Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

1061 results about "Visually guided" patented technology

Vision-based composite robot hand-eye calibration and workpiece positioning device and method

The invention discloses a vision-based composite robot hand-eye calibration and workpiece positioning device and method. The method comprises the following steps: S1, performing camera calibration and end tool TCP calibration on two cameras according to a preset operation height; s2, the mechanical arm is controlled to reach a calibration position, and image data of hand-eye calibration are collected; the tail end of the mechanical arm tool is controlled to reach the characteristic point position of the checkerboard calibration plate, and characteristic point data of hand-eye calibration are collected; calculating hand-eye calibration parameters based on the image data and the feature point data; and S3, the mechanical arm is demonstrated to reach the workpiece grabbing pose, the camera in the box collects the checkerboard image and the Aruco two-dimensional code image before and after demonstration, and station calibration parameter calculation is carried out. Hand-eye calibration is completed in a simpler, more convenient and quicker mode, the problem that the vision-guided workpiece grabbing precision is reduced due to movement of the chassis is solved, and meanwhile post-processing is conducted on subsequent workpiece grabbing poses.
Owner:GUILIN UNIV OF ELECTRONIC TECH +2

3D visual guidance mechanical arm grabbing method for irregular objects

The invention belongs to the technical field of mechanical arm automatic grabbing, and particularly relates to a 3D visual guidance mechanical arm grabbing method for irregular objects. Comprising the following steps that (1) a 3D visual guidance mechanical arm grabbing system is built, specifically, a 3D camera based on line structured light is adopted to guide a mechanical arm, the mechanical arm is a visual flexible six-axis mechanical arm, and after the mechanical arm completes accurate grabbing of all objects and carries out placement according to requirements, it is regarded that the grabbing task is successfully completed; and the camera in the 3D camera is calibrated, and the calibration of the camera is realized by calling a CalibrateCamera function in the OpenCV library. Through mutual cooperation of the 3D camera and the mechanical arm, intelligent grabbing of irregular objects such as industrial parts is achieved, more accurate grabbing operation is carried out according to the actual application situation, and the robot does not depend on training of three-dimensional point cloud samples. And the 3D camera can accurately obtain external information, and the grabbing requirement of the mechanical arm is met.
Owner:LIAOCHENG XINTAI MACHINE TOOL

Grabbing control system for robot visual guidance

The invention discloses a grabbing control system for robot visual guidance, and belongs to the technical field of grabbing control systems.The grabbing control system comprises a visual perception module used for collecting workpiece images, extracting workpiece feature information and calculating accurate coordinates of workpieces in space; the robot main body module is used for receiving a system instruction to drive a carrier to move to a target position; the grabbing execution module is used for being in contact with the workpiece, grabbing the workpiece stably and transferring the workpiece to a designated position to be placed without damage; the system integration module is used for guaranteeing the safety, operability and stability of the feeding and discharging process; according to the system, workpiece information can be accurately collected, the posture of the grabbing execution end is analyzed based on the workpiece position, the grabbing posture is corrected in real time according to the grabbing dynamic state, and the workpiece grabbing precision and stability are improved.
Owner:HUANYU AUTOMATION (SHENZHEN) CO LTD

System for computation of object coordinates accounting for movement of a surgical site for spinal and other procedures including interpolation of vertebral position and orientation

Aspects of the present disclosure relate to systems, devices and methods for performing a surgical step or surgical procedure for example with visual guidance using a head mounted display or with a surgical navigation system or with a surgical robot. A computer processor can be configured to determine the pose of a first vertebra with an attached first marker and a second vertebra with an attached second marker. The computer processor can be configured to determine the pose of at least one vertebra interposed or adjacent to the first and second vertebrae with attached markers, e.g. fiducial markers.
Owner:ONPOINT MEDICAL INC

