38 results about "Object registration" patented technology

The invention relates to the technical field of point cloud registration, and discloses a virtual model and real object registration method and device, equipment and a storage medium. The method comprises the following steps: firstly, performing single-view segmentation on virtual model point clouds, and performing feature extraction on each single-view point cloud obtained by segmentation to obtain a view global feature corresponding to each single-view point cloud; and performing feature extraction on the point cloud of the real registration object to obtain real global features. And then, based on the matching degree between the visual angle global feature corresponding to each single visual angle point cloud and the real global feature, determining a target visual angle point cloud from the plurality of single visual angle point clouds. And finally, performing registration based on the target visual angle point cloud and the real registration object point cloud, and registering the virtual model to a real space coordinate to obtain a target virtual model. According to the method, the interference of exterior points is effectively reduced, the number of required iterations is reduced, the accuracy of a registration result is remarkably improved, and the problem that registration needs multiple iterations when the pose of a real object is unknown is solved.

Devices, systems, and techniques for a shared set of object registrations for devices with independent reference planes. An example imaging device may capture a first imaging data stream of a visualized surgical structure. The imaging device may communicate registration information with another surgical imaging device capturing a second imaging data stream of the visualized surgical structure. The imaging device may identify, based on the registration information, a first location, within the first imaging data stream, associated with the visualized surgical structure. The first location may be determinable based on: a first reference geometry associated with a field of view of the first surgical imaging device, a second reference geometry associated with a field of view of the second surgical imaging device, a transformation between the first reference geometry and the second reference geometry, and a reference landmark common to the first imaging data stream and the second imaging data stream.

The invention relates to the technical field of archive storage, and discloses an archive storage system and method based on a digital object architecture, and the system comprises a unique identification and relation analysis assembly which is used for generating a globally unique object identifier; the digital object warehouse is used for constructing digital objects; the digital object registry is used for establishing a metadata index which can be retrieved; the distributed account book module is used for forming an on-chain record; and a policy-driven engine for monitoring and receiving the broadcasted structured transactions and determining the affected context scope to execute the embedded lifecycle policy. According to the technical scheme, the electronic original text is constructed into the digital object containing the Merkel tree integrity verification data, and all key operations are recorded in the distributed account book module, so that full-chain trust guarantee of archive data from content to process is realized; therefore, the integrity of the data in the long-term storage process can be effectively verified.

A method for registering digital objects on at least one blockchain (BCN1), comprising the steps of creating a first off-chain object container (OC1(AG1), OF1(AG1)) associated with a reconciliation agent; receiving, between a first and a second time, requests (R1(AG1)) to register objects in the first object container issued by a first operator (OP1) and designating a first reconciliation agent (AG1); using the first reconciliation agent, generating reconciliation objects based on the off-chain object registrations that occurred between two times, and generating a reconciliation request (R2(AG1)); receiving, via the management platform, the reconciliation request and registering the reconciliation objects in a reconciliation wallet (SW1(AG1)) on the blockchain. Abbreviated figure: Fig. 1

The application relates to the technical field of image three-dimensional reconstruction. The application discloses a monocular hand-object interaction three-dimensional reconstruction method and device, a terminal and a storage medium, which can improve the quality of a hand-object interaction reconstruction result. The method comprises the following steps: acquiring an initial object grid, an initial hand grid and a target hand-object interaction grid corresponding to a target image; performing hand region and object region extraction processing on the target hand-object interaction grid to obtain a target hand rough region and a target object rough region; performing coarse registration of the initial object grid to the target object rough region by using an object registration algorithm to obtain an optimized object grid; performing coarse registration of the initial hand grid to the target hand rough region by using a hand registration algorithm to obtain an optimized hand grid; and performing parameter adjustment processing on the optimized object grid and the optimized hand grid by using a joint optimization algorithm to obtain a hand-object interaction reconstruction result corresponding to the target image.

