AR.data

A dataset containing the skeleton data extracted from videos of people performing
six different actions, recorded by a humanoid robot. Each class has several instances with
50 values (25 XY body keypoints extracted using OpenPose <a href="https://github.com/CMU-Perceptual-Computing-Lab/openpose">https://github.com/CMU-Perceptual-Computing-Lab/openpose</a>)
per frame of the video (92 frames).

datasets

A way to apply Distance-Based Common Spatial Patterns
(DB-CSP) techniques in different fields, both classical Common Spatial
Patterns (CSP) as well as DB-CSP. The method is composed of two
phases: applying the DB-CSP algorithm and performing a classification.
The main idea behind the CSP is to use a linear transform to project
data into low-dimensional subspace with a projection matrix, in such a
way that each row consists of weights for signals. This transformation
maximizes the variance of two-class signal matrices.The dbcsp object
is created to compute the projection vectors. For exploratory and
descriptive purpose, plot and boxplot functions can be used. Functions
train, predict and selectQ are implemented for the classification
step.

Itsaso Rodr<c3><ad>guez-Moreno

dbcsp

Distance-Based Common Spatial Patterns

Itziar Irigoien

Concepción Arenas

Itsaso Rodríguez-Moreno

AR.data function

A list of 6 different actions:<dl>
<dt>come</dt>
<dd>Gesture for telling the robot to come to you. 46 instances of [50x92] matrices.</dd><dt>five</dt>
<dd>Gesture of 'high five'. 45 instances of [50x92] matrices.</dd><dt>handshake</dt>
<dd>Gesture of handshaking with the robot. 45 instances of [50x92] matrices.</dd><dt>hello</dt>
<dd>Gesture for telling hello to the robot. 44 instances of [50x92] matrices.</dd><dt>ignore</dt>
<dd>Ignore the robot, pass by. 46 instances of [50x92] matrices.</dd><dt>look_at</dt>
<dd>Stare at the robot in front of it. 46 instances of [50x92] matrices.</dd>
</dl>

Format

A dataset containing the skeleton data extracted from videos of people performing
six different actions, recorded by a humanoid robot. Each class has several instances with
50 values (25 XY body keypoints extracted using OpenPose <a href='https://github.com/CMU-Perceptual-Computing-Lab/openpose'>https://github.com/CMU-Perceptual-Computing-Lab/openpose</a>)
per frame of the video (92 frames).

Skeleton data for 6 different actions. — AR.data

A list of 6 different actions:<dl>
<dt>come</dt>
<dd>Gesture for telling the robot to come to you. 46 instances of [50x92] matrices.</dd>

<dt>five</dt>
<dd>Gesture of 'high five'. 45 instances of [50x92] matrices.</dd>

<dt>handshake</dt>
<dd>Gesture of handshaking with the robot. 45 instances of [50x92] matrices.</dd>

<dt>hello</dt>
<dd>Gesture for telling hello to the robot. 44 instances of [50x92] matrices.</dd>

<dt>ignore</dt>
<dd>Ignore the robot, pass by. 46 instances of [50x92] matrices.</dd>

<dt>look_at</dt>
<dd>Stare at the robot in front of it. 46 instances of [50x92] matrices.</dd>


</dl>

AR.data: Skeleton data for 6 different actions.

Description

Usage

Arguments

Format

Examples