BELONG: Body Experienced Learning Support System
based on Gesture Recognition
Enhancing the Sense of Immersion in a Dinosaurian Environment
Mikihiro Tokuoka
1
, Haruya Tamaki
1
, Tsugunosuke Sakai
1
, Hiroshi Mizoguchi
1
, Ryohei Egusa
2,3
,
Shigenori Inagaki
3
, Mirei Kawabata
4
, Fusako Kusunoki
4
and Masanori Sugimoto
5
1
Department of Mechanical Engineering, Tokyo University of Science, 2641 Yamazaki, Noda-shi, Chiba-ken, Japan
2
JSPS Research Fellow, Tokyo, Japan
3
Graduate School of Human Development and Environment, Kobe University, Hyogo, Japan
4
Department of Computing, Tama Art University, Tokyo, Japan
5
Hokkaido University, Hokkaido, Japan
Keywords: Kinect V2 Sensor, Immersive, Learning Support System, Body Movements.
Abstract: As the first step toward realizing an immersive learning support system for museums, Yoshida et al. developed
and evaluated a prototype system. However, this system was problematic in that it could only be operated by
using simple body movements. Moreover, the other problem was that learning about paleontology itself
cannot be performed only by learning about a paleontological environment. Therefore, we developed an
immersive learning support system "BELONG" as an upgraded version of the above-mentioned system. Using
a recognizer capable of gesture recognition, the system can be operated using complicated body movements.
The improved system enables learners to enhance their sense of immersion in a paleontological environment
and learn about the fossil itself and its paleontology. This paper summarizes the prototype of "BELONG" and
describes the experiments that were performed to evaluate its ability to achieve learning support and
immersion.
1 INTRODUCTION
Museums are important places for children to learn
about science (Falk, J. H., 2012). They also operate
as centers for informal education in connection with
schools, and they enhance the effectiveness of
scientific education (Stocklmayer, S. M., 2010).
However, because the main learning method within
museums is the study of the specimens on display and
their explanations, there are few opportunities for
learners to observe or experience the environment
about which they are learning. In particular, it is
impossible to experience a paleontological
environment, which includes extinct animals and
plants, and their ecological environment (Adachi, T.,
2013). It is difficult for children to learn about such
environments merely by looking at fossils and
listening to commentary. Overcoming this problem
would qualitatively improve scientific learning
within museums. As for these problems, a system that
simulates a paleontological environment and
transitions that would be impossible to experience in
reality would solve the problem. The system would
also need to enhance learners’ sense of immersion.
Therefore, such a system is needed.
In order to enhance the sense of immersion, a full
body interaction interface in which the movement of
the whole body is linked to the operation of the
system was previously shown to be effective
(Klemmer S., 2006). Yoshida et al. also developed a
system targeting a full body interaction interface;
however, the system could only be operated using
simple body movements and this was problematic
(Yoshida, R., 2015). Moreover, learning about
paleontology itself cannot be performed only by
learning of a paleontological environment.
Therefore, we developed an immersive learning
support system "BELONG" as an upgraded version
of the original system by Yoshida et al. The upgraded
system solves the above problems. Compared with
the conventional learning support system, using a
recognizer capable of gesture recognition, the system
is operated using complicated body movements.
Tokuoka, M., Tamaki, H., Sakai, T., Mizoguchi, H., Egusa, R., Inagaki, S., Kawabata, M., Kusunoki, F. and Sugimoto, M.
BELONG: Body Experienced Learning Support System based on Gesture Recognition - Enhancing the Sense of Immersion in a Dinosaurian Environment.
DOI: 10.5220/0006357104870492
In Proceedings of the 9th International Conference on Computer Supported Education (CSEDU 2017) - Volume 1, pages 487-492
ISBN: 978-989-758-239-4
Copyright © 2017 by SCITEPRESS Science and Technology Publications, Lda. All rights reserved
487
Moreover, body movements are incorporated as part
of the observation behavior of a fossil exhibition,
which previously consisted of a conventional written
explanation. The system enables learners to enhance
their sense of immersion in a paleontological
environment and learn about the fossil itself and its
paleontology.
In this paper, we summarize the prototype of
"BELONG" as the first step toward developing the
immersive learning support system for the fossil
exhibition at the museum. In addition, we describe the
results of our experimental evaluation of the learning
support and immersion abilities of the system with the
aim of clarifying whether it can provide learners with
a realistic paleontological observation experience.