Weld joint rapid identification method and system based on visual guidance

The invention provides a rapid weld joint recognition method and system based on visual guidance. Wherein a welding area image is captured in real time through a visual sensor, and the image quality of the welding area image is improved through an image enhancement technology; tracking a welding seam edge of the welding area image to obtain welding seam edge information; generating a multi-scale representation of the weld edge based on the weld edge information; processing the multi-scale representation of the weld edge to obtain a geometric consistency verification result; adjusting the angle and the focal length of a visual sensor through a real-time feedback mechanism so as to optimize the recognition precision of the welding seam edge; and according to the multi-scale representation of the welding seam edge and the geometric consistency verification result, outputting a guide signal of a welding seam identification path so as to guide welding equipment to move according to the welding seam identification path. According to the technical scheme provided by the invention, the accuracy and reliability of welding seam rapid identification are greatly improved.
Owner:SHANDONG ELECTRIC POWER PIPELINE ENG

Printed circuit board defect detection method and system based on cross-modal prompt learning and visual guidance

The invention discloses a printed circuit board defect detection method and system based on cross-modal prompt learning and visual guidance, and the method comprises the following steps: obtaining a defect-free PCB image sample, and obtaining a training data set; constructing an initial printed circuit board detection model; training the initial printed circuit board detection model by using the training data set to obtain a printed circuit board detection model; and completing the defect detection of the printed circuit board by using the printed circuit board detection model. According to the method, a synthetic anomaly generation strategy based on a PCB structure and physical prior is provided, a two-channel storage library mechanism is introduced, and a synthetic anomaly sample most valuable for model training is screened out through a difficult case mining strategy, so that visual anomaly mode guidance is provided. According to the method, a double-constraint alignment optimization strategy combining comparison loss and triple loss is adopted, the mapping relation between vision and text features is adjusted, and cross-modal alignment and clear normal / abnormal boundaries are achieved. According to the method provided by the invention, the accuracy, the robustness and the generalization capability of PCB defect detection under the data sparse condition can be remarkably improved.
Owner:CENT SOUTH UNIV

Sow vaccine injection method and system based on deep learning and machine vision

The invention discloses a sow vaccine injection method based on deep learning and machine vision. The sow vaccine injection method comprises the following steps that 1, an AGV chassis is controlled to arrive at a work station according to an instruction; 2, visually recognizing the posture of the sow to be injected, and if the recognition result is that the sow to be injected is in a non-standing posture, driving up the sow to be injected with manual assistance; if the recognition result is a standing posture, visually guiding the mechanical arm to move to a photographing position; 3, the RGBD camera shoots in real time to obtain the injection position and distance of the sow to be injected, and the mechanical arm moves to position the injection clamp to the pre-injection position; 4, injection is completed, and an injection result is recorded; the invention further discloses a sow vaccine injection system based on deep learning and machine vision. Manual operation is replaced by mechanical operation, automation of the vaccine injection process is achieved, direct contact between personnel and sows is reduced, and the risk of infectious disease transmission is reduced.
Owner:WENS FOODSTUFF GROUP CO LTD +1

Methods for participating in an artificial-reality application that coordinates artificial-reality activities between a user and at least one suggested user

Systems and methods are provided for facilitating an interactive artificial-reality activity. A method includes, after a user of a head-wearable device has opted-in to using an artificial-reality application to facilitate connecting with other participating users, determining, based on user-specific suggestion criteria, that a suggested user is located in an approved common space with the user and has opted-in to use the artificial-reality application. The method includes causing the head-wearable device to present an user interface (UI) element for linking the suggested user and the user. Upon the user selecting the UI element for linking the suggested user with the user, the method includes automatically causing the head-wearable device to provide visual-guidance UI elements to navigate the user to an interactive-activity location where the user and the suggested user will perform an artificial-reality activity while also displaying information about the artificial-reality activity to be performed.
Owner:META PLATFORMS TECHNOLOGIES LLC

Tunnel illumination control method considering visual adaptability of driver

The invention relates to a tunnel illumination control method considering visual adaptability of a driver, and belongs to the technical field of tunnel illumination control, and the method comprises the following steps: S1, employing a volume scattering point location method to obtain visual adaptability parameters of visual adaptation states of all segments in a tunnel; s2, dynamically constructing a predictive visual adaptation model of the driver group based on the visual adaptation parameters, and outputting expected visual states of the drivers according to the predictive visual adaptation model; s3, according to the expected visual state, a parameter control mechanism is adopted to control target illumination parameters of all the sections of the tunnel; s4, according to the target lighting parameters, the working state of lighting equipment in a corresponding section in the tunnel is regulated and controlled, so that the light environment in the tunnel is matched with the dynamic visual adaptability of a driver, and safe visual guidance is achieved; the method has the beneficial effects that the target illumination parameters of all the sections of the tunnel are controlled by adopting a parameter control mechanism according to the expected visual state according to the target illumination parameters.
Owner:SICHUAN HIGHWAY ENG CONSULTING & SUPERVISION CO LTD

