Using Kinect for 2D and 3D Pointing Tasks: Performance Evaluation
Lecture notes in computer sciencePublished 1 January 2013
Alexandros Pino, Evangelos Tzemis, Nikolaos Ioannou, Γεώργιος Κουρουπέτρογλου
Citations51
SJR quartileQ2
SJR score0.35
SNIP0.55
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is shown that the Kinect, operated by the user's hand and voice, is a suitable and effective input method for pointing and clicking, especially in 3D tasks.
Abstract
We present a study to comparatively evaluate the performance of computer-based 2D and 3D pointing tasks. In our experiments, based on the ISO 9241-9 standard methodology, a Microsoft Kinect device and a mouse were used by seven participants. For the 3D experiments we introduced a novel experiment layout, supplementing the ISO. We examine the pointing devices' conformance to Fitts' law and we measure a number of extra parameters that describe more accurately the cursor movement trajectories. Throughput, measured in bits per second is the most important performance measure. For the 2D tasks using Microsoft Kinect, Throughput is almost 39% lower than using the mouse, Target Re-Entry is 10 times up and Missed Clicks count is almost 50% higher. However, for the 3D tasks the mouse has a 9% lower Throughput than the Kinect, while Target Re-Entry and Missed Clicks are almost identical. Our results are also compared to older studies, and we finally show that the Kinect, operated by the user's hand and voice, is a suitable and effective input method for pointing and clicking, especially in 3D tasks.
Keywords
Computer ScienceNeuroscience
Journal of Experimental Psychology GeneralThe information capacity of the human motor system in controlling the amplitude of movement.
6,321 Citations1992Paul M. Fitts
The experiments reported in the present paper extend the theory to the human motor system, including the visual and proprioceptive feedback loops that permit S to monitor his own activity and create an experimental situation in which it is reasonable to assume that performance is limited primarily by the capacity of the motor system.
International Journal of Human-Computer StudiesTowards a standard for pointing device evaluation, perspectives on 27 years of Fitts’ law research in HCI
1,030 Citations2004R. William Soukoreff, I. Scott MacKenzie
This paper makes seven recommendations to HCI researchers wishing to construct Fitts' law models for either movement time prediction, or for the comparison of conditions in an experiment that support the methods described in the recent ISO 9241-9 standard on the evaluation of pointing devices.
Efficient model-based 3D tracking of hand articulations using Kinect
874 Citations2011Iason Oikonomidis, Νikolaos Kyriazis +1 more
A novel solution to the problem of recovering and tracking the 3D position, orientation and full articulation of a human hand from markerless visual observations obtained by a Kinect sensor is presented.
Accuracy measures for evaluating computer pointing devices
431 Citations2001I. Scott MacKenzie, Tatu Kauppinen +1 more
Seven new accuracy measures to elicit (sometimes subtle) differences among devices in precision pointing tasks are proposed, which capture aspects of movement behaviour during a trial.
Personal and Ubiquitous ComputingAccelerometer-based gesture control for a design environment
293 Citations2005Juha Kela, Panu Korpipää +5 more
Gesture commands were found to be natural, especially for commands with spatial association in design environment control, and can augment other modalities.
Tracking the articulated motion of two strongly interacting hands
228 Citations2012Iason Oikonomidis, Νikolaos Kyriazis +1 more
The proposed method is the first to attempt and achieve the articulated motion tracking of two strongly interacting hands and employs Particle Swarm Optimization, an evolutionary, stochastic optimization method with the objective of finding the two-hands configuration that best explains observations provided by an RGB-D sensor.
Human Movement ScienceExtending Fitts' law to a three-dimensional pointing task
191 Citations2001Atsuo Murata, Hirokazu Iwase
An attempt was made to extend Fitt's' law to a three-dimensional movement (pointing) task to enhance its predictive performance in this domain and the extended model was shown to better fit the data than the conventional Fitts' model.
Cursor measures for motion-impaired computer users
81 Citations2002Simeon Keates, Faustina Hwang +3 more
This paper discusses work that aims to reveal the nature of people with motion-impairments' difficulties through analyses that consider the cursor's path of movement, and introduces new cursor characteristics for motion-impaired users.
Lawrence Erlbaum eBooksUniversal access in HCI : inclusive design in the information society
64 Citations2003Constantine Stephanidis
Universal Access and Design for All Assistive Technologies Mobile and Ubiquitious Interaction Adaptation and Personalization Access to Information User Diversity Accessibility and Usability Applications and Services Non-Visual Interaction Interaction Devices, Techniques and Modalities Design and Evaluation Tools.
Journal of Visual Languages & ComputingTactile feedback enhanced hand gesture interaction at large, high-resolution displays
29 Citations2009Stephanie Foehrenbach, Werner A. König +2 more
It is suggested that tactile feedback can interfere with other senses in a negative way, resulting in the observed higher error rate for horizontal targets, and more systematic research is needed to clarify the influencing factors on the usefulness of tactile feedback.
The $3 recognizer
22 Citations2010Sven Kratz, Michael Rohs
The $3 Gesture Recognizer is presented, a simple but robust gesture recognition system for input devices featuring 3D acceleration sensors that requires significantly less training data than other gesture recognizers and is thus suited to be deployed and to deliver results rapidly.
Lecture notes in computer scienceUsing Wiimote for 2D and 3D Pointing Tasks: Gesture Performance Evaluation
21 Citations2012Γεώργιος Κουρουπέτρογλου, Alexandros Pino +5 more
A novel configuration analogous to the ISO 9241-9 standard methodology is introduced and the pointing devices' conformance to Fitts' law is examined and eight extra parameters are measured that describe more accurately the cursor movement trajectory.
Lecture notes in computer scienceGesture and Sign Language in Human-Computer Interaction and Embodied Communication
17 Citations2012Eleni Efthimiou, Γεώργιος Κουρουπέτρογλου +1 more
This book constitutes revised selected papers from the 9th International Gesture Workshop, GW 2011, held in Athens, Greece, in May 2011, which were carefully reviewed and selected from 35 submissions.
Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIEPerformance evaluation of consumer-grade 3D sensors for static 6DOF pose estimation systems
2 Citations2012Jeremy A. Marvel, Marek Franaszek +2 more
This paper describes a framework for performance evaluation and measurement error analysis for 6 degrees of freedom pose estimation systems using traceable ground truth instruments, and focuses on artifact surface fitting and static pose analysis.