Patents
Literature
Patsnap Copilot is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Patsnap Copilot

563 results about "Large target" patented technology

Video/audio intelligent analysis management control system

The invention relates to the fields of computer vision and artificial intelligence, in particular to the field of intelligent video analysis, and provides a video/audio intelligent analysis management control system. The invention aims to solve the problems of the existing intelligent video analysis system of high misinformation rate, high report missing rate, low accuracy, single working mode, failure of realizing transmission and storage as required, and the like. The system comprises a video/audio feature database, a video/audio acquisition module, a video/audio quality improvement module, a video/audio feature extraction module, a video/audio feature recognition module, a video/audio management control trigger rule judgment module and a video/audio real-time management control platform. The system has three working modes: front-end analysis, back-end analysis and distributed analysis. The system combines voice information and image information for intelligent analysis, thereby effectively reduces the misinformation rate and report missing rate of the intelligent video analysis system. The invention enhances the quality of the video/audio information and establishes a large target and behavior feature database, thereby enhancing the system accuracy and realizing management control as required.
Owner:王巍

Small target detection method based on multi-scale images and weighted fusion loss

The invention belongs to the field of image and video processing, and relates to a small target detection method based on multi-scale images and weighted fusion loss, and the method comprises the steps: extracting a plurality of groups of feature vectors from a plurality of different-scale images based on an improved Mask RCNN model, carrying out the fusion of the plurality of groups of feature vectors, and constructing a feature pyramid; generating a candidate detection box based on the feature pyramid and screening to obtain a suggested detection box; correspondingly returning the suggesteddetection boxes to the feature pyramid to generate feature maps of the suggested detection boxes, and performing aligned interception on the feature maps; inputting the aligned suggested detection boxes into a classifier layer to obtain category confidence coefficients and position offsets of the suggested detection boxes; in the test stage, screening a certain suggested detection box according tothe category confidence score of the suggested detection box, and performing non-maximum suppression; in the training stage, weighting the loss function calculated by detecting the small target feature layer and fusing with the loss function of detecting the large target layer and the middle target layer, thus the sensitivity of the model to the small target object is enhanced.
Owner:SOUTH CHINA UNIV OF TECH

Method and apparatus for the detection of noncovalent interactions by mass spectrometry-based diffusion measurements

The present invention provides a method and apparatus for detecting the noncovalent binding of a potential ligand (such as a drug candidate) to a target, e.g. a biochemical macromolecule such as a protein. The method is based on the Taylor dispersion of an initially sharp boundary between a carrier solution, and an analyte solution that contains the potential ligand(s) and the target. Dispersion profiles of one or more potential ligands are monitored by mass spectrometry at the exit of the laminar flow tube. Potential ligands will usually be relatively small molecules that have large diffusion coefficients. In the absence of any noncovalent interactions in solution, very steep dispersion profiles are expected for these potential ligands. However, a ligand that binds to a large target in solution, will show an apparent diffusion coefficient that is significantly reduced, thus resulting in a more extended dispersion profile. Noncovalent binding can therefore be detected by monitoring dispersion profiles of potential ligands in the presence and in the absence of the target. In contrast to other mass spectrometry-based methods for detecting noncovalent interactions, this method does not rely on the preservation of specific noncovalent interactions in the gas phase. This method has an excellent sensitivity and selectivity, therefore it can be used for testing multiple potential ligands simultaneously. The method is therefore useful for the high throughput screening of compound libraries.
Owner:UNIV OF WESTERN ONTARIO

An image small target detection method based on combination of two-stage detection

PendingCN109598290AFully excavatedReduce the problem of false detection and missed detection of small targetsCharacter and pattern recognitionPattern recognitionNetwork model
The invention discloses a small target detection method based on combination of two-stage detection. The method includes: Sending the original image into a first detector to detect a first-stage target B1; Fusing the output features of the shallow CNN and the output features of the deep CNN to obtain M1 ', and selecting a corresponding feature map M2 from the M1' by using B1; taking the M2 as an input feature map and sending the M2 to an RPN module and a classification and regression module of a second-stage detector for detection and positioning of a second-stage target; And adding d loss obtained from two-stage detection as the total Loss of the whole network to obtain an end-to-end detection network model. According to the invention, a two-stage detection network is constructed; A largetarget is accurately detected firstly, then a small target is detected in a large target area, and a detection frame of the small target is limited in a local area which is most possible and most easily detected, namely the area where the large target is located, so that complex background interference is effectively removed, the false detection probability is reduced, and the detection precisionof the small target and the small target in the image is improved.
Owner:SHANGHAI JIAO TONG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products