, VR, metaverse and other fields.

The invention provides an end-to-end multi-task three-dimensional depth and semantic fusion visual perception system and an end-to-end multi-task three-dimensional depth and semantic fusion visual perception method. Comprising an image acquisition module used for outputting image data carrying calibration parameter identification; the fusion preprocessing module is used for processing the synchronous image pair to obtain a registration image pair; the multi-task network module comprises a shared feature extraction layer, a depth estimation branch and a semantic segmentation branch; the multi-task coupling unit is used for applying consistency constraint to the shared features and the branch features and transmitting geometric priori and category priori among branches; and the output interface module is used for packaging the depth map and the semantic mask according to a preset data structure, and outputting the depth map and the semantic mask to a real-time control interface of an external execution control system through an industrial real-time communication interface for calling. According to the invention, end-to-end low delay and deterministic output, time synchronization and calibration consistency maintenance, compact integration and simplified wiring can be realized, and a high-precision depth map and a semantic mask can be stably provided for a control system.

The invention provides a multi-view three-dimensional depth estimation method and device, equipment and a readable storage medium. The method comprises the following steps: acquiring a plurality of views of a target scene; performing multi-scale feature extraction on the views to obtain image features and edge features of each view; according to the image features and the edge features, depth estimation and edge depth optimization processing are carried out on the views through geometric perception, and a depth map of each view is generated; and fusing the depth maps of the plurality of views to obtain a three-dimensional point cloud map of the target scene. According to the embodiment of the invention, the depth estimation is more accurate, and the precision of the weak texture region is higher.

The invention provides a three-dimensional depth estimation method based on pulse streams, and belongs to the technical field of three-dimensional computer vision and neuromorphic imaging. The method comprises the following steps: (1) constructing a training and testing data set of a synthetic pulse stream; (2) constructing a pulse stream data set of a real scene; (3) constructing a three-dimensional depth estimation network model based on the pulse flow; (4) training a three-dimensional depth estimation network model based on the pulse flow; and (5) performing depth prediction by adopting the trained pulse stream-based stereo depth estimation network model. According to the invention, depth estimation can be directly carried out from the original pulse stream data, and a high-definition depth image is obtained without sequence framing or other post-processing; compared with an existing method, the method has better interpretability and higher prediction precision under a pulse flow data test set through iterative updating of the multi-layer and multi-scale cyclic pulse neural network and an algorithm of the pulse neural network.

Stereoscopic and multiscopic imaging methods and systems are disclosed. An example method can include capturing, with a first image capture device, first image data from a scene within a first field of view, and capturing, with a second image capture device, second image data from the scene within a second field of view overlapping with the first field of view over a stereoscopic overlap region, wherein either or both of the first and second image capture devices include a transmissive diffraction mask (TDM) configured to encode TDM depth information in the first and / or second image data. The method can also include determining stereoscopic depth information within the stereoscopic overlap region based on the first and second image data, determining the TDM depth information encoded in first and / or second image data, and generating combined depth information based on the stereoscopic depth information and the first and / or second TDM depth information.

Embodiments of the invention provide an image processing method and apparatus, and an electronic device. The method comprises the steps of obtaining images acquired by an image acquisition device when a lens is located at different optical axis positions in different illumination modes; generating a super depth-of-field depth map based on the obtained image; generating a photometric stereo normal vector diagram based on the obtained image, and generating a photometric stereo depth map based on the photometric stereo normal vector diagram; and correcting depth information in the same depth-of-field region in the super depth-of-field depth map according to a photometric stereo normal vector in the photometric stereo normal vector map, and correcting depth information in a low texture region in the super depth-of-field depth map according to a photometric stereo depth value in the photometric stereo depth map. The detail depth information in the same depth-of-field region can be corrected by the photometric stereo normal vector, and the missing depth information in the low-texture region can be restored by the photometric stereo depth value, so that the super depth-of-field depth map which can well reflect the depth details of the collection view field can be obtained.

The invention provides an online measurement method and system for the key size of a lock based on lightweight edge calculation. The method comprises the following steps: building a detection system of a cloud-edge collaborative architecture; after a lock to be detected is conveyed to a detection station through a conveying belt, a uniform illumination scene is constructed through a shadowless panel light source in an optical detection environment construction system, and RGB color images and infrared depth images of the lock are synchronously collected and detected through an Intel RealSense D405 stereoscopic depth camera; and the qualification of the lock is judged according to a preset dimensional tolerance standard, and unqualified product sorting is completed by controlling the mechanical arm. According to the technical scheme, the key size of the lock on an assembly line can be efficiently measured in real time.

