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

36 results about "Consistency rules" patented technology

Method for converting flat video to tridimensional video based on bidirectional tracing and characteristic points correction

The invention relates to a method for converting a plane video to a stereoscopic video, based on bidirectional tracking and characteristic dot correction, which pertains to the multimedia technical filed of computers. The method comprises the steps as follows: a whole plane video sequence is divided into subsequences which have relevant contents; a frame is appointed as a key frame; foreground object segmentation is carried out to the key frame, and corresponding depth maps and profile feature points are extracted; bidirectional tracking is carried out to obtain the profile feature points of a non-key frame; the profile feature points that do not meet the motion consistency rules is eliminated; the position of each profile feature point in the collection of the profile feature points of the non-key frame is adjusted to be on the profile of a corresponding foreground object so as to obtain the collection of the profile feature points corresponding to each non-key frame of the video subsequences and recover the foreground object profile of the non-key frame, thus the depth map sequence of an original plane video sequence is obtained; finally, a stereoscopic video sequence corresponding to the original plane video sequence is obtained. Based on the key frame, the method obtains the high-precision depth map of the video sequence, thus well realizing the conversion from the plane video to the stereoscopic video.
Owner:TSINGHUA UNIV

Multi-agent system motion control method based on improved physicomimetics

ActiveCN110275527AAchieving Gathering MovementSolve the boundary oscillation problemAutonomous decision making processPosition/course control in two dimensionsSimulationMulti-agent system
The invention discloses a multi-agent system motion control method based on improved physicomimetics, and relates to the field of multi-agent coordinated motion control. The method comprises the steps of: firstly establishing a motion model of a single agent, and describing the motion rules of the multiple agents by using a method of physicomimetic force; then, combineing the physicomimetics with classic cohesion, separation and speed consistency rules, and calculating a cohesion coefficient and a speed consistency coefficient by using the distance and the relative velocity speed; then, improving the effects of various items of the physicomimetics by attention parameter adjustment so that the agent selectively follow other agents or targets; finally, adjusting the motion of the agents through the improved physicomimetics so as to realize the cohesion motion, the speed consistency, and the group motion of the multi-agent system under a multi-objective environment. The method mainly solves the boundary oscillation of the classic multi-agent system motion control algorithm during the cohesion motion and the group motion problem of the multi-agent system in the multi-objective environment.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

An automatic calibration algorithm for multi-group multi-line laser radar

ActiveCN106872963BDisambiguating QuestionsCoordinate Transformation AccurateWave based measurement systemsData synchronizationRadar systems
The invention discloses an automatic calibration algorithm for a multi-group multi-line laser radar. The automatic calibration algorithm is implemented as follows: S1, a coordinate transformation relation initial value Tguess of a laser radar A and a laser B is estimated; S2, local sub map M construction is carried out on point cloud data collected by the laser radar A; S3, on the basis of hypotheses of data synchronization and track synchronization, the point data P<n>B are transformed to positions at the local sub map M at a time n by T<n>A and the Tguess and a near point at the local sub map M is found out by using a nearest neighbor point cloud searching algorithm; S4, on the basis of an environment consistency constraint, a multi-group calibration relation T<n>cali; between the laser radar A and the laser radar B is calculated; and S5, an abnormal sample point in a multi-group calibration matrix is eliminated by using a random sampling consistency rule and then averaging is carried out to obtain Tcali. According to the automatic calibration algorithm, a coordinate relationship between radars can be calibrated automatically only according to synchronization radar of the laser radar sensor, so that the operation becomes efficient and convenient; and the automatic calibration algorithm can be applied to calibration of a multi-radar system.
Owner:XIAMEN 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