Gesture Recognition

Detailed Description

ChaLearn Looking at People

Implements loading dataset:

“ChaLearn Looking at People”: http://gesture.chalearn.org/

Usage

1. Follow instruction from site above, download files for dataset “Track 3: Gesture Recognition”: Train1.zip-Train5.zip, Validation1.zip-Validation3.zip (Register on site: www.codalab.org and accept the terms and conditions of competition: https://www.codalab.org/competitions/991#learn_the_details There are three mirrors for downloading dataset files. When I downloaded data only mirror: “Universitat Oberta de Catalunya” works).

2. Unpack train archives Train1.zip-Train5.zip to folder Train/, validation archives Validation1.zip-Validation3.zip to folder Validation/

3. Unpack all archives in Train/ & Validation/ in the folders with the same names, for example: Sample0001.zip to Sample0001/

4. To load data run:

Sheffield Kinect Gesture Dataset

Implements loading dataset:

“Sheffield Kinect Gesture Dataset”: http://lshao.staff.shef.ac.uk/data/SheffieldKinectGesture.htm

Usage:

1. From link above download dataset files: subject1_dep.7z-subject6_dep.7z, subject1_rgb.7z-subject6_rgb.7z.

2. Unpack them.

3. To load data run:

Classes

Name	Description
class cv::datasets::GR_chalearn	View details
struct cv::datasets::GR_chalearnObj	View details
class cv::datasets::GR_skig	View details
struct cv::datasets::GR_skigObj	View details
struct cv::datasets::groundTruth	View details
struct cv::datasets::join	View details
struct cv::datasets::skeleton	View details

Enumerations

enum cv::datasets::actionType {
    cv::datasets::circle = 1,
    cv::datasets::triangle,
    cv::datasets::updown,
    cv::datasets::rightleft,
    cv::datasets::wave,
    cv::datasets::z,
    cv::datasets::cross,
    cv::datasets::comehere,
    cv::datasets::turnaround,
    cv::datasets::pat
}

View details

enum cv::datasets::backgroundType {
    cv::datasets::woodenBoard = 1,
    cv::datasets::whitePaper,
    cv::datasets::paperWithCharacters
}

View details

enum cv::datasets::illuminationType {
    cv::datasets::light = 1,
    cv::datasets::dark
}

View details

enum cv::datasets::poseType {
    cv::datasets::fist = 1,
    cv::datasets::index,
    cv::datasets::flat
}

View details

Enumeration Type Documentation

actionType

enum cv::datasets::actionType

#include <opencv2/datasets/gr_skig.hpp>

Enumerator:

circle Python: cv.datasets.circle

triangle Python: cv.datasets.triangle

updown Python: cv.datasets.updown

rightleft Python: cv.datasets.rightleft

wave Python: cv.datasets.wave

z Python: cv.datasets.z

cross Python: cv.datasets.cross

comehere Python: cv.datasets.comehere

turnaround Python: cv.datasets.turnaround

pat Python: cv.datasets.pat

backgroundType

enum cv::datasets::backgroundType

#include <opencv2/datasets/gr_skig.hpp>

Enumerator:

woodenBoard Python: cv.datasets.woodenBoard

whitePaper Python: cv.datasets.whitePaper

paperWithCharacters Python: cv.datasets.paperWithCharacters

illuminationType

enum cv::datasets::illuminationType

#include <opencv2/datasets/gr_skig.hpp>

Enumerator:

light Python: cv.datasets.light

dark Python: cv.datasets.dark

poseType

enum cv::datasets::poseType

#include <opencv2/datasets/gr_skig.hpp>

Enumerator:

fist Python: cv.datasets.fist

index Python: cv.datasets.index

flat Python: cv.datasets.flat