Sharing Cognition Between Human and Intelligence Machine

人类与智能机器共享认知

基本信息

  • 批准号:
    16J03504
  • 负责人:
  • 金额:
    $ 0.83万
  • 依托单位:
  • 依托单位国家:
    日本
  • 项目类别:
    Grant-in-Aid for JSPS Fellows
  • 财政年份:
    2016
  • 资助国家:
    日本
  • 起止时间:
    2016-04-22 至 2018-03-31
  • 项目状态:
    已结题

项目摘要

In this research, three topics are discussed to explain the detail of “See what I See” system as an interface for sharing human’s cognition. At first, a wearable Gaze Tracking (GT) was made to estimate gaze position in 2D coordinate space. Commercial GT is readily available, but they are usually fabricated at the same size. A three-dimensional (3-D)-printable frame and an open-source architecture was made to fabricate a wearable GT with low-cost configuration and reasonable performance. The output of this GT stays very steady at 75 cm or more with an accuracy of 2.58°. Three dimensions (3D) object detection was developed to make the system work in a real environment. The model uses Convolution Neural Network (CNN) on four channels formed using RGBD information (splitting into R, G, B, Depth in separate channels). The evaluation results show that the combination of RGB and depth improve the accuracy of object recognition. Gaze tracking is the important tool for “see what I see” system to identify the 3D object of the person’s attention in the visual world coordinate. The wearable GT requires calibration of scene geometry and camera to make it applicable in visual world coordinates. The result of this approach reports that the gaze estimation error is 5 degrees.
在本研究中,三个主题进行了讨论,以解释“看到我所看到的”系统作为共享人类认知的接口的细节。首先,可穿戴式视线跟踪(GT)估计视线位置在二维坐标空间。商业燃气轮机是现成的,但他们通常是在相同的尺寸制造。为了实现低成本、性能合理的可穿戴GT,设计了一种可三维打印的框架和开源架构。这款GT的输出在75 cm或更高时保持非常稳定,精度为2.58°。三维(3D)目标检测的发展,使系统工作在一个真实的环境。该模型在使用RGBD信息形成的四个通道上使用卷积神经网络(CNN)(在单独的通道中分成R、G、B、深度)。评价结果表明,RGB和深度的结合提高了目标识别的准确性。视线跟踪是“看我所见”系统在视觉世界坐标系中识别人的注意力所关注的三维物体的重要工具。可穿戴GT需要场景几何和相机的校准,使其适用于视觉世界坐标。该方法的结果报告注视估计误差为5度。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Three Dimensional Object Classifications withMultichannel Convolution Neural Network
多通道卷积神经网络的三维物体分类
Gaze Tracking in 3D Space with Convolution Neural Network
使用卷积神经网络在 3D 空间中进行注视跟踪
RGB-D Object Classification with Deep Convolution Neural Network
使用深度卷积神经网络进行 RGB-D 对象分类
  • DOI:
  • 发表时间:
    2017
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Adiba;Amalia I
  • 通讯作者:
    Amalia I
An Adjustable Gaze Tracking System and Its Application for Automatic Discrimination of Interest Objects
  • DOI:
    10.1109/tmech.2015.2470522
  • 发表时间:
    2016-04
  • 期刊:
  • 影响因子:
    0
  • 作者:
    A. Adiba;Nobuyuki Tanaka;Jun Miyake
  • 通讯作者:
    A. Adiba;Nobuyuki Tanaka;Jun Miyake
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

AMALIA ISTIQLALI ADIBA其他文献

AMALIA ISTIQLALI ADIBA的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

相似海外基金

Website design by the use of gaze tracking
利用视线追踪进行网站设计
  • 批准号:
    17K00392
  • 财政年份:
    2017
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Research on construction of computer-aided interpretation system using a gaze-tracking measurement in mammogram
乳房X光检查中利用视线跟踪测量的计算机辅助判读系统的构建研究
  • 批准号:
    16K19237
  • 财政年份:
    2016
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Grant-in-Aid for Young Scientists (B)
An Examination of Attentional Disengagement from Emotional Images in Currently and Previously Depressed Individuals Using Eye Gaze Tracking
使用视线追踪检查当前和以前抑郁症患者的注意力从情绪图像中脱离的情况
  • 批准号:
    349949
  • 财政年份:
    2015
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Studentship Programs
Using Eye Gaze Tracking to Study Attention to Emotional Images
使用眼睛注视跟踪来研究对情感图像的注意力
  • 批准号:
    480995-2015
  • 财政年份:
    2015
  • 资助金额:
    $ 0.83万
  • 项目类别:
    University Undergraduate Student Research Awards
Innovation Voucher: Gaze Tracking
创新券:视线追踪
  • 批准号:
    752844
  • 财政年份:
    2015
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Vouchers
Using Eye Gaze Tracking to Study Attention to Emotional Images
使用眼睛注视跟踪来研究对情感图像的注意力
  • 批准号:
    467135-2014
  • 财政年份:
    2014
  • 资助金额:
    $ 0.83万
  • 项目类别:
    University Undergraduate Student Research Awards
Using Eye Gaze Tracking to study Attentional Biases in Individuals with a History of Depression
使用视线追踪研究有抑郁症病史的人的注意力偏差
  • 批准号:
    199717
  • 财政年份:
    2010
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Studentship Programs
Gaze Tracking Haptic User Interface for the Blind
盲人视线追踪触觉用户界面
  • 批准号:
    DP0881180
  • 财政年份:
    2008
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Discovery Projects
Gaze tracking based on spatiotemporal integration of classifiers and recognition of relationship between people
基于分类器时空整合的视线跟踪和人与人之间关系的识别
  • 批准号:
    20700152
  • 财政年份:
    2008
  • 资助金额:
    $ 0.83万
  • 项目类别:
    Grant-in-Aid for Young Scientists (B)
Eye-Gaze tracking of normal listeners to alaryngeal speech
正常听众对喉部言语的眼睛注视跟踪
  • 批准号:
    7293606
  • 财政年份:
    2006
  • 资助金额:
    $ 0.83万
  • 项目类别:
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了