An intelligent access control system
By fusing multimodal sensors and constructing a virtual access space envelope, accurate spatiotemporal alignment and deformation compensation of multimodal access data are achieved. This solves the problems of low spatiotemporal reference alignment accuracy of multi-sensor data and poor anti-tailgating detection accuracy in existing technologies, improves the accuracy of identity recognition and anti-tailgating detection capabilities, and effectively resists forgery attacks.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- XIAMEN QIUSHI INTELLIGENT NETWORK TECH CO LTD
- Filing Date
- 2026-05-20
- Publication Date
- 2026-06-19
AI Technical Summary
Existing multimodal intelligent access control systems pose security risks in peak, densely populated traffic scenarios due to backlight interference, low spatiotemporal alignment accuracy of multi-sensor data, and poor accuracy in anti-tailgating detection. This allows unauthorized personnel to tailgate into enterprise areas, and it is difficult to identify spoofing attacks.
A multimodal sensing fusion architecture is adopted, which includes radar probes, near-infrared multispectral cameras, and anti-tailgating buffer 3D structured light scanners. Through virtual passage space envelope construction, topological mesh discretization, and geometric deformation field correction technology, accurate spatiotemporal alignment and spatial deformation compensation of multimodal passage data are achieved. This is combined with a virtual unit displacement vector field and comprehensive passage confidence determination.
It improves the accuracy of identity recognition and anti-tailgating detection in complex environments, effectively resists forgery attacks, and ensures traffic safety and enterprise information security.
Smart Images

Figure CN122244983A_ABST