The invention provides a data processing method and device, equipment and a storage medium, and can be applied to the technical field of computers. The method comprises the following steps: acquiring a data directory published by a first object, wherein the data directory comprises description information of a data source provided by the first object; registering a decentralized identity (DID) for the first object by using a public key of the first object, and storing a first DID identifier of the first object and a corresponding first DID document to the block chain; registering a DID for a data directory, and storing a second DID identifier corresponding to the data directory and a second DID document corresponding to the data directory to the block chain; signing and issuing a first verifiable declaration VC of the data directory by using a private key of the first object, and storing the first VC to the block chain; the first VC is used for determining that a data directory is created and owned for the first object. The method and the device are beneficial to ensuring security and credibility of data sharing.

Among other techniques, techniques for dynamic survivorship, cross-tenant matching, and lineage entity identifier (EID) promotion are described. A system utilizing these techniques can include an industry-agnostic datastore, an industry-focused datastore, a tenant datastore, a new dataset datastore, a new dataset onboarding engine, an EID assignment engine, an object registration engine, a primary EID selection engine, a matching engine, a merging engine, a survivorship engine, a cross-tenant matching engine, and a lineage EID promotion engine. A method utilizing these techniques can include new dataset onboarding, EID assignment, object registration, primary EID selection, matching, merging, survivorship, cross-tenant matching, and lineage EID promotion.

The invention belongs to the technical field of image processing, and provides a target object change detection method, device and equipment based on deep learning, and a medium, and the method comprises the steps: obtaining a dual-temporal remote sensing image pair containing target object registration and a training sample of a binary change annotation graph corresponding to the pixel level of the dual-temporal remote sensing image pair; constructing a target object change detection model, wherein the target object change detection model comprises a feature extraction module used for extracting multi-scale features of two time-phase images in the dual-time-phase remote sensing image pair, a bidirectional semantic alignment module used for fusing the multi-scale features of the two time-phase images, and a decoder module used for recovering spatial details; training a target object change detection model by using the training sample to obtain a trained target object change detection model; and inputting the dual-temporal remote sensing image pair registered with the target object to be detected into the trained target object change detection model, and outputting a corresponding binary change prediction map. According to the invention, a changing target object area can be accurately and robustly segmented from the dual-time-phase low-altitude image.

Various embodiments provide for a registry for augmented reality (AR) objects, which can provide AR objects to a client device to support various software or hardware applications. For instance, some embodiments provide for an AR object registry that facilitates or enables registration of one or more AR objects in association with one or more locations across a planet.

In one embodiment, a method includes capturing a stereoscopic image of a predetermined calibration object having a predetermined pose using a pair of cameras of a video perspective AR system, and obtaining position data for each of the pair of cameras as the stereoscopic image is captured. The method includes generating a 3D reconstruction of the calibration object. The method includes performing a registration process by: generating a stereoscopic virtual view including a predetermined calibration object using parameters of each of a pair of stereoscopic virtual cameras, and determining, for each of the stereoscopic virtual views, one or more differences between a real-world calibration object corresponding to a predetermined calibration object in the stereoscopic image and a virtual rendering of the calibration object, and using these differences to adjust virtual camera parameters and repeat a registration process or store parameters for the system.

Aspects of this technical solution can include modifying a customizable region of a media object into a customized media object having a modified customizable region, generating, based on a card template having a portion compatible with the media object, a card object corresponding to the card template and including the customized media object embedded in the card object at a location corresponding to the portion of the card template, generating, based on the card object, an NFT including a first identifier of the customized media object and a second identifier of the card template, registering, based on the NFT, the card object to a user account via a block at a blockchain, and linking the NFT with a wallet object corresponding to the user account.

Embodiments of the present disclosure provide a system (200) and method (300) for registering unknown objects into a device management system. The method comprises receiving (302), through a processor (204), one or more object data related to an object. The object is unknown to the device management system. The method further comprises extracting (304) one or more object identifiers from the one or more object data to identify the one or more objects, transmitting (306) the one or more object identifiers to an external source to identify a refined information about the object. The refined information is used to classify the object. The method further comprises registering (308) the object with the device management system according to the classification of the object.

