Cortically coupled computer vision with Emotiv headset using distractor variables

被引:0
|
作者
Ousterhout, Thomas [1 ]
Dyrholm, Mads [2 ]
机构
[1] Univ Copenhagen, Ctr Language Technol, Njalsgade 140, DK-2300 Copenhagen S, Denmark
[2] Univ Copenhagen, Dept Psychol, DK-1353 Copenhagen S, Denmark
关键词
D O I
暂无
中图分类号
TM [电工技术]; TN [电子技术、通信技术];
学科分类号
0808 ; 0809 ;
摘要
Visual search tasks can take long amounts of time and the more complicated the image is the longer it takes to find a target. Therefore, it is of interest to come up with a system that can augment a searcher's vision, in relation to speed, enabling the searcher to find the target faster than through normal means. Audition and vision are important for both communicative and informational purposes and therefore neurological signatures related to such abilities can greater increase cognitive infocommunicative devices. The P300 neurological response is a well known event-related potential that identifies the recognition of a target in such a search task. Clinical electroencephalogram (EEG) technology has previously been used to detect the P300 signature in response to target recognition during a Rapid Serial Visual Presentation (RSVP). Following the oddball paradigm, this study uses the 14-electrode Emotiv EPOC to detect the P300 in eight subjects performing a novel Where's Waldo target recognition task with the success criterion to optimize their completion time. In this paradigm, the number of targets and distractors are varied following a geometric distribution in order to have the participants engage in the task throughout the session. Although the Emotiv EPOC is crude in comparison to other EEG systems such as those with 256 electrodes, our results show better search times compared to baseline, and thus proves the feasibility of augmented vision even with such a limited system.
引用
收藏
页码:245 / 249
页数:5
相关论文
共 50 条
  • [41] Ultra Low Power Coupled Oscillator Arrays for Computer Vision Applications
    Shukla, N.
    Tsai, W. -Y
    Jerry, M.
    Barth, M.
    Narayanan, V.
    Datta, S.
    2016 IEEE SYMPOSIUM ON VLSI TECHNOLOGY, 2016,
  • [42] Tightly-Coupled LIDAR and Computer Vision Integration for Vehicle Detection
    Huang, Lili
    Barth, Matthew
    2009 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1 AND 2, 2009, : 604 - 609
  • [43] Probabilistic graphs using coupled random variables
    Nelson, Kenric P.
    Barbu, Madalina
    Scannell, Brian J.
    MACHINE INTELLIGENCE AND BIO-INSPIRED COMPUTATION: THEORY AND APPLICATIONS VIII, 2014, 9119
  • [44] Identification of Eye Blink Artifacts using Wireless EEG headset for Brain Computer Interface System
    Sridhar, S.
    Ramachandraiah, U.
    Sathish, E.
    Muthukumaran, G.
    Prasad, P. Rajendra
    2018 IEEE SENSORS, 2018, : 1678 - 1680
  • [45] Automated Human Vision Assessment using Computer Vision and Artificial Intelligence
    Van Eenwyk, Jonathan
    Agah, Arvin
    Cibis, Gerhard W.
    2008 IEEE INTERNATIONAL CONFERENCE ON SYSTEM OF SYSTEMS ENGINEERING (SOSE), 2008, : 317 - +
  • [46] Automated human vision assessment using computer vision and artificial intelligence
    Department of Electrical Engineering and Computer Science, University of Kansas, Lawrence, KS, United States
    不详
    IEEE Int. Conf. Syst. Syst. Eng., SoSE, 2008,
  • [47] Computer vision accelerated using photons and electrons
    Sweeney, Yann
    NATURE, 2023,
  • [48] Identification of tea varieties using computer vision
    School of Food and Biological Engineering, Jiangsu University, Zhenjiang, China
    不详
    Trans. ASABE, 2008, 2 (623-628):
  • [49] Violence Detection Using Computer Vision Approaches
    Talha, Khalid Raihan
    Bandapadya, Koushik
    Khan, Mohammad Monirujjaman
    2022 IEEE WORLD AI IOT CONGRESS (AIIOT), 2022, : 544 - 550
  • [50] Facial Emotion Recognition Using Computer Vision
    Jonathan
    Lim, Andreas Pangestu
    Paoline
    Kusuma, Gede Putra
    Zahra, Amalia
    2018 INDONESIAN ASSOCIATION FOR PATTERN RECOGNITION INTERNATIONAL CONFERENCE (INAPR), 2018, : 46 - 50