一种多区域高斯概率融合模型的被动式人员定位方法及设备
By using a multi-region Gaussian probability fusion model and leveraging line-of-sight links and Gaussian distribution models, the problem of identifying false targets in passive positioning technology was solved, reducing data acquisition costs and improving positioning accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- TIANJIN UNIV OF COMMERCE
- Filing Date
- 2026-04-09
- Publication Date
- 2026-07-17
AI Technical Summary
In multi-person positioning scenarios, passive positioning technology is prone to false target positioning problems, and high-density fingerprint point collection increases the manual cost of constructing the training database.
A multi-region Gaussian probability fusion model is adopted. By setting up a passive positioning system, a line-of-sight link is formed using a signal transmitter and receiver. True target samples are extracted and clustered to establish true and false target Gaussian distribution models. Multiple Gaussian distribution models are fused to distinguish the true and false of candidate targets.
Accurate identification of false targets reduces the manual and time costs of training data collection, promoting the application of passive human positioning technology in smart buildings and smart cities.
Smart Images
Figure CN122109990B_ABST