The present application discloses an object registration method and apparatus, relating to the field of computer vision, and solves the problem of how to improve the accuracy of the pose of a terminal device. The solution includes: obtaining a plurality of first input images including a first object, where the plurality of first input images include a real image of the first object and / or a plurality of first synthesized images of the first object; the plurality of first synthesized images are obtained by differentiable rendering of a three-dimensional model of the first object at a plurality of first poses; the plurality of first poses are different; respectively extracting feature information of the plurality of first input images, where the feature information is used to indicate the features of the first object in the first input image where it is located; corresponding the feature information extracted from each first input image to the identifier of the first object to perform registration of the first object.

Devices, systems, and techniques for a shared set of object registrations for devices with independent reference planes. An example imaging device may capture a first imaging data stream of a visualized surgical structure. The imaging device may communicate registration information with another surgical imaging device capturing a second imaging data stream of the visualized surgical structure. The imaging device may identify, based on the registration information, a first location, within the first imaging data stream, associated with the visualized surgical structure. The first location may be determinable based on: a first reference geometry associated with a field of view of the first surgical imaging device, a second reference geometry associated with a field of view of the second surgical imaging device, a transformation between the first reference geometry and the second reference geometry, and a reference landmark common to the first imaging data stream and the second imaging data stream.

To provide an information processing apparatus, a control method of the information processing apparatus, and a program capable of making an object unnecessary for user's appreciation invisible from the user while suppressing a load of image processing.SOLUTION: An HMD100 that generates an MR image includes an object registering unit 105 that registers an object to be viewed and an object to be deleted in a viewing target list and a deletion target list in accordance with inputs instructing to register the object to be viewed and the object to be deleted, a line-of-sight position calculation unit 106 that acquires the line-of-sight position of an HMD user 400, a line-of-sight position setting unit 107 that sets an effective visual field region 401 of the HMD user 400 in accordance with the line-of-sight position of the HMD user 400, and a control unit that performs image processing for making the object to be deleted invisible to the HMD user 400 in the MR image. And a processing operation part 109 for performing processing to the inside of the effective visual field area 401 of the HMD user 400 including the object of the viewing object.SELECTED DRAWING: Figure 1

The invention discloses an application registration method, apparatus and device, and a readable storage medium. The method comprises the steps of obtaining registry form information submitted by a first object; the registry form information comprises a target application tenant identifier and first object registration information; performing hook query processing on the target application tenant identifier to obtain a hook query result; and if the hook query result indicates that the pre-registration tenant management hook in the enabled state exists in the target application tenant identifier, submitting the first object registration information to a target application tenant server according to the pre-registration tenant management hook, so that the target application tenant server performs registration verification processing on the first object registration information, obtaining a registration verification result; and if the registration verification result is a registration verification passing result, performing application registration processing according to the first object registration information to obtain an application registration result. According to the invention, the flexibility and diversity of registration verification in a multi-tenant application scene can be improved.

The application discloses a kind of data processing method, equipment and readable storage medium based on blockchain, the method includes: the target object information of target object is obtained based on the object registration request for target application service;A key address and target object identifier are generated;Target object identifier is added to target object identifier set, and updated object identifier set is obtained;Updated object identifier set includes one or more object identifiers with associated relationship with target object information;Each object identifier in updated object identifier set respectively corresponds to different application service;Updated object identifier set is used to carry out legitimacy verification to the object identifier to be verified before sending the business processing request carrying the object identifier to be verified to blockchain network;Target object identifier and A key address are all sent to blockchain network.Using the present application, the authenticity and legality of the business processing request transmitted to the blockchain network can be improved.

