Abstract:

The traditional Steady-State Visual Evoked Potential（SSVEP） brain-computer interface system cannot interact with the real world, and the long time monotonous light flashing stimulation is easy to cause visual fatigue and affect the recognition accuracy. In order to enhance the interaction between humans and machines and the perception of the environment, this study designs a paradigm combining Augmented Reality（AR） and SSVEP to identify and track objects in the real environment, marking objects with flashing blocks, and processing EEG signals using the Filter Bank Canonical Correlation Analysis（FBCCA） method. The results show that the control signal transmission speed of the system reaches 50.69 bit/min, the recognition accuracy of FBCCA is 99.68%, and the intended targets can be distinguished within 1 s. Studies have shown that brain computer interface systems based on SSVEP and augmented reality are more suitable for complex real-world environments.

Key words: brain-computer interface, augmented reality, steady-state visual evoked potential

摘要：

传统的稳态视觉诱发电位（SSVEP）脑机接口系统无法与现实世界进行交互，长时间单调的光闪烁刺激容易导致视觉疲劳，影响识别精度。为了增强人与机器的交互以及对环境的感知，设计了增强现实（AR）和SSVEP结合的范式，在真实环境下对物体进行识别与追踪，并将闪烁块对物体进行标记，采用滤波器组典型相关分析（FBCCA）方法对脑电信号进行处理。结果表明，系统的控制信号传输速度达到50.69 bit/min，FBCCA的识别正确率为99.68%，能够在1 s内对4个目标中的意图目标进行有效区分。研究表明，基于SSVEP和增强现实的脑机接口系统更适合于复杂的现实环境。

关键词: 脑机接口, 增强现实, 稳态视觉诱发电位