一种基于脑电源定位的视觉信息解码方法
By using brain power localization technology and visual coding models, the problem of insufficient spatial resolution in EEG data decoding has been solved, achieving high-precision visual information decoding and accurately reconstructing the user's visual content.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHANGHAI SHULI INTELLIGENT TECH CO LTD
- Filing Date
- 2025-07-07
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies, when decoding visual information based on EEG data, the spatial resolution is limited, making it difficult to accurately locate various features of visual information processing, resulting in poor decoding performance.
By acquiring the target user's EEG data and combining it with EEG power estimation techniques and a visual coding model, the source estimation data of the visual brain region is determined, enabling the decoding of the image content observed by the user. This method involves constructing a forward model and a backward decoding model to convert EEG data into neural source activity in the source space, improving spatial resolution, and decoding based on the mapping relationship between different levels of visual cortical neural activity patterns and visual stimulus features.
While preserving the temporal resolution of EEG data, high spatial precision visual information decoding was achieved, enabling the inference and reconstruction of visual content observed by the user, thus improving the accuracy and efficiency of visual information decoding.
Smart Images
Figure CN120765767B_ABST