Laminating method, device and equipment for light guide plate

The invention discloses a light guide plate film covering method, device and equipment, and the method comprises the steps: responding to the detected size, material and surface condition of a light guide plate, and judging whether the light guide plate meets a film covering standard or not; commanding the robot to grab the membrane material, accurately positioning the alignment operation of the light guide plate and the membrane material through a visual guidance system, and adjusting the fitting position; controlling the membrane material to be preliminarily attached to the light guide plate, and adjusting pressure and adsorption force in real time according to material characteristics; analyzing data of the visual detection system, commanding the intelligent fluid dynamics control device to process bubbles or wrinkles, and meanwhile, re-scanning the processed area to ensure that the defoaming effect is qualified; and controlling the curing time, the curing temperature or the UV light intensity according to the used curing mode. According to the technical scheme, the laminating quality is improved, and bubbles and flaws are reduced.
Owner:SHENZHEN SAMSON OPTOELECTRONICS CO LTD

Mobile flexible docking platform, method and equipment based on visual guidance and storage medium

The invention provides a movable flexible docking platform, method and equipment based on visual guidance and a storage medium, and relates to the field of automatic auxiliary assembly. The docking platform comprises an AGV trolley, a six-degree-of-freedom platform erected in the middle of the upper portion of the AGV trolley, and a binocular vision system erected on the rear side of the upper portion of the AGV trolley. The binocular vision system provides real-time vision guidance in the advancing process of the AGV; a butt joint workpiece A is placed on a six-degree-of-freedom platform, and a butt joint workpiece B which has an assembly relation with the butt joint workpiece A is placed on a working table at a target position; and the AGV transports the butt joint workpiece A to the target position, and butt joint of the butt joint workpiece A and the butt joint workpiece B is completed. According to the invention, the six-degree-of-freedom parallel platform is arranged on the AGV trolley, so that the pose fine adjustment of the assembled workpiece is realized, the pose of the workpiece can be continuously adjusted in the transportation process to keep balance, and the workpiece transportation and high-precision butt joint can be realized.
Owner:NANJING SAIEN NAVIGATION TECH CO LTD

Audio-visual event positioning system and method based on cross-modal consistency and time sequence multi-granularity cooperation

The invention discloses an audiovisual event positioning system and method based on cross-modal consistency and time sequence multi-granularity cooperation, and relates to the technical field of computer vision. A single-modal feature coding module obtains single-modal features of videos and audios; the cross-modal consistency cooperation module is formed by stacking a plurality of multi-modal cooperation layers, each multi-modal cooperation layer comprises a visual guidance module and an audio guidance module, and the visual guidance module and the audio guidance module are each composed of a cross-modal interaction branch and a time sequence consistency branch; splicing the video features and the audio features output by each multi-modal cooperation layer to obtain multi-granularity time sequence features; the timing sequence multi-granularity cooperation module performs timing sequence cooperation from coarse granularity to fine granularity and timing sequence cooperation from fine granularity to coarse granularity on the multi-granularity timing sequence characteristics; and the decoding module predicts the event category and the event time through the features after time sequence bidirectional cooperation enhancement. The method can be used for processing, analyzing and positioning long-sequence audiovisual videos.
Owner:HEFEI UNIV OF TECH

Abdominal cavity reconstruction and focus positioning method, system and equipment based on binocular endoscope

