Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Sign up for free
Menu
Search
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Features
All features
Private URLs
Password Protection
Custom URLS
Scheduled publishing
Remove Branding
Restrict embedding
Deck Collections
Notes
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Explore
Featured decks
Featured speakers
Programming
Technology
Storyboards
Pricing
Search
Sign in
Sign up for free
コンピュータビジョン4.2節
Search
Sponsored
·
Your Podcast. Everywhere. Effortlessly.
Share. Educate. Inspire. Entertain. You do you. We'll handle the rest.
→
Takahiro Kawashima
June 13, 2018
Science
370
1
Share
Embed
Copy iframe code
Copy JS code
Copy link
Start on current slide
コンピュータビジョン4.2節
研究室のゼミで発表したRichard Szeliski 著,玉木徹ら訳の『コンピュータビジョン − アルゴリズムと応用』4.2節のスライド
Takahiro Kawashima
June 13, 2018
More Decks by Takahiro Kawashima
See All by Takahiro Kawashima
論文紹介:HalluCitation Matters
wasyro
0
160
引力・斥力を制御可能なランダム部分集合の確率分布
wasyro
0
450
集合間Bregmanダイバージェンスと置換不変NNによるその学習
wasyro
0
400
論文紹介:Precise Expressions for Random Projections
wasyro
1
670
ガウス過程入門
wasyro
0
1.2k
論文紹介:Inter-domain Gaussian Processes
wasyro
0
220
論文紹介:Proximity Variational Inference (近接性変分推論)
wasyro
0
420
機械学習のための行列式点過程:概説
wasyro
0
2.2k
SOLVE-GP: ガウス過程の新しいスパース変分推論法
wasyro
1
1.7k
Other Decks in Science
See All in Science
Bリーグのショットデータを活用した得点期待値モデルの構築 / Construction of expected points model using shot data of B.LEAGUE
konakalab
0
210
生成AIが科学とRAにもたらしていること:メタサイエンスの視点から
rmaruy
0
130
[TMLR 2026, Featured Certification] Double Bounded α-Divergence Optimization for Density Estimation
gkazunii
1
120
Build your own LLM, Live, with MicroGPT
ianozsvald
0
140
明治薬科大学講義_ビッグデータ解析を支えるデータベース技術とクラウドコンピューティング
ktatsuya
1
170
JSAI2026企画セッションKS-14 インタビュー集『⼈⼯知能と哲学と四つの問い』が提起する⼈⼯知能のこれからの課題 趣旨説明 / JSAI2026 Special Session: A Collection of Interviews, “Artificial Intelligence, Philosophy, and Four Questions”
ykiyota
0
450
データベース14: B+木 & ハッシュ索引
trycycle
PRO
0
920
人生を変えた一冊「独学大全」のはなし / Self-study ENCYCLOPEDIA: The Book Which Change My Life #独学大全 #EM推し本
expajp
0
210
Kritische evaluatie van GenAI-output voor literatuuronderzoek
voginip
0
230
コーヒー豆様核 (Coffee-bean nuclei) における形態学的サブタイピングと精選・焙煎特性の同定
jagupath
PRO
0
170
Wet Active Matter