The application relates to a three-dimensional model reconstruction method and device based on a Gaussian sputtering model. The method comprises the following steps: acquiring sparse-view scene images of a target scene, and determining initialization parameter information of a Gaussian ellipsoid according to the scene images by using a motion recovery structure technology and a Gaussian sputtering model; determining prior depth, a color loss function and a gradient smoothing loss function according to the scene images by using a monocular depth model; determining reference depth according to the scene images by using a multi-view stereo depth estimation algorithm; determining a depth consistency loss function according to the prior depth and the reference depth; updating the initialization parameter information based on the depth consistency loss function, the color loss function and the gradient smoothing loss function by using the Gaussian sputtering model, determining updated parameter information, and generating a three-dimensional model of the target scene according to the updated parameter information. The reliability and robustness of the three-dimensional model can be improved by using a depth prior constraint information and a dynamic gradient control method.

The invention provides a multi-view three-dimensional depth reasoning method for unmanned aerial vehicle aerial images, which comprises the steps of data preprocessing and input, frequency perception feature extraction, cost body construction, double regularization and depth map generation and loss calculation, and is used for a multi-view depth estimation task in an unmanned aerial vehicle aerial scene. A traditional method mainly depends on commercial software such as SURE, while a current deep learning method is insufficient in generalization ability and often generates more errors in a boundary region and a weak texture region when processing deep reasoning and reconstruction of multi-view aerial images of an unmanned aerial vehicle. According to the method, spatial features are extracted by adopting frequency adaptive feature extraction and BiFormer global feature modeling, and a depth map is generated and optimized by adopting a double regularization module, so that the problem of reconstruction errors caused by depth inference errors of a boundary region and a weak texture region is solved.

The present invention relates a stereo depth camera and in particular to a stereo depth camera based on multiple detectors configured as event sensors and at least one illumination source oriented by 1-axis or 2-axis high-speed scanning for operation in optically clear to contaminated environments. A stereo depth camera (100) according to the present invention comprises an illumination unit (10) including a first illumination source (12-1) for emitting a first light beam, wherein the illumination unit (10) is configured for actively steering the first light beam to a first measurement position (P) in a surrounding of the stereo depth camera (100) within the field of view of the illumination unit (10); an imaging unit (20) including at least two detectors (22-1, 22-2) for detecting the first light beam reflected by a first object point at the first measurement position (P), wherein the detectors (22-1, 22-2) have different alignments and are configured to image a common field of view to enable stereoscopic imaging of the first object point; wherein the detectors (22-1, 22-2) include multiple pixels (S1, S2) that are configured as event sensors sharing a predefined pixel threshold trigger setting and which are adapted to collect multiple depth points from the first object point at the first measurement position (P) during a predetermined time interval Δt, wherein statistical analysis, filters, deep learning or machine learning algorithms, and / or a trained AI-model are applied to the collected depth points for determining and outputting the most probable distance of the first object point as pixel depth value for the first measurement position (P).

Deformable sensors having a stereo depth sensor and an infrared sensor and methods of their use are disclosed. In one embodiment, a deformable sensor includes an enclosure having a housing and a deformable membrane, wherein the deformable membrane is transparent to a wavelength band in the infrared spectrum, a stereo depth sensor that is disposed within the enclosure and is configured to view an underside of the deformable membrane, and output a deformation region of the deformable membrane as a result of contact with an object, wherein the deformation region includes depth information, and an infrared sensor that is disposed within the enclosure and is configured to view the object through the deformable membrane when the object contacts the deformable membrane and output a contact patch region corresponding with a region of the deformable membrane that contacts the object.

Aspects relate to stereo depth estimation utilizing asymmetric down-sampling in different directions. A device may include one or more memories configured to store a plurality of images and a plurality of cameras. The plurality of cameras may be configured to capture a left and right image, in which, each of the images includes one or more patches, each patch including plurality of pixels. The device may include one or more processors coupled to one or more memories, in which, the one or more processors are configured to: down-sample in a first direction on a first set of pixels in a first patch of a first image to generate a first down-sample; and down-sample in a second direction on a second set of pixels in a second patch of a second image to generate a second down-sample, the second down-sample including a greater number of pixels.

Deformable sensors having a stereo depth sensor and an infrared sensor and methods of their use are disclosed. In one embodiment, a deformable sensor includes an enclosure having a housing and a deformable membrane, wherein the deformable membrane is transparent to a wavelength band in the infrared spectrum, a stereo depth sensor that is disposed within the enclosure and is configured to view an underside of the deformable membrane, and output a deformation region of the deformable membrane as a result of contact with an object, wherein the deformation region includes depth information, and an infrared sensor that is disposed within the enclosure and is configured to view the object through the deformable membrane when the object contacts the deformable membrane and output a contact patch region corresponding with a region of the deformable membrane that contacts the object.