The invention belongs to the technical field of medical image three-dimensional reconstruction, and discloses an abdominal cavity reconstruction and focus positioning method based on a binocular endoscope, which comprises the following steps of: calibrating and correcting internal reference of the binocular endoscope; inputting the trained depth estimation network to obtain a disparity map and processing the disparity map into a picture according to frames; the luminosity error is minimized through a coarse-to-fine pyramid optimization method, and a transformation matrix of the endoscope pose between two continuous frames is calculated through nonlinear iterative optimization; light beam adjustment optimization is carried out on the motion trail of the endoscope, a depth map is superposed, outliers are removed, and three-dimensional reconstruction of the abdominal cavity tissue is achieved; recognizing a focus, extracting three-dimensional information according to the disparity map, and visually guiding the operation arm to move to a focus point in combination with a calibrated hand-eye matrix so as to realize positioning. According to the method, rapid and dense three-dimensional reconstruction of the peritoneal environment before the operation and accurate focus positioning based on visual guidance during the operation are realized, the accuracy of motion track estimation of the endoscope is improved, and autonomous development of the surgical robot is expected to be promoted.
Owner:HUAZHONG UNIV OF SCI & TECH +1

Scribing robot automatic calibration method based on visual guidance

The invention relates to the technical field of image analysis, in particular to an automatic marking robot calibration method based on visual guidance, which comprises the following steps of: establishing an image set comprising different resolution levels based on operation site image data acquired by a marking robot, and performing corner detection and straight line segment detection on each level image in parallel. According to the method, through a parallel detection mechanism of a multi-resolution hierarchical image set, angular point and straight line segment features under different scales are synchronously extracted, and a multi-scale feature point set with high robustness is constructed in combination with cross-hierarchical coordinate stability measurement and response intensity quantification. And performing dynamic screening and grouping association on the feature points based on a preset geometric constraint condition, eliminating noise interference and false detection features, and generating a candidate calibration structure set with spatial consistency. Weighted contribution value fitting is adopted, cross-scale stability and detection confidence of feature points are integrated, and geometric accuracy and anti-interference capability of calibration reference point coordinates are improved.
Owner:FOSHAN DAOSHAN INTELLIGENT ROBOT CO LTD

Robust visual constraint control method and system for manipulator and computer equipment

The invention discloses a robust visual constraint control method and system for a mechanical arm and computer equipment, and the method comprises the steps: building an overall dynamic model of a visual servo system through combining a mechanical arm dynamic model, a visual servo kinematics model and a hand-eye calibration relation between a camera and the mechanical arm; in combination with a visual servo kinematic model, by designing a time-varying asymmetric control barrier function, a constraint satisfaction condition for constraining a visual servo characteristic error within a preset range is obtained, and an optimal visual servo speed controller is designed, and in combination with a robot dynamical model, an optimal visual servo speed controller is designed. A constraint satisfaction condition for constraining joint angular velocity within a preset range is obtained through a time-varying asymmetric control obstacle function, an optimal torque controller is designed in combination with a visual servo characteristic error constraint satisfaction condition, a torque control signal meeting performance constraint is obtained in combination with quadratic programming, and the robot is driven to reach an expected characteristic position. The success rate of a visual servo task is improved, and high-precision visual guide assembly work of the mechanical arm is achieved.
Owner:HUNAN UNIV

Systems and methods for a vision guided end effector

Systems and method for an object from a plurality of objects are disclosed. An image of a scene containing the plurality of objects is obtained, and a segmentation map is generated for the objects in the scene. The shapes of the objects are determined based on the segmentation map. An end effector is adjusted in response to determining the shapes of the objects. The adjusting the end effector includes shaping the end effector according to at least one of the shapes of the objects. The plurality of objects is approached in response to the shaping of the end effector, and one of the plurality of objects is picked with the end effector.
Owner:INTRINSIC INNOVATION LLC

Guiding type monitoring method and system based on wireless surface myoelectricity analysis feedback instrument

The invention relates to the technical field of electromyographic signal monitoring, and discloses a guided monitoring method and system based on a wireless surface electromyographic analysis feedback instrument. The method comprises the following steps: acquiring electromyographic signal time sequence data and limb movement track space coordinate information when a target muscle group moves through a multi-channel wireless surface electromyographic sensor; muscle activation intensity and fatigue change features are extracted, a joint activity angle change sequence is calculated, and a muscle-joint collaborative activity feature matrix is generated through space-time alignment fusion; analyzing signal transduction delay and amplitude matching degree in the matrix, and evaluating the nerve driving coordination level; according to the deviation from the preset standard mode, generating a real-time biological feedback signal containing an action correction instruction and a muscle activation intensity adjustment parameter; and converting into a tactile vibration mode and a visual guidance mark to be output. According to the method, synchronous acquisition and fusion analysis of multi-dimensional motion information are realized, and visual guidance is provided through multi-modal feedback.
Owner:MEI HOSPITAL UNIV OF CHINESE ACAD OF SCI +1