2 LEARNING SUPPORT SYSTEM
2.1 Belong
We aim to realize the immersive learning support
system "BELONG" that simulates a paleontological
environment and transitions that are impossible to
experience in reality for efficient learning at the
museum. Figure 1 illustrates the concept of
"BELONG." This system accepts body movements as
input for observational behavior. The movements of
the whole body and the system operation are linked;
therefore, it is possible to enhance the sense of
immersion in the paleontological environment. The
sense of immersion improves if the system can be
operated in conjunction with complicated body
movements as compared with a case in which the
system is operated with simple body movements. The
recognition of complicated body movements should
not involve attaching expensive sensors or devices to
learners when implementing it in a museum. In this
system, we utilize Microsoft’s Kinect v2 sensor, a
range-image sensor originally developed as a home
videogame device. Because BELONG comprises
only a Kinect v2 sensor, projector, and control PC, it
allows us to provide a low-cost immersive learning
experience within a small space. The advantage of
this arrangement is that it is possible to easily change
the learning contents. Moreover, we recognize the
body movements of learners by gesture recognition
using the Kinect v2 sensor. The gesture recognition
system, which can also interpret complicated body
movements, registers the body movement the creator
wishes to recognize and judges whether it is
recognized by verifying the similarity with the body
movement.
Figure 1: Concept of BELONG.
2.2 Configuration of the System
We developed an immersive learning support system
"BELONG" that simulates a paleontological
environment and transitions that are impossible to
experience in reality.
As a first step towards the
realization of this system, we are developing a system
to simulate paleoecology, especially learning about
dinosaurs, based on experiences that simulate a
paleontological excavation.
Our assumption was that
learners' interest would increase by virtually
excavating fossils included in the current exhibition.
However, because excavation motions are complex
body movements, gesture recognition was used.
(Tokuoka, M., 2017) When the excavation proceeds
successfully, videos showing the characteristics of the
dinosaur are displayed.
Linking the body and the
video in this way increases the sense of immersion.
These body movements are recognized by a Kinect v2
sensor, the properties of which are described below.
Microsoft’s Kinect v2 sensor is a range-image
sensor originally developed as a home videogame
device. Although it is inexpensive, the sensor can
record sophisticated measurements regarding the
user’s location. Additionally, this sensor can
recognize humans and the human skeleton using the
library in Kinect’s software development kit for
Windows. Kinect can measure the location of human
body parts such as hands and legs, and it can identify
the user’s pose or status with this function and the
location information. Moreover, Kinect Studio and
Visual Gesture Builder are used to recognize
complicated body movements captured by the Kinect
sensor. These enable complicated body movements to
be recognized using the discriminator (Tokuoka, M.,
2017). By using these, it is possible to create a
discriminator that registers the body movements we
want to recognize and can accurately recognize body
movements using machine learning. As a complicated
CSEDU 2017 - 9th International Conference on Computer Supported Education
488
body movement, this time we adopted the movements
associated with performing an excavation.
Figure 2 shows that this system consists of the
above Kinect V2 sensor, a control PC, and a projector.
As shown in Figure 3, the current system enables
children to learn about five dinosaurs, namely
Tyrannosaurs, Tambaryu, Archeoptery, Pteranodon,
and Ichthiosaurus. This system starts operation when
learners stand in front of the screen. First they select
the dinosaur fossil of which they want to learn by
using a pushing motion of the palm toward the screen.
After selection, learners excavate the corresponding
dinosaur fossil. We recognize the excavation
movement in this step using the Kinect v2 sensor.
When the excavation succeeds with the excavation
movement at full power, the video showing the
characteristics of dinosaurs is shown. This video
shows the habitat of the dinosaur in the Paleozoic era
and the size of the animal. Our evaluation aimed to
recognize whether complicated body movements
such as excavation are recognized by the
discriminator of the subsystem. (Tokuoka, M., 2017)
We determined that movements associated with
excavation are recognized when extensive and
accurate movements are made at full power. If
learners are shy and make a small movement, it is not
recognized as an excavation movement and fails.
Learners concentrate further by moving their bodies
towards the screen with enthusiasm, increasing the
sense of immersion in the paleontological
environment. In the museum, fossils are mere
sightings; however, they felt that the virtual
excavation enhanced their participation by
visualizing the virtual world.
After the excavation movement succeeds, you can
conduct separate learning for the five dinosaurs. This
is followed by an explanation of five contents. Figure
4 (a), (b), (c), (d), and (e) show the operation for each
of the contents.
Figure 2: Setup of the system.
Figure 3: Details of dinosaurs.
(a)Tyrannosaurs
Learners can answer quizzes about the tyrannosaurs
in this content by using a pushing motion of the palm
toward the screen. There are three quizzes. A
commentary video follows when learners answer
correctly. An incorrect answer allows learners to
make another selection. By learning about dinosaurs
in the form of quizzes, they can learn while having
fun.
