Method and system for realizing combined semantic hierarchical connection model based on panoramic area scene perception

A scene-aware and regional technology, applied in biological neural network models, character and pattern recognition, instruments, etc., can solve the problems of lack of optimization methods, limited application range and scientific value, lack of versatility, etc., to achieve accurate and fast spatial information, The algorithm is simple and efficient, and the effect of high boundary precision
CN110533048AActive Publication Date: 2019-12-03SHANGHAI JIAO TONG UNIV
1 Cites 15 Cited by

Patent Information

Authority / Receiving Office
CN Β· China
Patent Type
Applications(China)
Current Assignee / Owner
SHANGHAI JIAO TONG UNIV
Publication Date
2019-12-03

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a method and a system for realizing a combined semantic hierarchical connection model based on panoramic area scene perception. The system comprises an ROI extraction module, apanoramic region segmentation module, a spatial information acquisition module and a multi-level modeling module; the ROI extraction module is in segmentation connection with a target instance and transmits target salient region information; the panoramic region segmentation module is connected with the interest point 3D reconstruction module and transmits region boundary information; the spatialinformation acquisition module is connected with the semantic subspace model and transmits region position correlation information, and the multi-level modeling module outputs spatial semantics and correlation degree information of each region. On the basis that the ROI is obtained through region significance for panoramic segmentation, on the premise that interest points are extracted for geometric reconstruction and element space semantic information association, multi-level modeling of scene perception is achieved according to analysis of probability symbiosis of scene composition elements.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to a technology in the field of graphics processing, in particular to a method and system for realizing a combined semantic hierarchical connection model based on panoramic area scene perception. Background technique

[0002] In the late 1970s and early 1980s, a complete scene understanding system began to appear, but the existing systems that try to fully understand the visual scene are not self-adaptive, and need to manually set parameters for specific scenes, which cannot be applied to new scene. Although the global energy optimization method based on the high-order Markov model can effectively describe the structural prior of the scene, express the local and global prior of the scene, and effectively integrate multiple scene understanding methods under the same energy optimization framework, but The contradiction between expressiveness and solvability. Although many complex high-order energy models provide rich const...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More