19 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 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.

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.

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 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.

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.

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.

It is presented a method for controlling a robot, comprising the steps of: detecting, by a first image sensor, first image information of a first field of view, providing the first image information to a data processing device, detecting, by a second image sensor, second image information of a second field of view, wherein the first field of view and the second field of view at least partially overlap, providing the second image information to the data processing device, determining, by the data processing device, first monocular depth information based on the first image information and / or determining, by the data processing device, second monocular depth information based on the second image information, determining, by the data processing device, stereo depth information based on the first image information and the second image information, determining, by the data processing device, control information for controlling the robot based on the first monocular depth information and / or the second monocular depth information and the stereo depth information, providing the control information to a control device, and controlling a movement of the robot by the control device in accordance with the control information.

The application provides an end-to-end multi-task stereo depth and semantic fusion visual perception system and method. It comprises an image acquisition module for outputting image data carrying calibration parameter identification; a fusion preprocessing module for processing synchronous image pairs to obtain registered image pairs; a multi-task network module comprising a shared feature extraction layer, a depth estimation branch and a semantic segmentation branch; a multi-task coupling unit for applying consistency constraints to shared features and branch features, and transmitting geometric priors and class priors between branches; and an output interface module for packaging depth maps and semantic masks according to a preset data structure, and outputting them to the real-time control interface of an external execution control system through an industrial real-time communication interface for calling. The application can realize end-to-end low latency and deterministic output, time synchronization and calibration consistency maintenance, compact integration and simplified wiring, and stably provide high-precision depth maps and semantic masks to the control system.

The application discloses a stereo depth estimation method, system, device and medium, and relates to the technical field of computer vision, and the method comprises the following steps: calling a visual basic model to perform monocular depth estimation on a left view to obtain monocular depth reference information; performing scale calibration on the monocular depth reference information by using geometric constraints of a stereo image pair to obtain initial disparity; performing iterative optimization on the initial disparity by using stereo geometric features extracted from the stereo image pair to obtain final disparity; and generating a metric depth map according to the final disparity. Through step-by-step processing, high-precision stereo depth estimation of an image to be processed is realized, monocular depth without absolute scale is converted into accurate initial disparity, local errors are corrected and detail precision is improved through iterative optimization, the problems of insufficient scale of monocular depth estimation and lack of initial disparity precision are solved, and the practicability and accuracy of the depth result are ensured.

In various examples, depth image analysis and correction for stereo image machine learning systems and applications are provided. A depth image anomaly identification stage of a depth image anomaly processor may perform functions for evaluating a depth image to identify anomalous segments where the values of pixels predicted by a stereo depth perception model appear anomalous with respect to accuracy in comparison with 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 may compute estimates or predictions for depth values within identified anomalous segments. Correction may be based on detected structural characteristics within the volume of space corresponding to the identified anomalous segments, and / or based on characteristics of local phenomena (e.g., lighting, reflections, glare, etc.) identified as potentially causing the inaccuracies in depth values.