GestureMidAirD2
收藏资源简介:
This dataset is part of the UCR Archive maintained by University of Southampton researchers. Please cite a relevant or the latest full archive release if you use the datasets. See http://www.timeseriesclassification.com/. Data contain 3D hand trajectories collected with Leap Motion device. There are 13 subjects, each performs 26 interface-command gestures. Each gesture is encoded as a sequence of 3D points, representing the position of the dominant-hand forefinger. There are 26 classes corresponding to unique gestures. See Fig. 1 of [2] for the list of gestures and their visualisation. - Class 1: arc3Dleft- Class 2: arc3Dright- Class 3: caret- Class 4: check- Class 5: circle- Class 6: curly-bracket-left- Class 7: curly-bracket-right- Class 8: delete- Class 9: left-swipe- Class 10: pigtail- Class 11: poly3Dxyz- Class 12: poly3Dxzy- Class 13: poly3Dyxz- Class 14: poly3Dyzx- Class 15: poly3Dzxy- Class 16: poly3Dzyx- Class 17: rectangle- Class 18: right-swipe- Class 19: spiral- Class 20: square-bracket-left- Class 21: square-bracket-right- Class 22: star- Class 23: triangle- Class 24: v- Class 25: x- Class 26: zig-zag We make three datasets out of these data, one for each dimension. We follow the original paper (see [2]) and use data of 8 subjects for training and 5 subjects for testing. Data of a same subjects does not appear in both train and test set, so resampling may introduce bias. Data created by Fabio M. Caputo et al. (see [1], [2]). Data edited by Hoang Anh Dau. [1] Github repo: https://github.com/giach68/gesturesCodes[2] Caputo, Fabio M., et al. Comparing 3D trajectories for simple mid-air gesture recognition. Computers & Graphics. 73 (2018): 17-25. Donator: H. A. Dau
本数据集隶属于南安普敦大学研究者维护的UCR档案库(UCR Archive)。若使用本数据集,请引用相关或最新的完整档案发布版本。详情请见http://www.timeseriesclassification.com/。 数据集包含通过Leap Motion设备采集的三维手部轨迹数据,共有13名受试者,每名受试者完成26种界面命令手势。 每种手势被编码为一系列三维点坐标,用以表征优势手食指的空间位置。本次数据集共设26个类别,对应26种独特手势,手势列表与可视化效果详见文献[2]中的图1。 - 类别1:3D左弧形(arc3Dleft) - 类别2:3D右弧形(arc3Dright) - 类别3:脱字符(caret) - 类别4:勾选标记(check) - 类别5:圆形(circle) - 类别6:左花括号(curly-bracket-left) - 类别7:右花括号(curly-bracket-right) - 类别8:删除(delete) - 类别9:左滑动(left-swipe) - 类别10:麻花形(pigtail) - 类别11:三维多路径xyz(poly3Dxyz) - 类别12:三维多路径xzy(poly3Dxzy) - 类别13:三维多路径yxz(poly3Dyxz) - 类别14:三维多路径yzx(poly3Dyzx) - 类别15:三维多路径zxy(poly3Dzxy) - 类别16:三维多路径zyx(poly3Dzyx) - 类别17:矩形(rectangle) - 类别18:右滑动(right-swipe) - 类别19:螺旋形(spiral) - 类别20:左方括号(square-bracket-left) - 类别21:右方括号(square-bracket-right) - 类别22:星形(star) - 类别23:三角形(triangle) - 类别24:V形(v) - 类别25:X形(x) - 类别26:之字形(zig-zag) 我们基于上述原始数据构建了三个子数据集,分别对应三维坐标的单个维度。本次划分遵循原始文献(详见[2])的设定:以8名受试者的数据作为训练集,剩余5名受试者的数据作为测试集。同一受试者的数据不会同时出现在训练集与测试集中,因此重采样操作可能引入偏差。 本数据集由Fabio M. Caputo等人创建(详见文献[1]、[2]),并经Hoang Anh Dau整理编辑。 [1] GitHub仓库:https://github.com/giach68/gesturesCodes [2] Caputo, Fabio M., 等. 面向简易空中手势识别的三维轨迹对比研究. 计算机与图形学, 73(2018): 17-25. 捐赠者:H. A. Dau