(b)Tambaryu
Tambaryu moves sideways following learners’
movement to either the right or the left. Thus,
Tambaryu moves in response to their movement,
thereby increasing their sense of immersion in the
paleontological environment.
(c)Archeoptery
Learners can feed an Archeoptery by using the hand
action of gripping and opening. First, they can select
the bait of the Archeoptery displayed on the screen by
using a hand gripping action. They then move this
bait toward the mouth of the Archeoptery and open
their hands. Then, the Archeoptery eats the bait.
Therefore, they virtually experience feeding and they
know what the Archeoptery ate.
(d)Pteranodon
When learners wave their hands in a greatly animated
way a Pteranodon approaches.
A video of the
Pteranodon approaching is shown, and they seem to
be attacked by it. However, in the video the
Pteranodon does not have muscular strength as it
takes learners away. This enables them to learn about
the physical features of dinosaurs.
(e)Ichthiosaurus
When learners move forward and backward, they can
learn about the physical features of the Ichthiosaurus.
When they approach the screen, a video showing the
BELONG: Body Experienced Learning Support System based on Gesture Recognition - Enhancing the Sense of Immersion in a
Dinosaurian Environment
489
state of the stomach is shown. When they retreat from
the screen, the video shows the full appearance of the
body. Thus, their sense of distance changes in
conjunction with moving forward and backwards.
This enables them to learn about the size and shape of
the Ichthiosaurus.
As an observation behavior of paleontology, this
system can learn while experiencing contents
accompanying five kinds of different physical
behaviors using the above-mentioned technique of
gesture recognition.
By performing more complicated body
movements than would be possible with conventional
systems, we were able to develop a full-body
interactive interface that is more immersive. The use
of different actions for each dinosaur enables learners
to learn while having fun. Moreover, learners can
learn about five dinosaurs themselves and clearly
understand the difference between these dinosaurs.
(a)
(b)
(c)
(d)
(e)
Figure 4: Five contents.
3 EVALUATION
3.1 Methodology
Participants: Twenty-two fifth grade students (9 boys
and 13 girls) from elementary schools attached to the
national university corporation.
Location: H Prefectural Museum of Natural History
Topic: The participants each experienced the system
individually, after which they evaluated the system.
The evaluation method was used to obtain their
CSEDU 2017 - 9th International Conference on Computer Supported Education
490
feedback using a seven-point Likert scale
questionnaire on paper; the values on the Likert scale
correspond to “strongly agree,” “agree,” “somewhat
agree,” “neither agree nor disagree,” “somewhat
disagree,” “disagree,” and “strongly disagree,” from
seven to one, respectively. The questionnaire
structure was based on the
physical/emotional/narrative presence scale (PENS).
The questionnaire consisted of eight statements in
response to which the participants rated their
agreement: “When I was moving my body and
playing the game to learn about dinosaurs, I felt like I
was in a time or place different from my usual
environment,” “The details of the ancient time made
me feel like I was actually having an adventure in that
time,” “What happened within the system (creatures
and their movements) did not inspire me (reverse
score question),” “The system experience was
fascinating,” “I was able to experience the ancient
time just as deeply as the real world,” “During my
system experience, I felt as though I became part of
the time when dinosaurs lived,” “I felt very satisfied
with the system experience,” and “I felt that the
ancient scenery, creatures, and the way they lived on
the screen were very real.”
Test Date: 11/26/2016
3.2 Results
Responses for “strongly agree,” “agree,” and
“somewhat agree” were grouped as positive
responses; those for “neither agree nor disagree,”
“somewhat disagree,” “disagree,” and “strongly
disagree” were grouped as neutral/negative
responses. The number of positive and
neutral/negative responses was analyzed using
Fisher’s exact test with a 1 × 2 contingency table. The
responses for the reverse score question were
reversed.
Table 1 summarizes the system evaluations. The
positive responses exceeded neutral/negative
responses for all eight questions. Additionally, there
were significant differences at the 1% level between
the number of positive and neutral/negative responses
for seven of the statements: “When I was moving my
body and playing the game to learn about dinosaurs,
I felt like I was in a time or place different from my
usual environment,” “The details of the ancient time
made me feel like I was actually having an adventure
in that time,” “What happened within the system
(creatures and their movements) did not inspire me
(reverse score question),” “The system experience
was fascinating,” “I was able to experience the
ancient time just as deeply as the real world,” “I felt
very satisfied with the system experience,” and “I felt
that the ancient scenery, creatures, and the way they
lived on the screen were very real.”
