WhoLoDancE: Towards a methodology for selecting Motion Capture Data across different Dance Learning Practice

Conference Paper (PDF Available) · July 2016with 78 Reads
DOI: 10.1145/2948910.2948912
Conference: the 3rd International Symposium
Abstract
In this paper we present the objectives and preliminary work of WhoLoDancE a Research and Innovation Action funded under the European Union's Horizon 2020 programme, aiming at using new technologies for capturing and analyzing dance movement to facilitate whole-body interaction learning experiences for a variety of dance genres. Dance is a diverse and heterogeneous practice and WhoLoDancE will develop a protocol for the creation and/or selection of dance sequences drawn from different dance styles for different teaching and learning modalities. As dance learning practice lacks standardization beyond dance genres and specific schools and techniques, one of the first project challenges is to bring together a variety of dance genres and teaching practices and work towards a methodology for selecting the appropriate shots for motion capturing, to acquire kinetic material which will provide a satisfying proof of concept for Learning scenarios of particular genres. The four use cases we are investigating are 1) classical ballet, 2) contemporary dance, 3) flamenco and 4) Greek folk dance.
WhoLoDancE: Towards a methodology for selecting
Motion Capture Data across different Dance Learning
Practices
WhoLoDancE partnersi
ABSTRACT
In this paper we present the objectives and preliminary work
of WhoLoDancE a Research and Innovation Action funded
under the European Union’s Horizon 2020 programme,
aiming at using new technologies for capturing and
analyzing dance movement to facilitate whole-body
interaction learning experiences for a variety of dance
genres. Dance is a diverse and heterogeneous practice and
WhoLoDancE will develop a protocol for the creation and/or
selection of dance sequences drawn from different dance
styles for different teaching and learning modalities. As
dance learning practice lacks standardization beyond dance
genres and specific schools and techniques, one of the first
project challenges is to bring together a variety of dance
genres and teaching practices and work towards a
methodology for selecting the appropriate shots for motion
capturing, to acquire kinetic material which will provide a
satisfying proof of concept for Learning scenarios of
particular genres. The four use cases we are investigating are
1) classical ballet, 2) contemporary dance, 3) flamenco and
4) Greek folk dance.
Author Keywords
Dance Learning; Motion Capture; Human Movement;
Whole-Body interaction; Dance practices and genres.
ACM Classification Keywords
H.5.5. Information interfaces and presentation (e.g., HCI):
Sound and Music Computing—Systems. J.5. Arts and
Humanities: Performing arts (e.g. dance, music).
INTRODUCTION
WhoLoDancE is a three years (January 2016-December
2018) Research and Innovation Action, under the framework
of ICT2015 of H2020 aiming at designing and developing
whole body interaction tools to support dance learning.
DANCE LEARNING PRACTICES
Dance education is mainly an example of “learning by
doing” and the development of embodied knowledge,
whereas technological tools can support the analytical and
conceptualization abilities of dance students, and
choreographers. Currently there is not one single repository
of these teaching methods, neither is there a repository of
dance actions that would support the development of the
teaching of dance. Learning based on ICT (Information and
Communication Technologies), and whole-body-interaction
in particular, can largely benefit from the outcomes of
applying it in the field of dance, as dancers are experts in
embodied communication and dance is by its nature
multimodal. WhoLoDancE data-driven tools will be
provided with a measurement of human-system interaction
fostering non-linear approaches to adaptive learning and
cognitive artifacts for effective human learning. Dance is
traditionally a practice that is passed from body to body, and
whilst there are established and codified dance ‘techniques’
that are genre specific these techniques evolve through the
teaching itself. Some techniques are therefore more
prescriptive than others, and those that are more prescriptive
tend to be guarded by a named innovator or the developer of
the technique. But aside from the specifics of these
techniques, there are teaching methods that connect all studio
based teaching of dance and whilst these methods are
moderated according to context (whether within a
professional/vocational teaching context, or a recreational
context, etc.) and according to genre, there are underlying
principles that pertain to all good teaching of dance. The
WhoLoDancE multimodal repository will enable the usage
of data analytics supporting the identification of effective
teaching methods and practices showing commonalities and
differences between them to support the future teaching of
dance within a variety of contexts.
