Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Chef*mo: 動画が調理器具を制御して調理を支援するシステムの提案 / Chefmo
Search
Tsubasa Yumura
December 23, 2017
Research
1
1.4k
Chef*mo: 動画が調理器具を制御して調理を支援するシステムの提案 / Chefmo
2017年12月23日(土)にグランフロント大阪で開催されたEC46の発表資料。論文はこちら →
https://goo.gl/6oJHh4
Tsubasa Yumura
December 23, 2017
Tweet
Share
More Decks by Tsubasa Yumura
See All by Tsubasa Yumura
Human-Computer Interaction (HCI) 入門 #北海道LT大会 / HCI2023
yumu19
0
170
Tinkercadの電子回路シミュレータはいいぞ #北海道まったりLT大会 / Tinkercad
yumu19
1
3.1k
メイカーズ文化とシチズンサイエンス #JOSS2021 / Makers Culture and Citizen Science
yumu19
0
610
バーチャルSNS clusterを用いたイベント開催 / Event Organization with Virtual SNS “cluster”
yumu19
0
130
石川での6年間 / 6 years in Ishikawa
yumu19
0
290
NT札幌2020 in cluster 開催報告 #XRMTG / NT Sapporo 2020 in cluster
yumu19
0
89
Space Apps Challenge Tokyo 2020 開会式
yumu19
0
94
社会人博士のススメ
yumu19
2
7.4k
SpaceApps COVID-19 Challenge開会式
yumu19
0
140
Other Decks in Research
See All in Research
Whoisの闇
hirachan
3
280
EBPMにおける生成AI活用について
daimoriwaki
0
280
ラムダ計算の拡張に基づく 音楽プログラミング言語mimium とそのVMの実装
tomoyanonymous
0
400
ベイズ的方法に基づく統計的因果推論の基礎
holyshun
0
800
Weekly AI Agents News! 11月号 プロダクト/ニュースのアーカイブ
masatoto
0
290
リモートワークにおけるパッシブ疲労
matsumoto_r
PRO
6
4.9k
Prithvi-EO-2.0: A Versatile Multi-Temporal Foundation Model for Earth Observation Applications
satai
2
150
Segment Any Change
satai
2
210
Weekly AI Agents News! 12月号 プロダクト/ニュースのアーカイブ
masatoto
0
320
Leveraging LLMs for Unsupervised Dense Retriever Ranking (SIGIR 2024)
kampersanda
2
300
文化が形作る音楽推薦の消費と、その逆
kuri8ive
0
240
A Segment Anything Model based weakly supervised learning method for crop mapping using Sentinel-2 time series images
satai
2
130
Featured
See All Featured
Building Flexible Design Systems
yeseniaperezcruz
328
38k
Raft: Consensus for Rubyists
vanstee
137
6.8k
A Philosophy of Restraint
colly
203
16k
Code Reviewing Like a Champion
maltzj
521
39k
Making the Leap to Tech Lead
cromwellryan
133
9.1k
Fireside Chat
paigeccino
34
3.2k
YesSQL, Process and Tooling at Scale
rocio
172
14k
Testing 201, or: Great Expectations
jmmastey
42
7.2k
Building Better People: How to give real-time feedback that sticks.
