Patents
Literature
14 results about "Interest point detection" patented technology
Efficacy Topic
Property
Owner
Technical Advancement
Application Domain
Technology Topic
Technology Field Word
Patent Country/Region
Patent Type
Patent Status
Application Year
Inventor
Interest point detection is a recent terminology in computer vision that refers to the detection of interest points for subsequent processing. Historically, the notion of interest points goes back to the earlier notion of corner detection, where corner features were in early work detected with the primary goal of obtaining robust, stable and well-defined image features for object tracking and recognition of three-dimensional CAD-like objects from two-dimensional images. In practice, however, most corner detectors are sensitive not specifically to corners, but to local image regions which have a high degree of variation in all directions. The use of interest points also goes back to the notion of regions of interest, which have been used to signal the presence of objects, often formulated in terms of the output of a blob detection step. While blob detectors have not always been included within the class of interest point operators, there is no rigorous reason for excluding blob descriptors from this class. For the most common types of blob detectors (see the article on blob detection), each blob descriptor has a well-defined point, which may correspond to a local maximum, a local maximum in the operator response or a centre of gravity of a non-infinitesimal region. In all other respects, the blob descriptors also satisfy the criteria of an interest point defined above.
SuperPoint variant network image feature extraction method and system based on multi-attention mechanism
PendingCN120431426ADrawing from basic elementsBiological modelsFeature extractionInterest point detection
The invention provides a SuperPoint variant network image feature extraction method and system based on a multi-attention mechanism, a SuperPoint variant network is designed, the SuperPoint variant network comprises a backbone coding network, an interest point decoding network and a descriptor decoding network, an RE-SE module is designed in the backbone coding network, and the rotation robustness of the backbone coding network is enhanced; an SW-MA module is applied to the POI decoding network, so that the local feature extraction capability of the POI decoding network is improved; an EN-GA module is applied in a descriptor decoding network, the calculation amount is reduced through downsampling, and the network pays attention to more abstract features. The SuperPoint variant network provided by the invention can maintain high-precision interest point detection and descriptor matching capability in a complex scene, and further improves the pose estimation precision and robustness of the SLAM system.
Owner:JIANGSU UNIV OF SCI & TECH
Anesthesia puncture positioning method and system based on visual assistance
The invention relates to the technical field of vision assistance, and discloses an anesthesia puncture positioning method and system based on vision assistance, and the method comprises the steps: accurately positioning an anesthesia puncture point through multi-view image fusion, hyperspectral image processing, image preprocessing, illumination equalization, edge enhancement, depth feature extraction and the like. The method comprises the following steps: firstly, constructing an image coordinate system, collecting a plurality of camera images, and obtaining a fused clear image through a designed multi-view fusion algorithm and distance calculation; and in combination with a hyperspectral image fusion algorithm, the image quality is further improved. Then, residual mapping filtering denoising and local histogram enhancement are used for illumination equalization, and the image contrast and edge details are enhanced; a convolutional neural network is adopted, interest point detection is carried out, a Hessian matrix is utilized to describe image second-order changes, and local depth features are extracted. And accurate positioning of an anesthesia puncture point is realized through a weighted soft voting classifier and a dynamic threshold method.
Owner:THE EIGHTH DIVISION SHIHEZI GENERAL HOSPITAL (SHIHEZI PEOPLES HOSPITAL THE THIRD AFFILIATED HOSPITAL OF SHIHEZI UNIV SCHOOL OF MEDICINE)
Visual odometer method, system and equipment based on point-line characteristics and medium
InactiveCN119555105AHigh precisionimprove accuracyImage analysisBiological modelsEngineeringOdometer
The invention discloses a visual odometer method, system and device based on point-line features and a medium. Visual odometers are crucial to navigation and planning of autonomous robots, but weak light conditions, violent illumination changes and low texture scenes make a significant challenge to odometer estimation. Therefore, according to the visual odometer method based on the point-line features, the point-line features and deep learning are integrated, the point features and the line features are obtained through a self-supervised learning model for interest point detection and a line detection mode combining line light flow tracking and cross constraint, and the influence of complex lighting conditions is overcome. Meanwhile, the key frame is selected based on point feature counting and line feature overlapping angle constraint, and sparse matching is performed by integrating the convolutional neural network and the graph neural network, so that the accuracy and the calculation efficiency are improved.
Owner:SHENZHEN UNIV
Method and device for point of interest (POI) detection clustering using image embeddings
ActiveUS20250061687A1ForecastingNavigation instrumentsInterest point detectionOptical character recognition
Aspects concern a method for point of interest (POI) detection clustering using image embeddings, the method including obtaining, using a neural network, the image embeddings from POI detections including portions of one or more images that are captured in an area of a map, in which at least one POI is detected, calculating an embedding distance between the obtained image embeddings, and recognizing texts included in the POI detections. The method further includes calculating an optical character recognition (OCR) distance between the recognized texts, calculating a final distance between the POI detections, based on the calculated embedding distance and the calculated OCR distance, and clustering the POI detections, based on the calculated final distance.
Owner:GRABTAXI HOLDINGS PTE LTD
Graphics-Informed Data-Contextual Report Compilation via Automated Point-of-Interest Detection in Visualization Inventories
PendingUS20260057182A1Drawing from basic elementsDigital data information retrievalLinguistic modelTheoretical computer science
A graphical, hierarchical document stream browser and environment for semantic (e.g. framing) and performance data analysis and interactive visualization integrates three scales: entities (competitive), entity (diachronic), and document (linguistic). The document level includes annotation and computational linguistics facilities; the entity level has calendrical and time-series focus. All levels emphasize deep linkage and network (i.e. connective / relational space) view of objects, with user-configurable connectivity. Large language model (LLM) integrations provide synthetic advisories, public opinions, reports, plot insights, comparisons; traditional natural language processing techniques and neural models are also employed. A smart plot system includes a “plot cart” and interpreter with an analysis snippet library. Graph structure may arise via adjustable blending or perceptual optimization of canned attribute-related distance functions or via link-induction query language with deep “semantic stored procedure” subexpressions, or feed into graph neural network-style inference for predictions. Most non-LLM ongoing computational load is client-side, using precomputed hierarchical summary files.