This application discloses a method, apparatus, and electronic device for updating node links of a target service, relating to the field of software development technology. It is used to dynamically reorganize node links at runtime without interrupting service or modifying code, thereby improving the flexibility of business orchestration and system availability. The method includes: in response to receiving a node link change request, obtaining configuration information of the target node link; the configuration information includes at least one service node identifier arranged in execution order; obtaining configuration rules for the service instance object corresponding to each service node identifier; generating a proxy class object corresponding to the target node link based on the execution order indicated by the configuration information and the configuration rules corresponding to each service node identifier; the proxy class object is used to represent the execution logic of calling the service node corresponding to the service node identifier in execution order; registering the proxy class object to the business execution system; and the business execution system using the proxy class object when implementing the target service.

The invention discloses a rapid registration method and a registration positioning device for aircraft assembly, and the method comprises the steps: building a three-dimensional stl model of an aircraft part, and taking a crossed rib on a frame beam of the aircraft part as a virtual-real matching feature point; a plane equation R11 and a plane equation RR2 of the two ribs are obtained respectively, and then a middle plane equation RMid1 and a middle plane equation RMid2 of the two ribs are obtained; and combining the plane equations RMid1 and RMid2 with the top plane equation RTop, and calculating to obtain a plane intersection point as a theoretical registration coordinate point F (x, y, z). And finally, according to the thickness of the real object registration point device, adjusting the offset to obtain an aircraft assembly registration point Final (x + s * a, y + s * b and z + s * c) so as to carry out registration assembly. The method solves the problems that in the prior art, the theoretical coordinates of the registration points cannot be rapidly obtained, the real object registration points are not accurate enough to place, and the adaptability is not high, and has good practicability.

The present application discloses a method and device for rendering a display page, a storage medium and an electronic device, and relates to the field of smart home technology. The method for rendering a display page includes: receiving first session information sent by a communication server of a third-party instant communication, wherein an application client performs instant communication through a software development kit provided by the third-party instant communication, and the first session information includes: a first session list between a target object and a first session object and a first user identifier of the communication server registered by the session object; sending a first request information to an application server corresponding to the application client; receiving a first response information sent by the application server according to a second user identifier and the first session identifier, and rendering a display page of the application client according to the first response information, wherein the first response information includes: user information of the first session object and the second session object, and a second session list between the target object and the second session object.

Various embodiments of this disclosure relate generally to an embedded services platform for generating an embedded shell widget. The platform may comprise a grandparent layer configured to provide a user interface for a merchant; a parent layer configured to receive an interaction with the user interface for the merchant and transmit data from an embedded services platform; a child layer configured to transmit data associated with a web application communicating with the embedded services platform; and an object registry configured to store source data defining the web application, wherein the source data is accessible by the child layer.

Various embodiments of this disclosure relate generally to an embedded services platform for generating an embedded shell widget. The platform may comprise a grandparent layer configured to provide a user interface for a merchant; a parent layer configured to receive an interaction with the user interface for the merchant and transmit data from an embedded services platform; a child layer configured to transmit data associated with a web application communicating with the embedded services platform; and an object registry configured to store source data defining the web application, wherein the source data is accessible by the child layer.

This application discloses a memory debugging method and apparatus, belonging to the technical field of computer and embedded devices. The memory debugging method includes: responding to a query command from an external program, parsing the variable hierarchy name in the query command to obtain the variable object name; searching in a variable object registry based on the variable object name to obtain the corresponding variable object information, which includes at least the variable object memory address and the variable object data type name; searching in a variable type registry based on the variable object data type name to obtain the corresponding data type information; calculating the actual memory address of the variable object; and generating a feedback command based on the actual memory address and data type information and sending it to the external program. By parsing the variable hierarchy name to extract the variable object name and searching in the variable object registry and variable type registry, inconsistencies between the tables and the program can be avoided, preventing abnormal query results.

A method for enabling controller tracking in an augmented reality environment, and a system-non-temporary computer-readable medium are provided. [Solution] A method for creating a control from a 3D object includes registering object 135 as a controller, placing marker 115 on the object in association with a constellation, capturing the object along with the marker in image data, determining the 3D geometry from the image data, determining the location of the marker relative to the geometry, and registering the 3D object as a controller by associating the geometry with the marker location. The constellation is tracked in additional image data, and the motion characteristics of the controller are determined based on the orientation determined by the constellation, determining the orientation of the controller and using it for user input actions.

