A key point mapping conversion method and system from two-dimensional space to three-dimensional space

By combining sparsification processing and Transformer encoders with strided convolutional layers and spatiotemporal constraint strategies, the problems of depth ambiguity and computational complexity in the mapping of key points from 2D space to 3D space are solved, achieving more efficient information utilization and detection accuracy.

CN117710198BActive Publication Date: 2026-07-10SOUTH CHINA UNIV OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SOUTH CHINA UNIV OF TECH
Filing Date
2023-11-22
Publication Date
2026-07-10

AI Technical Summary

Technical Problem

Existing technologies suffer from depth ambiguity and high computational complexity in keypoint mapping from two-dimensional to three-dimensional space, especially due to redundant sequence information and excessive computational resource requirements, resulting in low detection accuracy.

Method used

By improving data preprocessing, sequence aggregation, and supervised training methods, and by employing sparsification and Transformer encoders, combined with strided convolutional layers and spatiotemporal constraint strategies, information utilization and detection accuracy are improved.

Benefits of technology

With the same sequence length and computational cost, it improves information capture capability and key point detection accuracy, reduces sequence redundancy, and enhances the robustness and versatility of the model.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117710198B_ABST
    Figure CN117710198B_ABST
Patent Text Reader

Abstract

The application discloses a kind of two-dimensional space to three-dimensional space key point mapping conversion method and system, including sequence preprocessing module: the length of two-dimensional space key point sequence is obtained, carries out sparse preprocessing, obtains sparse two-dimensional space key point sequence;Mapping dimension-increasing module: sequence modeling is carried out to sparse two-dimensional space key point sequence, obtains three-dimensional space key point sequence after preliminary mapping;Sequence aggregation module: three-dimensional space key point of center target is obtained by compressing and aggregating three-dimensional space key point sequence after preliminary mapping;Training network module: end-to-end training is carried out to network using supervised learning, and mapping accuracy of three-dimensional space key point estimation network is improved using space-time constraint strategy;Visualization module is used to obtain visual result.The application has good robustness and universality, and can be widely applied in key point detection of a variety of objects.
Need to check novelty before this filing date? Find Prior Art