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

1703 results about "Scene graph" patented technology

A scene graph is a general data structure commonly used by vector-based graphics editing applications and modern computer games, which arranges the logical and often spatial representation of a graphical scene.

Method, system, and computer program product for visualizing a data structure

A data structure visualization tool visualizes a data structure such as a decision table classifier. A data file based on a data set of relational data is stored as a relational table, where each row represents an aggregate of all the records for each combination of values of the attributes used. Once loaded into memory, an inducer is used to construct a hierarchy of levels, called a decision table classifier, where each successive level in the hierarchy has two fewer attributes. Besides a column for each attribute, there is a column for the record count (or more generally, sum of record weights), and a column containing a vector of probabilities (each probability gives the proportion of records in each class). Finally, at the top-most level, a single row represents all the data. The decision table classifier is then passed to the visualization tool for display and the decision table classifier is visualized. By building a representative scene graph adaptively, the visualization application never loads the whole data set into memory. Interactive techniques, such as drill-down and drill-through are used view further levels of detail or to retrieve some subset of the original data. The decision table visualizer helps a user understand the importance of specific attribute values for classification.
Owner:RPX CORP +1

Network attack scene generating method based on multi-source alarm logs

InactiveCN104539626AReflects security threat statusShow intentData switching networksCorrelation analysisNetwork attack
The invention relates to a network attack scene generating method based on multi-source alarm logs. The network attack scene generating method includes the steps that firstly, the alarm logs generated by multiple network security protection devices are collected, effective alarm log data are extracted through preprocessing, and noise, redundancy or ineffective logs are removed; for the effective alarm logs acquired by one device, log format differences of different devices are shielded through single-source log aggregation and mapping, and attack event information is analyzed and extracted; attack events extracted from different sources are fused and analyzed, and network attack events with high credibility are generated; then through correlation analysis of the attack events, a network attack scene graph is generated, and the whole attack process of one attack operation is analyzed. Due to the fact that the multi-source logs are fused, the analyzed attack event information can more completely and more reliably depict attacks to which a network is subject, attack scenes are acquired through correlation analysis of the attack events, the intentions of attackers can be more clearly shown, and the security threat state of the network can be more clearly reflected.
Owner:THE PLA INFORMATION ENG UNIV

Indoor and outdoor seamless positioning system integrated with satellite navigation and bluetooth technology, and method thereof

ActiveCN104849740ASolve the accuracy problemOvercome the defect of inaccurate positioningSatellite radio beaconingBluetoothPositioning system
The invention relates to an indoor and outdoor seamless positioning system integrated with satellite navigation and a bluetooth technology, and a method thereof. The system comprises an outdoor satellite positioning module, an indoor bluetooth positioning module, an indoor and outdoor positioning fusion switchover module, and an electronic map display module. The outdoor satellite positioning module performs outdoor positioning by using GPS or Beidou Satellite navigation terminals. The indoor bluetooth positioning module performs indoor positioning by using a field intensity attenuation principle and a three-dimensional spatial positioning algorithm. The indoor and outdoor positioning fusion switchover module performs fusion, switchover, and integration on indoor and outdoor positioning methods according to strength of indoor and outdoor positioning communication signals and based on a federated kalman filter, so as to realize smooth transition of indoor and outdoor positioning. The electronic map display module displays positioning results based on two-dimensional electronic maps or indoor plane graphs, and three-dimensional building model scene graphs. The system can provide an indoor and outdoor integrated positioning function for intelligent mobile devices, and positioning speed is fast, and positioning precision is high.
Owner:FUZHOU UNIV

Cascaded convolutional neural network-based quick detection method of irregular-object grasping pose of robot

InactiveCN108510062AImprove real-time performanceGuaranteed to be dynamically scalableImage enhancementImage analysisColor imageNerve network
The invention relates to a cascaded convolutional neural network-based quick detection method of an irregular-object grasping pose of a robot. Firstly, a cascaded-type two-stage convolutional-neural-network model of a position-attitude rough-to-fine form is constructed, in a first stage, a region-based fully convolutional network (R-FCN) is adopted to realize grasping positioning and rough estimation of a grasping angle, and in a second stage, accurate calculation of the grasping angle is realized through constructing a new Angle-Net model; and then current scene images containing to-be-grasped objects are collected to be used as original on-site image samples to be used for training, the two-stage convolutional-neural-network model is trained by means of a transfer learning mechanism, then each collected monocular color image is input to the cascaded-type two-stage convolutional-neural-network model in online running, and finally, an end executor of the robot is driven by an obtainedgrasping position and attitude for object grasping control. According to the method, grasping detection accuracy is high, detection speed of the irregular-object grasping pose of the robot is effectively increased, and real-time performance of running of a grasping attitude detection algorithm is improved.
Owner:SOUTHEAST 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