Augmented reality guidance for vascular procedures

Devices and methods for performing an interventional vascular procedure with visual guidance using one or more optical head mounted displays are disclosed. Devices and methods for compensating the display of an optical head mounted display for cardiac and / or respiratory motion are disclosed.
Owner:LANG PHILIPP K

Ablation puncture surgery navigation system under AI visual guidance

The invention belongs to the technical field of ablation puncture navigation, and particularly relates to an ablation puncture surgery navigation system under AI visual guidance. Through cooperative work of the phase monitoring module, the channel construction module, the needle moving control module, the displacement prediction module and the feedback control module, an intelligent surgical navigation system is constructed, breathing phase information and multi-modal medical image data of a patient can be obtained in real time, and therefore a safe and optimized needle moving path is accurately planned, and the operation accuracy is improved. Meanwhile, through real-time monitoring and quantitative evaluation of parameters such as tissue deformation and pressure distribution in the needle moving process, potential operation risks can be found and corrected in time, smooth operation is ensured, in addition, the system can dynamically adjust the needle moving path and the puncture angle according to the real-time breathing state of a patient, and the operation safety is improved. The accuracy and the safety of the operation are further improved, so that intelligent management and personalized treatment in the ablation puncture operation process are realized.
Owner:CANYON MEDICAL INC

Method and apparatus for treating a joint, including the treatment of cam-type femoroacetabular impingement in a hip joint and pincer-type femoroacetabular impingement in a hip joint

A computer visual guidance system for guiding a surgeon through an arthroscopic debridement of a bony pathology, wherein the computer visual guidance system is configured to: (i) receive a 2D image of the bony pathology from a source; (ii) automatically analyze the 2D image so as to determine at least one measurement with respect to the bony pathology; (iii) automatically annotate the 2D image with at least one annotation relating to the at least one measurement determined with respect to the bony pathology so as to create an annotated 2D image; and (iv) display the annotated 2D image to the surgeon so as to guide the surgeon through the arthroscopic debridement of the bony pathology.
Owner:STRYKER CORP

Large steel structure corrosion damage integrated repair robot and control method

The invention belongs to the technical field of steel structure damage repair. The invention provides a large steel structure corrosion damage integrated repairing robot and a control method. The robot comprises a robot body, and a force control servo motor, an automatic polishing module, a damage identification camera, an air compression pump, a paint storage box, a control terminal, a magnetic adsorption module, a pipeline climbing module, a paint film thickness measuring module and an automatic paint spraying module which are arranged on the robot body. A robot compliance control strategy integrating force feedback, visual guidance and other modes is provided, dynamic parameter adjustment is combined, efficient and compliance control over the rust removal and spraying process of the repairing robot is achieved, the high efficiency and stability of the corrosion damage repairing process are ensured, and the corrosion damage repairing efficiency is improved. And flexible movement and efficient operation of the integrated repairing robot in a complex space structure are achieved.
Owner:SHANDONG UNIV

Visual guidance laser deburring device for nanocrystalline magnetism isolating sheet and application of visual guidance laser deburring device

The invention belongs to the technical field of machine vision positioning and guiding, and discloses a nanocrystalline magnetism isolating sheet vision guiding laser deburring device and application thereof, and the nanocrystalline magnetism isolating sheet vision guiding laser deburring device comprises an image acquisition module, an image preprocessing module, a central control module, a laser module, a positioning module, a collection module, a data analysis module and a display module; according to the visual guidance technology, an advanced visual recognition system is introduced, the burr position is accurately positioned by monitoring the surface state of a workpiece in real time, and therefore the more intelligent laser deburring process is achieved. And laser parameter optimization: parameters such as wavelength, power and pulse frequency of laser are optimized according to different materials and burr types, so that the optimal deburring effect is achieved, and meanwhile, the completeness of the workpiece is ensured. And in the laser deburring process, environment-friendly materials and technologies are adopted, the influence on the environment is reduced, and the safety in the operation process is enhanced.
Owner:KAIFENG VOCATIONAL COLLEGE

