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

1558results about How to "Accuracy" patented technology

Camera pose estimation apparatus and method for augmented reality imaging

ActiveUS20100232727A1Satisfactory accuracyFast and efficient implementationImage enhancementImage analysis3d cameraCandidate key
An apparatus for providing an estimate for a 3D camera pose relative to a scene from 2D image data of 2D image frame provided by said camera. A candidate 2D key points detector determines candidate 2D key points from the 2D image frame. A detected 3D observations detector determines detected 3D observations from pre-recorded scene data and the candidate 2D key points. A detected 3D camera pose estimator determines a detected 3D camera pose estimate from the camera data, the detected 3D observations and the candidate 2D key points. A first storage stores the detected 2D candidate key points and the 2D image data, and outputs in response to a 3D camera pose estimate output previous 2D image data and candidate 2D key points related to a previous 3D camera pose estimate output. A second storage stores and outputs a previous 3D camera pose estimate. A tracked 3D observations detector determines tracked 3D observations from the 2D image data, the candidate 2D key points, the camera data, the previous 2D image data and candidate 2D key points, the previous 3D camera pose estimate and 3D scene model data. A pose estimate selector outputs a selected one of the detected camera pose estimate and the previous 3D camera pose estimate. A 3D camera pose estimator computes and outputs the 3D camera pose estimate from the camera data, the detected 3D observations, the tracked 3D observations and the selected 3D camera pose estimate.
Owner:APPLE INC

Virtual learning environment natural interaction method based on multimode emotion recognition

The invention provides a virtual learning environment natural interaction method based on multimode emotion recognition. The method comprises the steps that expression information, posture information and voice information representing the learning state of a student are acquired, and multimode emotion features based on a color image, deep information, a voice signal and skeleton information are constructed; facial detection, preprocessing and feature extraction are performed on the color image and a depth image, and a support vector machine (SVM) and an AdaBoost method are combined to perform facial expression classification; preprocessing and emotion feature extraction are performed on voice emotion information, and a hidden Markov model is utilized to recognize a voice emotion; regularization processing is performed on the skeleton information to obtain human body posture representation vectors, and a multi-class support vector machine (SVM) is used for performing posture emotion classification; and a quadrature rule fusion algorithm is constructed for recognition results of the three emotions to perform fusion on a decision-making layer, and emotion performance such as the expression, voice and posture of a virtual intelligent body is generated according to the fusion result.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Method and device for monitoring and controlling network risks

The invention provides a method and device for monitoring and controlling network risks. The method comprises the following steps: step one, selecting the sample space of network objectives of some network element (NE), carrying out statistic analysis on the sample point data of the sample space, and calculating a dynamic baseline, wherein the network objectives comply with a normal distribution character; step two, according to preset tolerability and the dynamic baseline, determining the upper tolerance limit and the lower tolerance limit of the network objectives as early warning thresholds for triggering an early warning generating mechanism of the predictive network objectives; and step three, judging whether values of the predictive network objectives which are monitored and controlled in real time exceed the early warning thresholds; and if the values exceed the early warning thresholds, triggering the early warning generating mechanism. By realizing a dynamic threshold method, the threshold values can be set more reasonably and accurately, multiple early warning grades can be triggered, accurate monitoring and control for networks is reached, hidden failures in the networks are found, and finally after-event problem analysis of the prior art for the network failures is changed into initiative monitoring and controlling of the network objectives before problems generate, thus effectively ensuring the normal operation of the networks.
Owner:成都亿阳信通信息技术有限公司

Method for evaluating compressibility of shale gas reservoir

The invention discloses a method for evaluating compressibility of a shale gas reservoir. The method sequentially comprises the following steps of (1) calculating a shale brittleness index Brit, (2), calculating a shale fracture toughness index Kn, (3), calculating a natural weak plane opening facility index Pn, (4), calculating a natural weak plane penetrated index Cn, (5), introducing a complex seam net probability index Fcf and a transforming volume probability index Fsrv, and determining a reservoir compressibility index FI, (6), according to the size of the reservoir compressibility index FI, evaluating the compressibility of a block shale reservoir. According to the method, various compressibility influence factors are considered, and particularly on the basis of a seam net forming mechanism, the influence of the natural weak plane is fully considered; the shortcomings of an existing evaluation method are overcome, and logging data are utilized for calculating brittleness and breaking toughness of the shale gas reservoir; and the dependency on experimental data is reduced. The method is used for evaluating the reservoir quality of a fractured well, has feasibility and accuracy and provides a new decision making method for facture well selecting and layer selecting of the shale gas reservoir.
Owner:SOUTHWEST PETROLEUM UNIV

Optimization method of intersection dynamic comprehensive evaluation and signal control system based on real-time simulation model

The invention discloses an optimization method of an intersection dynamic comprehensive evaluation and signal control system based on a real-time simulation model. Statistical analysis is performed on an intersection vehicle arrival time distribution law and a saturation time headway distribution law, simulation control is performed on vehicles monitored in real time, analytical calculation of traffic flow parameters of an intersection such as mean queue length, queue time and travel vehicle speed, and characteristics such as vehicle exhaust, oil consumption and noise, and acquired information is shared and an optimized signal control scheme is implemented by a third party control platform. The method has the advantages that a real-time data acquisition function is realized by test coils embedded in interfaces at the near end and the far end of an intersection entrance road; the simulation model adopts vehicle arrival and green light termination as triggering conditions of starting a simulation system traffic flow parameter configuration; a saturation time headway is adopted as a time series distribution basis of vehicle leaving; simulation car following and lane changing behaviors are realized by a series of algorithms; and a traffic simulation function has timeliness, accuracy and rapid response.
Owner:上海济安交通工程咨询有限公司
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