In order to enhance the 3D display effect and increase the viewing range, the invention provides a panoramic disparity map multi-view-field stereoscopic display device. The structure of the multi-view-field stereoscopic display device for the panoramic disparity map is formed by sequentially arranging a light source panel, a transparent liquid crystal display panel, a middle light isolation plate, a diaphragm and a cylindrical lens array from back to front. Parallax image light rays are transmitted out of the stereoscopic display device through the diaphragm with the inclination angle and the cylindrical lens array and then are transmitted in the direction perpendicular to the cylindrical lens array, a plurality of watching view fields of left and right parallax images are formed, a viewer is in the watching range, the left eye and the right eye of the viewer are located at the view field positions of the two parallax images respectively, and therefore the viewer forms stereoscopic impression.

The invention relates to the technical field of intelligent monitoring, in particular to an inspector trajectory tracking method, system and device based on a binocular camera, and the method comprises the steps: obtaining a basic image in real time through the binocular camera worn by an inspector; calculating stereo depth information based on the basic image and the camera parameters at the same time; performing feature extraction and matching on the basic images at adjacent moments, and determining pose information corresponding to the basic images based on the depth information; and performing coordinate system conversion on the pose information, outputting the pose information, and determining the track of the inspector based on an output result. Therefore, the track tracking of the inspector can be comprehensively, accurately and efficiently carried out with lower cost and implementation difficulty.

Systems and techniques are provided for generating disparity information from two or more images. For example, a process can include obtaining first disparity information corresponding to a pair of images, the pair of images including a first image of a scene and a second image of the scene. The process can include obtaining confidence information associated with the first disparity information. The process can include processing, using a machine learning network, the first disparity information and the confidence information to generate second disparity information corresponding to the pair of images. The process can include combining, based on the confidence information, the first disparity information with the second disparity information to generate a refined disparity map corresponding to the pair of images.

The invention discloses a beef cattle body length non-contact accurate measurement method in a channel column-passing scene, and relates to the technical field of livestock three-dimensional measurement, and the method comprises the steps: generating an imaging configuration list and an environment label through an environment near-infrared pollution ratio, a glare index and a stroboscopic phase, and carrying out the linkage of an infrared cut-off filter, wave band / power, active illumination, polarization, exposure, a global shutter and stroboscopic inhibition; single cattle confirmation, quality gating and attitude gating are carried out, and multi-frame acquisition is triggered in short window time synchronization; a three-dimensional back line is obtained in the ridge area based on polarization normal and stereo depth combined constraint, an acromion and a recommended part are determined, extrapolation is carried out on a missing section limited spline, the geodesic body length is calculated, and an evidence field is generated; and monitoring and calibrating the health degree, re-calibrating an out-of-limit minimum sequence, solidifying an evidence packet and feeding forward a threshold value. Therefore, the measurable rate and the consistency are improved under strong direct incidence, wet back reflection and stroboflash, the quantity values are comparable, the reasons can be checked, and the maintenance is not interrupted.

Systems, apparatus, articles of manufacture, and methods are disclosed to perform human face distance estimation using a single calibrated two-dimensional (2D) camera, thereby eliminating the need for stereo depth systems, time-of-flight cameras, infrared pattern projectors, etc. Disclosed example techniques estimate three-dimensional (3D) distance from a camera to a human face by combining 2D facial landmarks, corresponding reconstructed 3D landmarks, and known anatomical distance priors such as interpupillary distance. An example multi-landmark technique that addresses occlusion issues by computing weighted-average distance estimates from multiple facial feature pairs is also disclosed. The example human face distance estimation techniques disclosed herein enable implementation of human-machine interfaces based on human face distance using standard 2D cameras with minimal software complexity.

This invention relates to stereo depth curvature correction and a method for correcting curvature in a flexible device. In one aspect, the method includes: accessing feature data of a first stereo frame generated by a stereo optical sensor of the flexible device, the feature data being generated based on a visual inertial odometry (VIO) system of the flexible device; accessing depth map data of the first stereo frame, the depth map data being generated based on a depth map system of the flexible device; estimating pitch-roll and yaw deviations based on the feature data and depth map data of the first stereo frame; and generating a second stereo frame after the first stereo frame, the second stereo frame being based on the pitch-roll and yaw deviations of the first stereo frame.

