3D hand posture recognition from small unlabeled point sets

Gardner, Alex; Duncan, Christian A.; Kanno, Jinko; Šelmić, Rastko R.

doi:10.1109/smc.2014.6973901

Cited by 12 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, motor disability (mobility disable) refers to a broadest category of disability with various causes. Common causes of motor disability are mainly paralysis, neurological disorders, repetitive stress injury, age related issues and lack of steadiness [7] [12] [13]. From game design perspective, motor disability or impairment is a game design problem which needs to be addressed.…”

Section: B Game Access For Motor Disabilitiesmentioning

confidence: 99%

“…For example, body part motion [3], head and mouth motions [5], eye tracking [6], and eye gaze [11] [10]. In related to these studies, various devices to facilitate access to motor disability have been developed in the last decade including: Setting button [5], Remap able key [6], Alternative Configuration [7], Camera Control [8], Moveable [9], Macro ability [10], Save Point [11], Click to Move [12], Input device [13], Speed [14] and Sensitivity [3]. The challenge, therefore, how to build a framework that unified various technologies as a guideline for game designer to develop games that fit the requirements of the users.…”

Section: Vickers Istance and Heronmentioning

confidence: 99%

“…Data for this study is a secondary data which has been used in a study reported by [12] [13]. The dataset for this study comprises of 74,975 samples that represents 5 classes of hand postures which were collected from 12 respondents that participated in the study.…”

Section: ) Datasetmentioning

confidence: 99%

See 2 more Smart Citations

Framework of Mobile Game Design as an Assistive Technology for Children with Motor Disabilities

Melyani

Heryadi²,

Trisetyarso³

et al. 2021

JGGAG

View full text Add to dashboard Cite

Computer games have emerged in the past decade as potential media beyond entertainment. Despite its popularity, game accessibility remains a major concern of various researchers. Children population with motor disabilities is a potential target for developing entertainment or therapeutic support games due to their interest to play. This paper presents: (1) a framework for mobile games for children with motor disability using simple hand postures and (2) Xgboost decision tree as a hand posture recognizer (98.48 percent training accuracy and 96.76 percent testing accuracy) as a prototype of hand posture-based commands as assistive technology to interact with games.

show abstract

Section: B Game Access For Motor Disabilitiesmentioning

confidence: 99%

Section: Vickers Istance and Heronmentioning

confidence: 99%

See 1 more Smart Citation

Framework of Mobile Game Design as an Assistive Technology for Children with Motor Disabilities

Melyani

Heryadi²,

Trisetyarso³

et al. 2021

JGGAG

View full text Add to dashboard Cite

show abstract

“…hand-postures: Five types of hand postures from 12 users were recorded using unlabeled markers attached to fingers of a glove in a motion capture environment (Gardner et al, 2014). Due to resolution and occlusion, missing values are common.…”

Section: Experiments On Uci Datasetsmentioning

confidence: 99%

Probability Calibration Trees

Leathart¹,

Frank²,

Holmes³

et al. 2018

Preprint

View full text Add to dashboard Cite

Obtaining accurate and well calibrated probability estimates from classifiers is useful in many applications, for example, when minimising the expected cost of classifications. Existing methods of calibrating probability estimates are applied globally, ignoring the potential for improvements by applying a more fine-grained model. We propose probability calibration trees, a modification of logistic model trees that identifies regions of the input space in which different probability calibration models are learned to improve performance. We compare probability calibration trees to two widely used calibration methods-isotonic regression and Platt scaling-and show that our method results in lower root mean squared error on average than both methods, for estimates produced by a variety of base learners.

show abstract

“…With respect to this, gesture interpretation represents an appealing, as well as valid, alternative to other more conventional contact-based or video-based modalities [7], [8]: In particular, the specialized literature reports on studies that refer to context-aware multimodal interfaces [9] based on video and audio inputs, static hand pose and dynamic hand gesture visual recognition [10], glove-based sensing [11], or marker-based motion capture systems [12]. These technologies have pioneered the research in the field but show some limitations for a seamless employment in a smart home: They require a dedicated and often expensive environment; they frequently need a complex setup that involves calibration procedures and may be strongly affected by environmental nuisances (e.g.…”

Section: Introductionmentioning

confidence: 99%

Home Automation Oriented Gesture Classification From Inertial Measurements

Cenedese

Susto

Belgioioso

et al. 2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

In this paper, a machine learning (ML) approach is presented that exploits accelerometers data to deal with gesture recognition (GR) problems. The proposed methodology aims at providing high accuracy classification for home automation systems, which are generally user independent, device independent, and device orientation independent, an heterogeneous scenario that has not been fully investigated in previous GR literature. The approach illustrated in this paper is composed of three main steps: event identification; feature extraction; and ML-based classification. The elements of the novelty of the proposed approach are 1) a preprocessing phase based on principal component analysis to increase the performance in real-world scenario conditions and 2) the development of parsimonious novel classification techniques based on sparse Bayesian learning. This methodology is tested on two datasets of four gesture classes (horizontal, vertical, circles, and eight-shaped movements) and on a further dataset with eight classes. In order to authentically describe a real-world home automation environment, the gesture movements are collected from more than 30 people who freely perform any gesture. It results in a dictionary of 12 and 20 different movements, respectively, in the case of the four-class and the eight-class databases

show abstract

3D hand posture recognition from small unlabeled point sets

Cited by 12 publications

References 23 publications

Framework of Mobile Game Design as an Assistive Technology for Children with Motor Disabilities

Framework of Mobile Game Design as an Assistive Technology for Children with Motor Disabilities

Probability Calibration Trees

Home Automation Oriented Gesture Classification From Inertial Measurements

Contact Info

Product

Resources

About