wjessup
367
19k
Building Your Own Lightsaber
phodgson
104
6.2k
Producing Creativity
orderedlist
PRO
344
39k
Designing Experiences People Love
moore
140
23k
Transcript
Chef mo * ౬ଜ ཌྷ†, ݹؘ ༎ࢠ†, দຊ ՚า‡, ᖒ
ͻ͞Έ†, ܀ݪ Ұو‡ɹ ಈը͕ௐཧث۩Λ੍ޚͯ͠ௐཧΛࢧԉ͢ΔγεςϜͷఏҊ † Chefˎmo ϓϩδΣΫτ ‡ ాक़େֶ ใॲཧֶձ ୈ46ճΤϯλςΠϯϝϯτίϯϐϡʔςΟϯάˏάϥϯϑϩϯτେࡕ
Chef mo * Chefˎmo 2
Chef mo * ຊൃදͷ֓ཁ • ྉཧಈըʹௐཧεΫϦϓτΛຒΊࠐΈɺಈըͷ༰ʹ ߹Θͤͯௐཧث۩Λ੍ޚͯ͠ௐཧࢧԉΛߦ͏γεςϜ ΛఏҊ • ίϯηϓτ࣮Λߦͬͨ
• ಈըͱIoTػثͷ࿈ܞϑϨʔϜϫʔΫsrt.jsΛ༻͍ͨ • ʮ͔͚ΔʯʮࠞͥΔʯʮΔʯͷ3छྨͷௐཧߦಈΛ ࣮ͨ͠ • ٞͱ՝Λ·ͱΊͨ 3
Chef mo * ͡Ίʹ • ྉཧಈը • Ωϡʔϐʔ3ΫοΩϯάʢ1962ʙʣ • 1ྉཧಈըʢKurashiruͳͲʣ
4 [2]kurashiru http://www.kurashiru.com/ ޘָ ࢹௌΛָ͠Ή ެ։Λָ͠Ή ޘָ ࣮ӹ ྉཧʹؔ͢Δ ใΛಘΔ ࣮ӹ ྉཧಈըΛͳͥ؍Δ͔ʁ
Chef mo * ͡Ίʹ • ػցʹΑΔௐཧࢧԉٕज़ͱΈ߹ΘͤΔ͜ͱʹΑΓɺ ྉཧಈըͷࢹௌΛΑΓΑ͍ͷʹঢ՚Ͱ͖ΔͷͰͳ ͍͔ʁ 5 [4]Moley
[6]Cooky
Chef mo * ͡Ίʹ 6 ྉཧಈըͷ ݩͷׂ ௐཧࢧԉ ྟײ ָ͠͞
Chef mo * ಈը͕ௐཧث۩Λ੍ޚͯ͠ௐཧΛࢧԉ͢ΔγεςϜ ޘָ ࢹௌΛָ͠Ή ެ։Λָ͠Ή ޘָ ࣮ӹ ྉཧʹؔ͢Δ ใΛಘΔ ࣮ӹ Chefˎmo Ͱ֦ு
Chef mo * ؔ࿈ݚڀ | ػցʹΑΔௐཧࢧԉ 7 [4]Moley – The
world's first robotic kitchen http://www.moley.com/
Chef mo * ؔ࿈ݚڀ | ػցʹΑΔௐཧࢧԉ 8 [6]Sugiura et al.,
Cooking with robots: designing a household system working in open environments (2010)
Chef mo * ؔ࿈ݚڀ | ϨγϐͱWeb 9 [10]٢ͱٶԼ, άϥϑΟΧϧσʔλϑϩʔʹΑΔ ௐཧϨγϐϓϩάϥϛϯάݴޠͷఏҊ
(2010) [9] RecipeML • Ϩγϐ • ྉཧΛͭ͘ΔͨΊʹඞཁͳࡐྉௐཧํ๏ͳͲͷใΛॻ͖هͨ͠खॱॻ • खॱॻͱ͍͏ಛੑ͔ΒߏԽ͞Εͨهड़ʹ͍͍ͯΔ
Chef mo * ؔ࿈ݚڀ | ϨγϐͱWeb 10 [12]ᬑΒ, smoon: Webͷ࣮ମԽʹΑΔߦಈࢧԉͱͦͷࢼ࡞
(2011)
Chef mo * ؔ࿈ݚڀ | ಈըʹΑΔεΫϦϓτ࣮ߦ 11 [13]܀ݪͱڮຊ, srt.js: ө૾ίϯςϯπͷ
IoT ࢦ֦ு ϓϩάϥϜຒΊࠐΈϑϨʔϜϫʔΫ (2016) • srt.js • srtϑΝΠϧ(ࣈນ)ʹJavaScriptΛهड़࣮ͯ͠ߦ͢ΔϑϨʔϜϫʔΫ • ࠶ੜͨ͠ಈըͷҙͷλΠϛϯάʹ߹ΘͤͯίʔυΛ࣮ߦ
