Upgrade to Pro — share decks privately, control downloads, hide ads and more …

Shoe Recognition Model with Floor Pressure Sens...

Avatar for yumulab yumulab
November 06, 2024
Research
0
28

Shoe Recognition Model with Floor Pressure Sensors (Slide)

2024年11月3日(日)〜7日(木)に開催されたSENSORCOMM2024の発表資料(スライド)
Avatar for yumulab

yumulab

November 06, 2024
Tweet

More Decks by yumulab

See All by yumulab
ASSADS：ASMR動画に合わせて撫でられる感覚を提示するシステムの開発と評価 / ec75-shimizu
Avatar for yumulab yumulab
1
400
ｳｯﾄﾞｽﾀｯｸﾁｬﾝ：木材を用いた小型エージェントロボットの開発と印象評価 / ec75-sato
Avatar for yumulab yumulab
1
420
MGDSS：慣性式モーションキャプチャを用いたジェスチャによるドローンの操作 / ec75-yamauchi
Avatar for yumulab yumulab
0
260
チャッドローン：LLMによる画像認識を用いた自律型ドローンシステムの開発と実験 / ec75-morisaki
Avatar for yumulab yumulab
1
480
NOVVS：北海道情報大学図書館における滞在人数可視化システムの開発と検証 / i2025-minami
Avatar for yumulab yumulab
0
92
CHaserWeb:ブラウザ上で動作する対戦型プログラミング学習環境の提案と評価 / i2025-inoue
Avatar for yumulab yumulab
0
240
CARMUI-NET：自動運転車遠隔監視のためのバーチャル都市プラットフォームにおける通信品質変動機能の開発と評価 / UBI85
Avatar for yumulab yumulab
0
250
待機電力を削減したネットワーク更新型電子ペーパーサイネージの研究開発 / UBISympo2025
Avatar for yumulab yumulab
0
110
デジタルファブリケーションの未来を北海道・札幌から考える / SIAF School 2025
Avatar for yumulab yumulab
0
110

Other Decks in Research

See All in Research
SSII2025 [TS3] 医工連携における画像情報学研究
Avatar for 画像センシングシンポジウム ssii
PRO
2
1.2k
20250605_新交通システム推進議連_熊本都市圏「車1割削減、渋滞半減、公共交通2倍」から考える地方都市交通政策
Avatar for Traffic Brain trafficbrain
0
520
[輪講] SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features
Avatar for Naoki Kato nk35jk
2
570
問いを起点に、社会と共鳴する知を育む場へ
Avatar for MATSUMOTO Ryosuke matsumoto_r
PRO
0
410
Weekly AI Agents News!
Avatar for masatoto masatoto
33
68k
Sosiaalisen median katsaus 03/2025 + tekoäly
Avatar for Harto Pönkä hponka
0
1.3k
電力システム最適化入門
Avatar for MIKIO KUBO mickey_kubo
1
700
Vision And Languageモデルにおける異なるドメインでの継続事前学習が性能に与える影響の検証 / YANS2024
Avatar for Sansan R&D sansan_randd
1
110
NLP Colloquium
Avatar for Juno Kim junokim
1
160
Adaptive Experimental Design for Efficient Average Treatment Effect Estimation and Treatment Choice
Avatar for MasaKat0 masakat0
0
140
RHO-1: Not All Tokens Are What You Need
Avatar for Sansan R&D sansan_randd
1
130
「エージェントって何？」から「実際の開発現場で役立つ考え方やベストプラクティス」まで
Avatar for MIKIO KUBO mickey_kubo
0
120

Featured

See All Featured
Balancing Empowerment & Direction
Avatar for Lara Hogan lara
1
440
Evolution of real-time – Irina Nazarova, EuRuKo, 2024
Avatar for Irina Nazarova irinanazarova
8
830
JavaScript: Past, Present, and Future - NDC Porto 2020
Avatar for David Neal reverentgeek
50
5.5k
RailsConf & Balkan Ruby 2019: The Past, Present, and Future of Rails at GitHub
Avatar for Eileen M. Uchitelle eileencodes
138
34k
BBQ
Avatar for Matthew Crist matthewcrist
89
9.7k
Faster Mobile Websites
Avatar for Dean Hume deanohume
307
31k
The Language of Interfaces
Avatar for Des Traynor destraynor
158
25k
Fashionably flexible responsive web design (full day workshop)
Avatar for Andy Clarke malarkey
407
66k
Imperfection Machines: The Place of Print at Facebook
Avatar for Scott Boms scottboms
267
13k
The MySQL Ecosystem @ GitHub 2015
Avatar for Sam Lambert samlambert
251
13k
Helping Users Find Their Own Way: Creating Modern Search Experiences
Avatar for Dan Newman danielanewman
29
2.7k
Designing for humans not robots
Avatar for Tammie Lister tammielis
253
25k

Transcript

  1. Shoe Recognition Model with Floor Pressure Sensors Sora Kamimura *1

    Tetsuo Yutani *2 Atsuko Shibuya *2 Tsubasa Yumura *1 *1 Hokkaido Information University *2 FirstFourNotes, LLC <%FNP>

