基于YOLOv8n的自动调焦眼镜焦距确定方法、系统、介质及设备
By using YOLOv8n-based autofocus glasses, image acquisition devices and neural network algorithms are employed to achieve classification, detection, and autofocus of everyday objects with extremely low power consumption and computing power. This solves the problem of multi-object ranging and focusing parameter calculation in existing technologies, adapts to users' lens focal length needs in different scenarios, and realizes intelligent eye protection functions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUTH CHINA UNIV OF TECH
- Filing Date
- 2025-09-12
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to efficiently coordinate the visual information collected by algorithm models and hardware devices, making it difficult to achieve accurate distance measurement and focus parameter calculation for multiple objects. This restricts the fine scene perception of the vision system and the adaptive control of the optical system.
The system employs autofocus glasses based on YOLOv8n. Scene images are acquired through image acquisition devices, and object features are extracted after preprocessing. The ResNet-50 model is used for object classification, and the scene state is determined by combining indoor and outdoor feature object databases and neural network algorithms. The distance to the object at the focal point is calculated, and autofocus is achieved through hardware focusing control.
It enables the classification and detection of everyday objects with extremely low power consumption and computing power, quickly acquires environmental information, intelligently determines the objects that need to be focused, and adapts to the lens focal length needs of users in different scenarios to the greatest extent, thus achieving intelligent eye protection.
Smart Images
Figure CN121142759B_ABST