A novel target selection approach by incorporating image segmentation into P300-based Brain-Computer Interfaces

A P300-based Brain-Computer Interface (BCI) can achieve a target selection task by detecting only the human brain activities. In conventional P300-based BCIs, the row-column mode was widely used to modulate the stimulations of the targets. However, when extending the P300-based BCIs to practical applications, the regular stimulation mode is insufficient to reflect the complex target information in actual environments. To address this problem, we propose a novel target selection approach by incorporating the image segmentation method into the P300-based BCIs. In this approach, the image of the environment was captured by a camera, and partitioned using the Entropy Rate Super-pixel Segmentation (ERS) algorithm. Then, a random flash stimulation was embedded on each segment of the image to evoke the P300 signal. A two-step mechanism was used in our BCI system, where a group containing the target was selected first and then the target was selected from this group. To verify the performance of our approach, a target selection experiment was performed in different real environments. The average online accuracy in the experiment for five subjects was found to be 83.4% using our proposed approach. The results showed that the feasibility and practicality of the P300-based BCIs for target selection was improved by incorporating the image segmentation method.