Tomato stem picking point attitude estimation method

The invention discloses a tomato stem picking point attitude estimation method, and relates to a computer vision processing technology. The method comprises the following steps: detecting a long-range directional frame target, acquiring a color flow by a depth camera, and detecting position information and shielding conditions of fruits and fruit stems through a directional frame; visual guidance: matching fruit stems based on tomato growth constraint conditions, and visually guiding the mobile platform and the mechanical arm to move in a coupling manner until the fruit stems are observed when the fruit stems are not matched; detecting close-range key points, regulating and controlling a mechanical arm to a close-range observation position, identifying two points of a main stem and three points of a fruit stem through a key point detection model, and extracting point clouds; performing point cloud data processing, removing point cloud noise through point cloud filtering, and performing adaptive compensation on key points with depth anomaly by using a neighborhood mean value; calculating picking poses, and establishing the picking poses of the fruit stem shear points according to the three-dimensional information of the five key points; according to the method, the problem of tomato shielding in a greenhouse complex scene can be effectively solved, and the fruit stem shearing point pose is obtained.
Owner:CHINA AGRI UNIV

Text knowledge enhanced scene graph generation method

The invention relates to a text knowledge enhanced scene graph generation method, and belongs to the field of computational vision. The method comprises the following steps: extracting text features of text information; extracting visual features and entity labels of the scene image, and combining the extracted visual features into paired entity pair features; introducing entity pair feature guidance to generate visual guidance text feature representation, so that the extracted text features are associated with visual entities; obtaining refined entity enhancement features and entity-to-visual predicate features based on the visual features and the entity tags; performing cross-modal alignment on the visual guidance text features and the entity pair visual predicate features to obtain graphical multi-modal feature representation; and inputting the multi-modal feature representation and the entity enhancement feature into a multi-layer perceptron for prediction to obtain prediction output of the entity pair and the entity pair relationship. According to the invention, the accuracy of entity object prediction and entity relationship prediction in the scene graph generation process can be improved.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Modularized visual guidance robot feeding and discharging device

The invention discloses a modular visual guidance robot feeding and discharging device, and relates to the technical field of robot-assisted feeding and discharging equipment, and the modular visual guidance robot feeding and discharging device comprises a visual module which is installed on a production line and is used for identifying the position of a workpiece and outputting coordinate information; the manipulator module is mounted on the production line, and a clamp connecting mechanism and an end effector are arranged at the tail end of the manipulator module; the clamp module is installed at the tail end of the mechanical arm module through a clamp connecting mechanism, and the clamp module is electrically connected with the tail end executor and used for grabbing a workpiece; and the control system module is electrically connected with the vision module, the manipulator module and the end effector and is used for controlling the manipulator module to act according to the coordinate information output by the vision module and controlling the clamp module to act through the end effector. The production requirements of diversified products on different production lines can be met, and the universality and adaptability of equipment are improved.
Owner:SICHUAN FUMOS IND TECH CO LTD

Mechanical arm visual guidance point cloud scanning method based on deep learning

The invention discloses a mechanical arm visual guidance point cloud scanning method based on deep learning. The method comprises the steps that a circular punctuation point is pasted to the upper right corner of a to-be-detected gap; a binocular camera on a tail end shaft of the mechanical arm collects a color image and a depth image and carries out registration; detecting a target point in real time; querying the registered depth image through a two-dimensional coordinate of a target point center in a pixel coordinate system obtained by a target detection network, and obtaining a depth value corresponding to the target point center in a camera coordinate system; the center coordinate of the target point is converted into a world coordinate system from a pixel coordinate system and sent to a mechanical arm; and after receiving the coordinates of the target point, the mechanical arm drives the point cloud scanning equipment at the tail end to move to the target point, scanning action is executed, and the point cloud scanning equipment transmits scanned assembling gap point cloud data to the upper computer. According to the invention, the gap of each part of the automobile can be rapidly positioned and accurately scanned in a complex scene, and the problems of tedious manual operation, low efficiency and limited measurement precision in a traditional method are effectively solved.
Owner:NANJING YUNTONG TECH CO LTD

Federal learning-based cross-brand household appliance maintenance knowledge sharing system and method thereof