  2. Table of contents  #BDLHSPVOE1VSQPTF  1SFTTVSFTFOTPS  .PEFM 

    %BUBTFUT  3FTVMU%JTDVTTJPO  $PODMVTJPO

  3. #BDLHSPVOE1VSQPTF 5SB ffi D fl PXBOBMZTJT #ZDBNFSB 4VSWFJMMBODFDBNFSBTDBOCFEJWFSUFE $BONBOBHFBMBSHFBSFBCZPOFDBNFSB *OWBTJPOPGQSJWBDZ

    #MJOETQPUTDBVTFECZPCTUBDMFT ɾ*NQSPWFEXPSLF ffi DJFODZ ɾ"WPJESJTL DPMMJTJPOT GBMMT FUDʜ  #Z fl PPSQSFTTVSFTFOTPS /PQSJWBDZJTTVF /PCMJOETQPUT

  4. #BDLHSPVOE1VSQPTF 5SB ff i D fl PXBOBMZTJTCBTFE fl PPSQSFTTVSFTFOTPS SFRVJSFTJEFOUJ

    fi DBUJPOPGQFPQMF )VNBOJEFOUJ fi DBUJPOVTFT XFJHIU TUSJEFMFOHUI TQFFE TIPFUZQF FUD *OUIJTTUVEZ XFEFWFMPQUIF TIPFSFDPHOJUJPONPEFMXJUI fl PPSQSFTTVSFTFOTPST

  5. 1SFTTVSFTFOTPS .BUFSJBMT ɾ7FMPTUBU QSFTTVSFTFOTJUJWFDPOEVDUJWFTIFFU ɾ$PQQFSGPJMUBQF ɾ"SEVJOP 4USVDUVSF ɾ$PQQFSGPJMUBQFTBSFNNXJEFBOE ɹTQBDFENNBQBSU ɾUBQFTCPUIWFSUJDBMMZBOEIPSJ[POUBMMZ

    ɾNFBTVSFNFOUQPJOUT ɾ.FBTVSFUIFWPMUBHFBUFBDIQPJOUFWFSZNT

  6. .PEFM ɾ5IF*OQVUMBZFSSFDFJWFTSBXEBUB ɾ5IFIJEEFOMBZFSJTUISFFGVMMZDPOOFDUFEMBZFS ɾ5IFPVUQVUMBZFSXJMMPVUQVUUIFTIPFJEFOUJ fi DBUJPOFTUBCMJTINFOU ɹ TOFBLFS SPPNTIPF BOETBOEBM

    /FVSBMOFUXPSLNPEFM

  7. %BUBTFUT )PXUPDPMMFDU  $BMJCSBUJPOUIFTFOTPS  1VUPOTIPF  8BJUBGFXTFDPOET TPST 

     .FBTVSFNFOUT  .FBTVSFNFOUTUJNFT JOFBDITIPF %BUB5ZQF ɾ&BDITFOTPS ʙ PS.FSHFE ɾ)PXMPOHXBJUGPSNFBTVSF TPST  ɾ/PSNBMPS3PUBUFEEFHSFFTGPS ɹEBUBBVHNFOUBUJPO

  8. 3FTVMU ɾ5IF'NFBTVSFJOTJT ɹIJHIFSUIBOT ˠ7JCSBUJPOTBOEPUIFSOPJTFTJT ɹMFTTCZXBJUJOH ɾ*OTFDPOET UIF'NFBTVSFPG ɹNFSHFEEBUBJTIJHIFSUIBO ɹFBDITFOTPSEBUB ˠ5IFTFOTPSIBTBTFOTJUJWJUZCJBT

    ɹ"OE NPEFMDBOUMFBSOJUCZ ɹFBDITFOTPSEBUB ɹ#VUMFBSOJOHCFDBNFQPTTJCMFCZ ɹNFSHFEEBUB 'NFBTVSF F = 2 × precision × recall precision + recall

  9. $PODMVTJPO ɾ*OUIJTTUVEZ XFEFWFMPQFEUIFOFVSBMOFUXPSLNPEFMUPSFDPHOJ[F ɹTIPFUZQFTXJUI fl PPSQSFTTVSFTFOTPSXJUIB7FMPTUBU ɾ6TJOHBSPUBUFEEBUBTFUQSPWFEUPCFUIFNPTUF ff FDUJWFBQQSPBDIGPS ɹSFBMXPSMEBQQMJDBUJPOT

    ɾ5IFSFBSFMBSHFEJ ff FSFODFCFUXFFOUIFFYQFSJNFOUBMFOWJSPONFOU ɹBOEUIFBTTVNFESFBMFOWJSPONFOU ɾ5IFSFBSFQSPCMFNTTVDIBTSFBDUJPOSBUFBOEBMMPXBCMFQSFTTVSF ɾ8FXJMMDPOUJOVFUPEFWFMPQCPUIIBSEXBSFBOETPGUXBSFUPTPMWF ɹUIFTFQSPCMFNT