14 results about "Feature orientation" patented technology

The invention discloses a ring main unit inspection robot autonomous navigation method and system based on SLAM, particularly relates to the technical field of robot autonomous navigation and intelligent inspection, and is used for solving the problem of positioning drift caused by repeated features of an existing ring main unit scene. Semantic feature analysis and topological constraints are introduced into an SLAM processing flow, acquired image data and point cloud data are processed through a deep learning model, objects such as an electrical cabinet, a corridor channel and a cable trench are identified, and a semantic feature set with category labels and spatial position information is generated; and constructing a topological graph containing node spacing, connectivity and directivity constraints based on the semantic features, adding the topological graph as a constraint factor into SLAM back-end optimization, and performing joint optimization in combination with vision, a laser odometer and inertial prior information, thereby avoiding only depending on repeated geometric feature positioning, and improving the positioning accuracy. The problems of loopback misjudgment and drifting caused by feature confusion are reduced, and the pose resolving stability in the ring main unit environment is improved.

The invention relates to the technical field of image processing, and particularly provides an intelligent matting method and device, a medium, equipment and a product, and the method can comprise the steps: obtaining a to-be-processed object after preprocessing; wherein the object to be processed is an image or a video; processing the to-be-processed object by using a target matting model to generate mask data; wherein the target matting model comprises a feature positioning module, a feature reconstruction module and a prediction module; and repairing the mask data, and generating and outputting a matting result matched with a preset parameter. According to the embodiment of the invention, the longitude and efficiency of matting can be improved.

The invention discloses a sheet metal part manufacturability reasoning method based on space-semantic map alignment, and relates to the field of manufacturing-oriented design evaluation and industrial knowledge reasoning, and the method comprises the following steps: carrying out geometric analysis on a CAD geometric model of a sheet metal part to be evaluated; abstracting the geometric features and the topological / metric spatial relationship thereof into a computable spatial semantic graph; performing semantic analysis on the process specification described by a natural language, converting the process rule into formalized logic check expression by using a large language model through context learning, and generating an executable domain-specific language check script; executing the script on a spatial semantic graph, realizing deterministic reasoning through graph matching and attribute verification, and completing accurate mapping and violation detection of text rules and geometric features; and outputting an interpretable diagnosis result containing violation feature positioning, triggering rules and numerical evidence. In order to solve the problems that a process rule'natural language-geometric model 'has a semantic gap, a traditional rule system is poor in adaptability, and an end-to-end learning method is high in data dependence and cannot be explained, a new rule can be quickly adapted under the condition that a large amount of data does not need to be labeled and a model does not need to be retrained; the method can accurately identify the violation of the micro-size and spatial relationship, and has reasoning preciseness, interpretability and engineering availability.

The invention relates to the technical field of image sensing, general image recognition and feature positioning under computer vision, and discloses an acupuncture point positioning method and system based on artificial intelligence, and the method comprises the steps: obtaining a non-rigid target section image through an image collection module; the key point identification module determines topological anchor points at two ends of the section; the reference construction module establishes a structure reference vector; a deflection calculation module extracts surface texture feature points, obtains a high-frequency component and a low-frequency component through multi-scale frequency domain decomposition, and determines a spatial deflection parameter based on the gradient of the energy distribution ratio of the high-frequency component and the low-frequency component; the proportion compensation module corrects a target distribution proportion coefficient; according to the method, the pose is inversed by using the scale invariance between the frequency domain components, the decoupling of the anatomical positioning logic and the pixel space is realized, and the non-linear interference of the non-uniformity of the biological surface and the dynamic environment illumination on the positioning precision is eliminated.

The invention relates to a multi-task face sensing method and device, electronic equipment, a storage medium and a computer program product. The multi-task face sensing method comprises the steps that a to-be-detected face picture is acquired; a to-be-detected face picture is input into the multi-task face perception model, face features and positioning reference points are extracted from the face picture through the multi-task face perception model, and the positioning reference points are used for executing a positioning task about face key point detection; semantic reference points are calculated based on the positioning reference points through a multi-task face perception model, and the semantic reference points are used for executing semantic tasks about face state detection; and executing a positioning task and a semantic task based on the face features, the positioning reference points and the semantic reference points through a multi-task face perception model. Therefore, by explicitly utilizing the physical representation of the face key points, effective supervision for the semantic reference points is realized, the guiding effect of the face key points on the face perception task is enhanced, and the prediction effect of the face perception model can be improved.

The application discloses a kind of based on machine vision's patch type infrared receiving head appearance detection method and system, belong to computer vision detection field.Method includes: through bottom collimating backlight source irradiation to be measured receiving head, utilize the image of two telecentric cameras of symmetrical arrangement Synchronous acquisition pin;Sub-pixel level feature positioning is carried out to image and rejects reflection false feature point;Based on binocular vision principle, reconstruct the three-dimensional space coordinates of pin end;Adopt lowest multipoint method to construct reference plane, calculate the vertical distance of each pin to reference plane as coplanarity deviation;Deviation and tolerance threshold are compared, and output determination signal.System includes object table, bottom collimating backlight source, double-side telecentric camera, hardware level synchronous trigger unit, image processing and three-dimensional reconstruction unit, coplanarity evaluation and determination unit.The application can high-precision measurement pin coplanarity, eliminate perspective distortion and stray light interference, suitable for on-line full inspection on automatic production line.

