计算机工程与应用 ›› 2018, Vol. 54 ›› Issue (23): 115-119.DOI: 10.3778/j.issn.1002-8331.1805-0066

• 模式识别与人工智能 • 上一篇    下一篇

目标视场角对P300-RSVP目标检测系统的影响分析

褚凯轩,常天庆,郭理彬,马  也   

  1. 陆军装甲兵学院 兵器与控制系,北京 100072
  • 出版日期:2018-12-01 发布日期:2018-11-30

Analysis of influence of target perspective on P300-RSVP target detection system

CHU Kaixuan, CHANG Tianqing, GUO Libin, MA Ye   

  1. Department of Weapon and Control, Army Academy of Armored Forces, Beijing 100072, China
  • Online:2018-12-01 Published:2018-11-30

摘要: 为了提高P300-RSVP目标检测系统的准确率,研究目标视场角对目标检测系统的影响。对5位被试者采用4种不同视场角的目标作为靶刺激进行实验;对被试者大脑产生的脑电波进行预处理,将目标图片对应的脑电信号进行50次叠加平均,发现目标所占视场角为8°左右时P300的峰值最高;采用结构化判别成分分析(HDCA)对单试次脑电信号进行分类,目标所占视场角为8°左右时的目标探测率平均达到82%以上,高于其他目标视场角对应的目标探测率。

关键词: 目标检测, 目标视场角, 结构化判别成分分析, 探测率

Abstract: In order to improve the accuracy of the P300-RSVP target detection system, the influence of the target perspective on the target detection system is studied. Five subjects are tested using four different angles of view as target stimuli. Brain waves generated by the subjects’ brains are preprocessed, and the EEG signals corresponding to the target images are averaged over 50 times. The peak value of P300 is highest when the target’s field of view angle is around 8°. Hierarchical Discriminant Component Analysis(HDCA) is used to classify single-trial EEG signals. When the target’s angle of view is about 8°, the target detection rate averages over 82%, which is higher than the target detection rate corresponding to the other target perspective.

Key words: target detection, target perspective, Hierarchical Discriminant Component Analysis(HDCA), detection rate