Chef mo * Chefˎmo • ௐཧεΫϦϓτ • ಈըʹ͋ΘͤͨௐཧࢧԉͷखॱΛهࡌ • User
Generated Contents(UGC)ͱͯ͠ͷੜΛఆ • ΩονϯϚωʔδϟ • ֤ՈఉͷΩονϯʹஔ • ௐཧث۩σΟεϓϨΠͳͲͷػثશମΛ౷ׅ 12
Chef mo * Chefˎmo • ௐཧࢧԉͷܗଶ 13
Chef mo * Chefˎmo • ௐཧࢧԉͷ߹͍ 14 ChefˎmoͷλʔήοτྖҬ
Chef mo * ίϯηϓτ࣮ • YouTubeͷطଘௐཧಈըΛ༻ • srt.jsͷϑϨʔϜϫʔΫΛར༻ͯ͠ௐཧεΫϦϓτΛ࣮ߦ • Webmo[16]Λར༻ͯ͠ௐཧث۩Λࣗ࡞
• ʮ͔͚ΔʯʮࠞͥΔʯʮΔʯΛ࣮ • 3ͭͷϢʔεέʔεΛ࣮ࢪ • (a)υϨογϯάΛ͔͚Δ • (b)ཛΛ༹͘ • (c)౾ΛΔ 15
Chef mo * ίϯηϓτ࣮ 16
Chef mo * ίϯηϓτ࣮ 17
Chef mo * ٞ | Chefˎmoͷ׆༻ • λϨϯτΩϟϥΫλʔͷጪґ • ༗໊γΣϑͷௐཧಈը
• ྉཧͷັྗΛߴΊΔߴڃ৯ࡐͷಈըͳͲͷಈը • өըΞχϝͱͷίϥϘϨʔγϣϯͷ࣮ݱ 18 [18]͚ͷϑϨϯζCAFE https://twitter.com/japaricafe_hara/status/929896900525830144
Chef mo * ٞ | ௐཧث۩ • ຊൃදͰWebmo(αʔϘϞʔλ)Λར༻ͯࣗ͠࡞ • API੍ޚͰ͖Δௐཧث۩ࠓޙීٴ͢ΔͰ͋Ζ͏
• ͍··Ͱʹͳ͍ௐཧث۩ͷࣗ࡞·Γͭͭ͋Δ • Maker Faire TokyoͰʮ৯ʯΧςΰϦ͕ઃஔ 19 [22];Γ͔͚ϓϩολ:LunchBot [24]ຊ֨ͩ͠ϝʔΧʔʮBUSHIʯ [25]ΫϨʔϓϩϘοτʮΫϨϓʯ
Chef mo * ٞ | ௐཧεΫϦϓτͷ࡞ • ຊൃදͷίϯηϓτ࣮Ͱsrt.jsʹ࣮ͯߦ͢ΔJavaScriptͰ WebmoͷؔΛهड़ •
جຊతͳௐཧߦಈΛϥΠϒϥϦͱͯ͠ཧ͠ػثͷࠩҟΛٵऩ • Ϩγϐͷղੳߦಈೝ͔ࣝΒௐཧεΫϦϓτͷࣗಈੜ 20 [28]Hashimoto et al., Kusk dataset: Toward a direct understanding of recipe text and human cooking activity (2014)
Chef mo * ٞ | ཧੈքͱಈըͷ༥߹ • ChefˎmoͷޮՌΛߴΊΔͨΊʹཧੈքͱಈըͷ༥߹͕ॏཁ • VR/MR/ARͷ׆༻
• ಈըͱͷଓײ 21 [29]ᬑͱதଜ, WorldConnector: Χϝϥͷମੑ༩ʹΑΔ ө૾ੈքೖΓࠐΉΠϯλϑΣʔε (2014)
Chef mo * ՝ • ௐཧߦಈͷཻ • ଟ͘ͷௐཧߦಈʹલ४උ͕ඞཁ • ྫ͑ʮΔʯͷલʹʮ৯ࡐΛ·ͳ൘ͷ্ʹͷͤΔʯͱ͍
͏४උߦಈ͕͋Δ • ղܾҊ • ௐཧεΫϦϓτৄࡉԽʹΑΔࣗಈԽ • ਓ͕ڠௐͰ͖ΔΑ͏ࢧ࣋ɾ༠ಋ 22
Chef mo * ՝ • ಈըͷ࣌ؒ࣠ͷௐ • طଘͷௐཧಈըਓ͕ࢹௌ͢ΔͨΊʹͭ͘ΒΕ͍ͯ Δ •
ಈըͰෆཁͳ෦লུ͞ΕΔͨΊ࣮ࡍͷௐཧ࣌ ؒΑΓ͍ • ղܾҊ • ௐཧߦಈͷਐḿʹΑΓಈը࠶ੜΛ੍ޚ 23
Chef mo * ·ͱΊ • ಈը͕ௐཧΛࢧԉ͢ΔγεςϜChefˎmoͷίϯηϓτ Λఏএ • Chefˎmoͷ׆༻ํ๏՝ɺՄೳੑʹ͍ͭͯٞΛ· ͱΊͨ
• ௐཧث۩ͷൃలಈըࢹௌελΠϧͷมԽʹΑͬͯ Chefˎmoͷ׆༻໘͕Δ 24