Calibration target(s) are mounted on a vehicle including a plurality of cameras. The calibration targets are in the field of view of the cameras. The calibration targets are sometimes LED or IR illumined targets. The targets in some embodiments are shielded to block light from oncoming cars and / or to block driver view of the target to reduce the risk of driver distraction. The cameras capture images at the same time. Calibration operations are then performed using the target or targets included in the captured images as a known visual reference of a known shape, size and / or having a known image pattern. Calibration parameters including parameters providing information about the location and / or spatial positions of the cameras with respect to each other and / or the target are generated from the captured images. Distance to objects in the environment which are included in the captured images are then determined.

Various examples provide depth image analysis and correction for stereo image machine learning systems and applications. A depth image anomaly identification stage of a depth image anomaly processor can perform functions to evaluate a depth image in order to identify anomalous segments where the values ​​of pixels predicted by a stereo depth perception model appear anomalous in terms of accuracy compared to other regions of the depth image. A correction stage adjusts the depth image based on the identified anomalous segments using one or more correction techniques that can compute estimates or predictions for depth values ​​within the identified anomalous segments. The correction can be based on detected structural characteristics within the spatial volume corresponding to the identified anomalous segments and / or on characteristics of local phenomena (e.g.,lighting, reflections, glare, etc.) are based on factors that have been identified as causing inaccuracies in depth values.

This disclosure provides systems, devices, apparatuses, and methods, including computer programs encoded on a storage medium, for motion estimation and mesh stitching of stereoscopic depth. The processor may obtain an indication of a grid associated with a set of motion vectors for a first frame and a second frame of the plurality of frames. The processor may detect a set of regions in the grid, the set of regions including a set of motion disparity values associated with the set of motion vectors, where each motion disparity value in the set of motion disparity values is less than a consistency threshold. The processor may compute an adjustment of the grid based on the region. The processor may output an indication of the adjustment of the grid.

The application provides an integrated imaging system and imaging method based on multi-layer atomized liquid crystal, relates to the technical field of three-dimensional imaging, and comprises a liquid crystal panel, a lens array and multi-layer atomized liquid crystal. Firstly, the imaging depth of each part in the image to be displayed is determined. Then, based on the imaging depth of each part in the image to be displayed and the corresponding imaging depth distribution of the multi-layer atomized liquid crystal, the area of each layer of the multi-layer atomized liquid crystal that needs to be atomized is determined. Finally, the area of each layer of the multi-layer atomized liquid crystal that needs to be atomized is atomized through time sequence voltage. The integrated imaging system and imaging method based on multi-layer atomized liquid crystal provided by the application can obtain a three-dimensional effect of continuous depth by mapping an image onto atomized liquid crystal at different positions, so that the depth of field of different layers can be effectively connected together to obtain continuous stereoscopic depth, and the display depth is large, and the imaging effect is better.

The application discloses a kind of based on knowledge mutual distillation's image depth estimation method, system, equipment and medium, it is related to computer vision technical field, the method includes collecting single frame image, multiple frame image and stereogram, respectively obtains corresponding depth map;Single frame image pixel is converted to three-dimensional space, and the scale between inherent geometric plane and the space point corresponding to the pixel is calculated, according to the scale and the depth map of single frame, multiple frame image, the depth map of recovery scale is obtained;The depth map estimated by single frame, multiple frame and stereoscopic model is aligned;Respectively using single frame, multiple frame and stereoscopic depth estimation model corresponding scale alignment depth value reconstructs pixel, according to original pixel and reconstructed pixel constructs knowledge mutual distillation model;Depth estimation model is trained based on knowledge mutual distillation model, according to the model after training, the depth of the image to be measured is estimated;The method fuses the advantage of single frame, multiple frame and stereoscopic depth estimation model, guarantees the independence of single model.

Provided in the embodiments of the present application are an image processing method and apparatus, and an electronic device. The method comprises: obtaining images collected by an image collection device in different illumination modes when a lens is located at different optical axis positions; on the basis of the obtained images, generating a super depth-of-field depth map; on the basis of the obtained images, generating a photometric stereo normal vector map, and on the basis of the photometric stereo normal vector map, generating a photometric stereo depth map; and on the basis of a photometric stereo normal vector in the photometric stereo normal vector map, correcting depth information in the same depth-of-field region in the super depth-of-field depth map, and on the basis of a photometric stereo depth value in the photometric stereo depth map, correcting depth information in a low-texture region in the super depth-of-field depth map. Since detailed depth information in the same depth-of-field region can be corrected by means of a photometric stereo normal vector, and missing depth information in a low-texture region can be restored by means of a photometric stereo depth value, a super depth-of-field depth map which can fully reflect the depth details of a collection field of view can be obtained.