The invention relates to the technical field of home appliance maintenance, in particular to a cross-brand home appliance maintenance knowledge sharing system and method based on federated learning, a multi-mode fault data collection and intelligent maintenance system integrates image, text, fault phenomena and multi-mode instruction data collection, and after pre-processing, the multi-mode fault data collection and intelligent maintenance system is established. A feature decoupling model is established through a maintenance knowledge analysis module, a cross-brand maintenance knowledge base stores general and specific fault information and assists knowledge migration, a federal learning training module adopts differential privacy homomorphic encryption, data privacy is protected, gradient aggregation cooperative training is achieved, a reality maintenance guidance terminal is augmented to visually guide maintenance, the efficiency is improved, and the maintenance efficiency is improved. The preventive maintenance module calculates the equipment maintenance cycle, generates a prevention scheme, and reduces the failure rate and cost. The system significantly improves the maintenance accuracy, rapidly fuses into a new brand, realizes knowledge sharing and utilization, and brings revolutionary revolutions to the household appliance maintenance industry.
Owner:XIAMEN OCEAN VOCATIONAL & TECH COLLEGE

Apple identification positioning and obstacle avoidance method based on zero sample and visual guidance

The invention discloses an apple recognition positioning and obstacle avoidance method based on zero samples and visual guidance. An improved YOLOV8 model is used for recognizing unknown category objects in a picking scene; semantic embedding of apples and branches is constructed by combining an external knowledge base Word2Vec, and unknown category objects in a picking scene are identified by using a zero sample learning method; constructing three-dimensional point cloud data of a fruit tree where an identification result is located, carrying out iterative convergence point cloud denoising by adopting a convex set constrained by an alpha norm, and updating point cloud coordinates; performing point cloud segmentation by using a potential energy function segmentation model; obtaining three-dimensional information of the apple and the obstacle through three-dimensional reconstruction of the point cloud feature information; extracting three-dimensional space position data of the branches at different time points to form a time sequence data set, and predicting the motion trail of the branches by using LSTM (Long Short Term Memory); through branch coordinate data of the point cloud and the LSTM, predicting a motion track of the branch, and utilizing a geometric collision detection method to evaluate and predict a collision risk between a robot end effector and the branch; and planning an optimal obstacle avoidance path by using an A * algorithm.
Owner:JIANGSU UNIV

Generating modified digital images using deep visual guided patch match models for image inpainting

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly generating modified digital images utilizing a guided inpainting approach that implements a patch match model informed by a deep visual guide. In particular, the disclosed systems can utilize a visual guide algorithm to automatically generate guidance maps to help identify replacement pixels for inpainting regions of digital images utilizing a patch match model. For example, the disclosed systems can generate guidance maps in the form of structure maps, depth maps, or segmentation maps that respectively indicate the structure, depth, or segmentation of different portions of digital images. Additionally, the disclosed systems can implement a patch match model to identify replacement pixels for filling regions of digital images according to the structure, depth, and / or segmentation of the digital images.
Owner:ADOBE INC

Visual guidance automatic sorting and deviation rectifying method and system

The invention relates to the technical field of artificial intelligence, and discloses a vision-guided automatic sorting and deviation rectifying method and system.The vision-guided automatic sorting and deviation rectifying system comprises a vision parameter processing module, a sorting strategy decision module and a deviation rectifying execution control module, a real-time judgment mechanism of dynamic and static resolution differences is established by setting a resolution collaborative correction end, and the deviation rectifying execution control module is established; a self-adaptive interpolation algorithm is adopted to adjust visual feature data, so that the system can eliminate imaging resolution deviation caused by ambient light and transmission vibration, the acquisition accuracy of material surface texture features is ensured, sorting identification errors caused by projection chromatic aberration are avoided, the environmental adaptability of the visual guidance system is improved, and the visual guidance system is more accurate in image quality. The position and posture coupling analysis end is arranged, the dynamic matching degree of the position and posture offset of the materials and the motion trail of the mechanical arm is monitored in real time, the grabbing angle offset is automatically corrected through a space coordinate compensation mechanism, and it is guaranteed that the relative space position of an end effector and the materials is in the optimal grabbing state all the time.
Owner:HANGZHOU MOXIN INTELLIGENT TECH CO LTD