Owner:PONTIMYX CORP
Repeatability predictions of interest points
The present disclosure describes approaches for evaluating interest points for localization uses based on a repeatability of the detection of the interest point in images capturing a scene that includes the interest point. The repeatability of interest points is determined by using a trained repeatability model. The repeatability model is trained by analyzing a time series of images of a scene and determining repeatability functions for each interest point in the scene. The repeatability function is determined by identifying which images in the time series of images allowed for the detection of the interest point by an interest point detection model.
Owner:NIANTIC SPATIAL INC
Interest point detection model training method, product positioning method, equipment and medium
The invention discloses an interest point detection model training method, a product positioning method, equipment and a medium, and relates to the technical field of computer vision, and the method comprises the steps: obtaining a sample image pair; extracting first information of each interest point in the original image through a to-be-trained interest point detection model, and extracting second information of each interest point in the transformed image; performing homography transformation on the position of each interest point in the original image, matching with the position of each interest point in the transformed image to obtain each interest point pair, and matching with the position of each interest point in the original image to obtain each interest point pair; calculating the sample loss of the sample image pair based on the first information and the second information corresponding to each interest point pair; and adjusting parameters of the interest point detection model based on the sample loss of the plurality of sample image pairs. According to the unsupervised interest point detection model training method provided by the invention, the method does not need to depend on any manual annotation data, and the training efficiency and the adaptive capacity of the model in different scenes are improved.
Owner:GOERTEK INC
Method and apparatus for improving detection accuracy of point of interest under various lighting conditions
Owner:LG ELECTRONICS INC
Systems and methods for real-time point-of-interest detection and overlay
PendingUS20250363687A1Image analysisCharacter and pattern recognitionPattern recognitionComputer graphics (images)
A region of interest is determined based on metadata associated with an image. The region of interest is then sliced into a plurality of slices. POI information is retrieved for each respective slice. An overlay for at least one POI is then generated for display over the image.
Owner:ADEIA IMAGING LLC
Repeatability predictions of interest points
The present disclosure describes approaches for evaluating interest points for localization uses based on a repeatability of the detection of the interest point in images capturing a scene that includes the interest point. The repeatability of interest points is determined by using a trained repeatability model. The repeatability model is trained by analyzing a time series of images of a scene and determining repeatability functions for each interest point in the scene. The repeatability function is determined by identifying which images in the time series of images allowed for the detection of the interest point by an interest point detection model.
Owner:NIANTIC SPATIAL INC
Focusing control method and device based on image signal, equipment and medium
ActiveCN119485018Aimprove integrityquality improvementTelevision system detailsColor television detailsImaging qualityComputer graphics (images)
The invention relates to the technical field of shooting lenses, and relates to a focusing control method and device based on an image signal, equipment and a medium. Collecting distributed images through a plurality of lenses of the camera device; fusing the distributed images based on the feature information in the distributed images to generate a panoramic image; detecting a corresponding image area in the panoramic image according to a preset interest point of each lens, and evaluating feature quality corresponding to the image area; determining an initial step length of focal length adjustment of each lens according to the feature quality, and determining an iterative step length of focal length adjustment of each lens according to the initial step length of the adjacent lens; and adjusting the focusing position of each lens based on the initial step length and the iterative step length. According to the method, the image area needing to be optimized can be accurately determined, the optimal focusing position is gradually approached through combined use of the initial step length and the iterative step length, the image quality and definition of the areas corresponding to the interest points are further improved, and cooperative and unified focusing adjustment under multiple lenses is achieved.
Owner:SHENZHEN CAN-RILL TECH CO LTD
Bullet trace recognition algorithm of rotation invariant coordinate convolutional neural network
PendingCN119579916Abig angleCharacter and pattern recognitionNeural learning methodsAlgorithmInterest point detection
The invention discloses a bullet trace identification algorithm based on a rotation-invariant coordinate convolutional neural network. The algorithm is used for realizing key point detection and feature matching of bullet traces. The algorithm comprises the following steps: collecting bullet traces of gun shooting; processing the bullet mark data by using a confocal microscope; reducing image noise through a three-dimensional spline filter; calling a coordinate generation function to generate coordinate points and establishing a coordinate system; carrying out image feature extraction on the trace image by using a self-supervised interest point detection and description algorithm; a non-maximum suppression algorithm is used for post-processing in feature point detection; and rotating the image and generating a new coordinate system, and performing feature matching on the trace image by using a rotation invariant coordinate convolutional neural network under the new coordinate system so as to judge the matching degree of the bullet. The method can further provide support for bullet trace matching and further provide guarantee for case detection.
Owner:NANJING TECH UNIV
Invalid interest point detection method and device and electronic equipment
The invention discloses an invalid interest point detection method and device and electronic equipment, and relates to the technical field of map making. The method comprises the following steps: acquiring a target area feature of map data of a target area type, thereby acquiring a target interest point density corresponding to the target area feature; wherein the target interest point density is calculated by a pre-trained regression model; acquiring map interest point density corresponding to the target area feature; and calculating a ratio of the map interest point density to the target interest point density, and if the ratio is greater than a ratio threshold, determining that invalid interest point information exists in the map data of the target area type. According to the embodiment, the technical problem that invalid interest point detection efficiency is low can be solved.
Owner:TOYOTA JIDOSHA KK