DANCE LEARNING PRINCIPLES
As the aforementioned dance genres provide a huge diversity
in both the kinetic vocabularies and the teaching
methodologies, one of the big challenges is to find learning
objectives that are common across genres. We aim for a
systematic way of selecting shots beyond the differences of
the kinetic material. A focus group, with the participation of
dance teachers of all genres, agreed that the following
Learning Principles summarize the different teaching styles
applied in different practices:
1. Mimesis: imitation/copying: the teacher is teaching the
student a specific movement or sequence of movements
and the student follows the movement. This is a case
where the learning is largely based on observational
abilities of the students as they are asked to see and do;
2. Generative: the teacher gives the student an
exercise/phrase/sequence as a starting point to achieve
technical and creative goals. In this case the student is
allowed to generate new kinetic material, or alter things
as long as he or she is consistent with the technical or
creative goals;
3. Reflexive: the student is given a movement
task/image/to work with, improvising without trying to
achieve a specific phrase/sequence and the teacher
provides feedback. In this case the memorization ability
of the student is challenged, as in contrary to the mimetic
approach the student has to remember the sequence,
rather than see and do, and at the same time is allowed
to alter or generate new material, as in the generative
approach;
4. Traditional also known as “command style teaching”:
where the teacher makes all the decisions and the learner
follows, while the teacher “commands” what the student
must correct or change to achieve the good performance
of the movement. The method requires precision and
accuracy of performance.
MOVEMENT PRINCIPLES
The aim of the WhoLoDancE is to develop learning tools that
will be designed upon the principles of contemporary models
of dance learning and teaching. The research will focus not
only on teaching steps by mimicking, but also on enhancing
the student’s movement literacy, increasing the learners’
ability to analyze her/his own movement, and enhancing
movement skills that will feed into the development of the
student’s creativity, musicality and broader dance
experience.
Following the approach of the interdisciplinary focus group,
we proposed ten essential Movement Principles that can
summarize the embodied skills which are to be improved in
each dance learning process, independent of the dance genre
and style. From our preliminary investigations, we defined a
first list of movement principles
1. Symmetry: The use of the two sides of the body (right
vs. left side, arm, leg) etc., both in position and while
moving. The ability to do the same thing simultaneously
or sequentially using both sides. Each Movement
Principle includes also the opposite. Playing with
asymmetry and isometry is included in this principle.
2. Directionality: The awareness of body orientation in
space. Usually this is derived from the position of hips
and torso, but interesting postures might derive from the
various directions of each body part in relation to a
space, e.g., the audience, the camera, the studio.
i
Antonio Camurri (University of Genova), Katerina El
Raheb (Athena RC), Oshri Even-Zohar (Motek), Yannis
Ioannidis (Athena RC), Amalia Markatzi (Lykeion
Ellinidon), Jean-Marc Matos (K.Danse), Edwin Morley-
3. Balance: The ability to stand and move in balance, but
also out of balance, depending on whether the line of
gravity falls within the line of your supporting limb(s)
or not. The awareness of the different vector forces on
your body.
4. Alignment – Posture Stability: The awareness of the
geometry of the body (e.g., the axes (sagittal, horizontal,
vertical) and planes, and how the relations of different
body parts and joint create “lines” in the body shape.
5. Weight bearing vs. Gesturing: This principle is about the
difference between movement that is concerned with
bearing weight (weight transference, stepping.) and
movement (gesture) that is not bearing weight but which
has intention/expression
6. Gross vs. Fine Motorics/Isolation/Articulation: The
ability to distinguish small movements done by specific
body parts e.g., hand or one hip, or one shoulder, without
moving the rest of the body, vs. moving larger parts of
the body as a whole.
7. Coordination: One of the most important skills practiced
in every kind of dancing, which is about the ability to
synchronize or not different parts of the body that can
move in the same or separate tempos.
8. Motion through Space: Progressing through space or
towards particular directions, paths etc. "Moving
through space vs. dancing on the spot. Also the body as
moving point in space, or as continuously changing
moving volume.
9. Rhythm and phrasing. The ability to move in particular
(predefined or improvised) rhythms. This principle is
also about how the dancer’s movement is related or not
to the music and its rhythmical aspects (tempo, time
signature, rhythmic patterns etc.).