Furthermore, there was a significant difference at
the 5% level between the number of positive and
Table 1: Subjective evaluation of the DINOU experience: physical/emotional/narrative presence.
7 6 5 4 3 2 1
1.
When I was moving my body and playing the game to learn
about dinosaurs, I felt like I was in a time or place different
from my usual environment
**
4 10 4 1 2 0 1
2.
The details of the ancient time made me feel like I was actually
having an adventure in that time
**
2 8 7 3 0 1 1
3.
What happened within the system (creatures and their
movements) did not inspire me (-)
**
1 1 1 5 2 7 5
4. The system experience was fascinating
**
11 4 5 1 0 0 1
5.
I was able to experience the ancient time just as deeply as the
real world
**
1 6 9 3 2 0 1
6.
During my system experience, I felt as though I became a part
of the time when dinosaurs lived
**
2 5 8 2 3 0 2
7. I felt very satisfied with the system experience
**
7 9 3 2 0 0 1
8.
I felt that the ancient scenery, creatures, and the way they lived
on the screen were very real
**
4 6 6 3 2 0 1
N = 22
**
p <.01,
*
p <.05 (-): Reverse score question
7 = Strongly agree; 6 = Agree; 5 = Somewhat agree; 4 = Neither agree nor disagree; 3 = Somewhat disagree;
2 = Disagree; 1 = Strongly disagree
BELONG: Body Experienced Learning Support System based on Gesture Recognition - Enhancing the Sense of Immersion in a
Dinosaurian Environment
491
neutral/negative responses for the statement: “During
my system experience, I felt as though I became a part
of the time when dinosaurs lived.”
4 CONCLUSIONS
In this paper, we proposed a prototype of "BELONG"
as the first step of the immersive learning support
system at the fossil exhibition at the museum. This
system comprises a full body interaction interface
using a Kinect v2 sensor as a gesture discriminator.
We used an experimental evaluation to assess the
extent to which the system supported learning and
immersion.
The results of the evaluation experiments revealed
that learners experienced reality, presence, and appeal
for paleoecology through experiencing this system
using complicated body movements. The results
showed that virtual observation behavior of
paleontology using the gesture recognition ability of
"BELONG" enabled learners to experience reality.
This indicates that "BELONG" is effective as a
method capable of providing a place of observation to
learn about aspects of paleontology such as dinosaurs
where a direct observational experience would be
impossible.
ACKNOWLEDGEMENTS
This work was supported in part by Grants-in-Aid for
Scientific Research (B). The evaluation was
supported by the Museum of Nature and Human
Activities, Hyogo, Japan.
REFERENCES
Falk, J. H., Dierking, L. D., 2012. Museum Experience
Revisited. Left Coast Press. Walnut Creek California,
USA, 2
nd
edition.
Stocklmayer, S. M., Rennie, L. J., Gilbert, J. K. 2010. The
roles of the provision of effective science education,
Studies in Science Education, 46(1), pp. 1-44,
Routledge Journals, Taylor & Francis Ltd.
Adachi, T., Goseki, M., Muratsu, K., Mizoguchi, H.,
Namatame, M., Sugimoto, M., Takeda, Y., Fusako, K.,
Estuji, Y., Shigenori, I., 2013. Human SUGOROKU:
Full-body interaction system for students to learn
vegetation succession. Proceedings of the 12th
International Conference on Interaction Design and
Children. pp. 364-367, ACM.
Klemmer S., Hartmann B., Takayama L., How bodies
matter: five themes for interaction design, DIS '06
Proceedings of the 6th conference on Designing
Interactive systems, pp. 140-149.
Yoshida, R., Egusa, R., Saito, M., Namatame, M.,
Sugimoto, M., Kusunoki, F., Etsuji, Y., Shigenori, I.,
Yoshiaki, T., Mizoguchi, H., 2015. BESIDE: Body
Experience and Sense of Immersion in Digital
Paleontological Environment. Proceedings of the 33rd
Annual ACM Conference Extended Abstracts on
Human Factors in Computing Systems. pp. 1283-1288.
ACM.
Tokuoka, M., Tamaki, H., Sakai, T., Mizoguchi, H., Egusa,
R., Inagaki, S., Kawabata, M., Kusunoki, F., Sugimoto,
M., 2017. Development of Gesture Recognition Sub-
system for BELONG. Proceedings of the 9th
International Conference on Computer Supported
Education, CSEDU 2017. To appeared.
CSEDU 2017 - 9th International Conference on Computer Supported Education
492