This application provides a vision-guided robotic arm assembly method and system, and a computer-readable medium, which can solve the technical problem of poor accuracy and stability in guided assembly in related technologies. The method includes: determining an initial detection point; obtaining a first center position based on the position of the target to be assembled in a first camera image; using the first center position to guide the collaborative arm to move so that the position of the target to be assembled in the camera image is a first preset center of the camera image; obtaining a feature localization result based on the geometric features of the target to be assembled in a second camera image; obtaining a second center position based on the feature localization result and a second preset center; using the second center position to make the position of the target to be assembled in the camera image a second preset center of the camera image; and obtaining a guided assembly path based on the initial detection point, the first center position, and the second center position. Using a 2D camera for object recognition and feature detection improves the accuracy and stability of the guided assembly.

Described herein are techniques for imaging and / or measuring a subject's eye, including the subject's retina fundus. In some embodiments, one or more processors may be used to generate a graph from an image and / or measurement (e.g., an optical coherence tomography image and / or measurement), which can be useful for locating features in the image and / or measurement. For example, the image and / or measurement can include a subject's retina fundus and the features may include one or more layers and / or boundaries between layers of the subject's retina fundus in the image and / or measurement.

The invention belongs to the technical field of helicopter surface spraying, and particularly relates to a helicopter pose determination method used before automatic paint spraying, which comprises the following steps: step 1, according to the overall appearance structure characteristics of a helicopter, dividing the helicopter into a front-section fuselage and a rear-section fuselage according to the space, and selecting feature point positions on the front-section fuselage and the rear-section fuselage; 2, establishing a workshop unified coordinate system, and determining the pose of the robot in the workshop coordinate system; 3, scanning the feature point positions of the front helicopter body, and fitting the feature point positions with the feature point positions at the corresponding positions in the original helicopter digital model; 4, scanning, correcting and compensating feature point positions of a rear-section helicopter body, and fitting the feature point positions with feature point positions at corresponding positions in the original helicopter digital model; 5, a spraying track is generated, and dynamic correction is carried out; according to the method, for the specificity of a helicopter product, feature positioning points are selected, coordinate system iteration calibration is carried out in a segmented recognition and fitting mode, the actual posture of the helicopter is accurately recognized, and data support is provided for spraying track correction of a paint spraying robot.

The application discloses a kind of CTP plate making quality detection analysis method based on image recognition technical field, it is related to the field of image recognition CTP plate making quality detection, including: using high-resolution image acquisition equipment Synchronous acquisition has been made CTP plate image and the printed matter image produced by the plate;With the geometric center outside the effective printing area of plate and corner point as physical reference mark, a unified coordinate system is constructed, and feature positioning and area division are carried out based on the unified coordinate system;By extracting multi-dimensional feature data such as dot gain and dirty dot coverage, generate deviation data set, and combine feature type and position relationship to carry out combined logic analysis to determine the reason of dot overexpansion and the root cause of dirty dot generation, realize the automatic detection and root cause tracing of CTP plate making quality, improve the detection efficiency.

The invention discloses a standard component automatic positioning method, electronic equipment and a storage medium, and relates to the technical field of computer-aided engineering. The automatic positioning method for the standard part comprises the following steps: acquiring an established standard part finite element model and a solid geometric model of a to-be-mounted position; identifying a plurality of mutually corresponding feature positioning points from the finite element model and the solid geometric model; based on the mutually corresponding feature positioning points, moving and rotating the standard component finite element model to be aligned with the target position of the solid geometric model through model transformation; and copying the positioned standard component finite element model, and applying the standard component finite element model to the installation positions of other standard components of the same type. A large amount of repeated manual operation is replaced by the automatic script, the positioning time of the standard component is shortened, and the modeling efficiency is improved.

The invention relates to the technical field of general testing, and discloses a Matlab-based test data feature positioning method and system, which are characterized in that data with different starting times and time lengths are quickly matched and merged by identifying the difference of test data time axes with different data sources and data formats, and feature parameters are specified, so that the test data feature positioning accuracy is improved. According to the method, the time position of the feature data to be identified is quickly positioned in cooperation with a sliding window method, and the equipment working performance test data in the corresponding time are read, so that the situation that multiple groups of data are aligned by using a manual contrast method is avoided, and the identification error when the equipment working performance parameters are identified by using a manual method is avoided. The feature positioning and segmented screening functions of the data can be realized, and the accuracy and the recognition efficiency of key parameter recognition are improved.

The invention discloses a blue film defect identification method, device and equipment and a readable storage medium, which are applied to the technical field of data processing, and the method comprises the steps: carrying out the feature positioning of a to-be-detected image, determining all feature regions of a blue film, carrying out the threshold segmentation and Blob analysis of the feature regions of the blue film, determining a normal feature region of the blue film, and carrying out the recognition of defects of the blue film. Determining an initial defect region according to all the feature regions of the blue film and the normal feature region of the blue film; after edge gradient detection is carried out on an S channel of the initial defect area, threshold segmentation and Blob analysis are carried out, and an area with color change is used as a suspected defect area; detecting the suspected defect area by using a feature detection algorithm to determine the blue film defect; and the feature detection algorithm is an algorithm for detecting by using features of the suspected defect area and determining the blue film defect category. According to the method, the to-be-detected image is analyzed and processed, the suspected defect area of the blue film is extracted, the suspected defect area is detected by using the feature detection algorithm, and the blue film defect is determined.

The application discloses a ship wake detection method and system based on a feature balance fusion technology, and belongs to the technical field of ocean detection. In the feature fusion part in the deep neural network, multi-dimensional feature cooperative fusion is adopted for feature fusion. Specifically, the first feature map output by the multi-dimensional feature embedded Gaussian non-local attention part is fused with the second feature output by the multi-dimensional cooperative attention, to obtain a final feature map, and feature positioning and classification are performed. The application utilizes multi-dimensional feature cooperative fusion to enable the network to simultaneously fuse low-dimensional features and high-dimensional features, which is helpful to solve the feature layer inconsistency problem existing in the single-stage target detection feature pyramid in the prior art, and better feature fusion effect is obtained.