10. Stillness. While movement seems to be the essence of
dance, a dancer needs to improve her/his ability to
remain still, whether this is a part of a choreography or
interpretation of rhythmical pauses, and exercise for
balance and isolation of body parts. Stillness is usually
connected to the notion of being present and has been
investigated in previous interdisciplinary work.
Fletcher (Lynkeus), Pablo Palacio (STOCOS), Muriel
Romero (STOCOS), Augusto Sarti (Politecnico di Milano),
Stefano Di Pietro (Lynkeus), Vladimir Viro (PeachNote),
Sarah Whatley (Coventry University).
MOCO16_WhoLoDancE_Final_Accepted.pdf
81.36 KB
  • Conference Paper
    Full-text available
    Recent advances in technologies for capturing, analyzing and visualizing movement can revolutionize the way we create, practice, learn dance, and transmit bodily knowledge. The need for creating meaningful, searchable and re-usable libraries of motion capture and video movement segments can only be fulfilled through the collaboration of both technologists and dance practitioners. Towards this direction, manual annotations of these segments by dance experts can play a four-fold role: a) enrich movement libraries with expert knowledge, b) create "ground-truth" datasets for comparing the results of automated algorithms, c) fertilize a dialogue across dance genres and disciplines on movement analysis and conceptualization, and d) raise questions on the subjectivity and diversity of characterizing movement segments using verbal descriptions. The web-based application presented in this work, is an archival system with, browsing, searching, visualization, personalization and textual annotation functionalities. Its main objective is to provide access to a repository of multimodal dance recordings including motion capture data, video, and audio, with the aim to also support dance education. The tool has been designed and developed within an interdisciplinary project, following a user-centered, iterative design approach involving dance researchers and practitioners of four different dance genres.
  • Conference Paper
    Full-text available
    Rhythm is the most basic skill for people learning to dance. Beginners need practice but also close coaching and constant feedback. However, in most dance classes teachers often find challenging to provide attention to each student. A possible solution to this problem would be to automate the provision of feedback to students by objectively assessing rhythm from their movement data. But how effective would a fully automated approach be compared to dance experts in evaluating dance performance? We conducted a study aimed at exploring this by 'measuring' dance rhythm from accelerometer data streams and contrasting the algorithm results with expert human judgement. We developed RiMoDe, an algorithm that tracks bodily rhythmic skills, and gathered a dataset that includes 282 independent evaluations made by expert dance teachers on 94 dance exercises performed by 7 dance students. Our findings revealed major gaps between a purely algorithmic approach and how experts evaluate dance rhythm. We identified 6 themes that are important when assessing rhythm. We discuss how these themes should be considered and incorporated into future systems aimed at supporting people learning to dance.
  • Conference Paper
    In this paper, we present (i) a computational model of Dynamic Symmetry of human movement, and (ii) a system to teach this movement quality (symmetry or asymmetry) by means of an interactive sonification exergame based on IMU sensors and the EyesWeb XMI software platform. The implemented system is available as a demo at the workshop.
  • Chapter
    In this paper we describe the Virtual Reality Annotator, a visualization tool that allows users to dynamically annotate dancers in a virtual reality environment. The current annotation types supported are sketches, speech-to-text, and highlighting. Each type of annotation can be applied to a bone or a set of bones of the skeleton data or a set of points of the point-cloud data. Using a wireless mouse, users can interact with the 3D objects of the virtual reality space, specifically a 3D menu that allows to choose the type of annotation and desired color as well as the skeleton and point cloud data. Examples of usage of this system using data from expert dancers are presented and discussed as well as suggestions for future work.
  • Oshri Even-Zohar (Motek) Yannis Ioannidis
    • Antonio Camurriathena
    • Amalia Markatzi
    i Antonio Camurri (University of Genova), Katerina El Raheb (Athena RC), Oshri Even-Zohar (Motek), Yannis Ioannidis (Athena RC), Amalia Markatzi (Lykeion Ellinidon), Jean-Marc Matos (K.Danse), Edwin Morley- Fletcher (Lynkeus), Pablo Palacio (STOCOS), Muriel Romero (STOCOS), Augusto Sarti (Politecnico di Milano),