The present invention provides a tracking method, a tracking device, a readable storage medium, an electronic device, and a robot. The tracking method includes: determining local point cloud data of a target object according to point cloud information; performing a complement processing on the local point cloud data to obtain the overall point cloud data of the target object, wherein the local point cloud data is unordered point cloud data, and the overall point cloud data is ordered point cloud data; and tracking the target object according to the overall point cloud data. By complementing and processing the unordered local point cloud data generated by a lidar into ordered overall point cloud data, the present application improves the integrity of observation, and when processing consecutive multiple frames of point clouds, the matching accuracy for the same object is greatly improved, thereby realizing high-precision object registration and object tracking.

The invention discloses a multi-target automatic registration method for a heterogeneous image, and the method comprises the steps: obtaining an infrared image and a visible light image, carrying out the preprocessing of the infrared image and the visible light image, and enhancing the features of the infrared image and the visible light image; key feature points and descriptor information of a target object in the infrared image and the visible light image are jointly extracted through a feature point extraction method based on a Super Point algorithm and an SIFT algorithm; registering the feature points and the descriptor information of the infrared image and the feature points and the descriptor information of the visible light image by adopting a Super Glue algorithm; and performing mismatching correction on the registered infrared image and visible light image, and then outputting a registered image. The high-precision different-source image registration is realized through pre-enhancement of features of an infrared image and a visible light image and division of multi-target sub-images, and through high-integrating-degree cooperation of a Super Point algorithm and a Super Glue algorithm, image registration is carried out.

This disclosure provides a method and apparatus for processing object information. The method includes: displaying a sub-object registration portal for a first target main object on a first application interface; and, in response to receiving sub-object registration information input by a first user based on the sub-object registration portal of the first target main object, establishing a master-sub-object binding relationship between the sub-objects and the first target main object. The first target main object has master-sub-object binding relationships with multiple sub-objects, and the main store identifier corresponding to the first target main object is different from the sub-store identifiers corresponding to each sub-object. The first application interface displays association cooperation information with a second user, which is used to instruct the second user to display the introduction information and order information of the first target main object on the second user's second application interface. The first user is the user providing the sub-object, and the second user is a user whose popularity value is greater than a first preset value. This method can increase the ways in which master and sub-objects can be combined.

A technique for creating a control from a three-dimensional object involves registering the object as a controller. Markers are placed on the object in a constellation pattern. The object is captured in image data with the markers. A geometry of the three-dimensional is determined from the image data, and a location of the markers relative to the geometry is determined. The three-dimensional object is registered as a controller by associating the geometry with the marker locations. The constellation is tracked in additional image data and motion characteristics for the controller are determined based on a determined orientation of the constellation. The orientation of the constellation is used to determine an orientation of the controller. The determined orientation of the controller is then used for a user input action.

Various implementations provide a registration table for augmented reality (AR) objects that can provide AR objects to client devices to support various software applications or hardware applications. For example, some implementations provide an AR object registration table that facilitates or enables registration of one or more AR objects associated with one or more locations on a planet.

The application relates to the technical field of archive storage, and discloses an archive storage system and method based on a digital object architecture. The system comprises a unique identification and relationship analysis component for generating a globally unique object identifier; a digital object warehouse for constructing a digital object; a digital object registry for establishing a searchable metadata index; a distributed ledger module for forming on-chain records; and a strategy-driven engine for listening to and receiving broadcast structured transactions, determining affected context scopes, and executing embedded life cycle strategies. The application realizes full-chain trust guarantee of archive data from content to process by constructing an electronic original text into a digital object containing Merkle tree integrity check data and combining the technical solution of recording all key operations in the distributed ledger module, thereby effectively verifying the integrity of data during long-term storage.