rajeshrinet
0
150
Understanding CVP Waveforms: Interpretation and Clinical Implications in Anesthesiology
taka88
0
870
Featured
See All Featured
End of SEO as We Know It (SMX Advanced Version)
ipullrank
3
4.4k
From Legacy to Launchpad: Building Startup-Ready Communities
dugsong
0
330
Templates, Plugins, & Blocks: Oh My! Creating the theme that thinks of everything
marktimemedia
31
2.9k
Automating Front-end Workflow
addyosmani
1369
210k
AI in Enterprises - Java and Open Source to the Rescue
ivargrimstad
0
1.5k
Collaborative Software Design: How to facilitate domain modelling decisions
baasie
1
320
A Tale of Four Properties
chriscoyier
163
24k
Technical Leadership for Architectural Decision Making
baasie
3
560
Context Engineering - Making Every Token Count
addyosmani
9
1.1k
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
230
23k
Code Review Best Practice
trishagee
74
20k
Product Roadmaps are Hard
iamctodd
55
13k
Transcript
4.2 અ Τοδ ౡوେ June 11, 2018 ిؾ௨৴େֶ ঙݚڀࣨ B4
࣍ 1. Τοδͷݕग़ 2. Τοδͷ࿈݁ 2
Τοδͷݕग़
Τοδͷݕग़ ྠֲઢͳͲͷΤοδ͖ΘΊͯଟ͘ͷใΛؚΉ ਓखʹΑΔΤοδݕग़ (ਤ 4.31) ˠ͜ΕΛύιίϯ༷ʹΒ͍ͤͨ 3
Τοδͷݕग़ ୯७ͳΤοδͷݕग़ํ๏ɿΤοδΛٸܹͳًมԽͱͯ͠ѻ͏ ˠًͷޯΛߟ͑Δ I(x) ΛϐΫηϧ x = (x, y)⊤ ্ͷًͱ͢Δͱɼًޯ
J(x) J(x) = ∇I(x) = ( ∂I ∂x , ∂I ∂y ) (x) (4.19) 4
Τοδͷݕग़ ϕΫτϧ J(x) ͷ • ͖ɿًؔͷ࠷ٸޯํ • େ͖͞ɿًؔͷมԽ߹͍ 5
Τοδͷݕग़ ߴपʹϊΠζ͕ଟ͍ ˠϩʔύεϑΟϧλͰฏԽ͔ͯ͠ΒޯΛܭࢉ ローパス フィルタ 6
Τοδͷݕग़ ϑΟϧλద༻ޙޯͷ͖͕ਖ਼͘͠อଘ͞Ε͍ͯͯ΄͍͠ ˠԁܗͷϑΟϧλ ՄೳͳԁܗϑΟϧλΨεϑΟϧλͷΈ (3.2 અɼਤ 3.14) ˠΤοδݕग़ͷͨΊͷϩʔύεϑΟϧλΨγΞϯ͕ఆ൪ 7
Τοδͷݕग़ ඍઢܗԋࢉͰ͋ΔͷͰଞͷϑΟϧλԋࢉͱՄ ΨεϑΟϧλؔΛ Gσ(x) = 1 2πσ2 exp ( −
x2 + y2 2σ2 ) ͱ͢Δ ฏԽޙͷը૾ͷޯΛ Jσ(x) ͱॻ͘ͱɼ Jσ(x) = ∇[Gσ(x) ∗ I(x)] = [∇Gσ(x)] ∗ I(x) (4.20) ͱͳΓɼΨεϑΟϧλؔͷඍͱͷͨͨΈࠐΈͰදݱͰ͖Δ 8
Τοδͷݕग़ ΨεϑΟϧλؔͷඍͷධՁ ∇Gσ(x) = ( ∂ ∂x , ∂ ∂y
)⊤ Gσ(x) = ( ∂ ∂x , ∂ ∂y )⊤ 1 2πσ2 exp ( − x2 + y2 2σ2 ) = 1 σ2 (−x, − y)⊤ 1 2πσ2 exp ( − x2 + y2 2σ2 ) ((4.21) ࣜͱ߹Θͳ͍͕ͨͿΜ͜ΕͰ͍͋ͬͯΔ) 9
Τοδͷݕग़ thinning ΤοδΛ 1 ըૉͷଠ͞Ͱදݱ͍ͨ͠߹͕ଟ͍ (ࡉઢԽ; thinning) (ը૾ [1] ΑΓ)
10
Τοδͷݕग़ thinning ʮΤοδʹରͯ͠ਨͳํͷޯڧ͕࠷େʹͳΔ࠲ඪʯΛٻ ΊΕΑ͍ ˠًͷ 2 ֊ඍ (ϥϓϥγΞϯ) Λߟ͑ΕΑͦ͞͏ͩ ͜ͷ
2 ֊ඍͷ Sσ(x) ɼ∇2 = ∇ · ∇(= div grad) ΑΓ Sσ(x) = ∇ · Jσ(x) = [∇2Gσ(x)] ∗ I(x) (4.22) 11
Τοδͷݕग़ thinning ΨεϑΟϧλͷϥϓϥγΞϯͷධՁ ∇2Gσ(x) = ∇ · [ 1 σ2
(−x, − y)⊤ 1 2πσ2 exp ( − x2 + y2 2σ2 )] = ∂ ∂x [ − x 2πσ4 exp ( − x2 + y2 2σ2 )] + ∂ ∂y [ − y 2πσ4 exp ( − x2 + y2 2σ2 )] = 1 2πσ2 ( x2 + y2 − 2σ2 σ4 ) exp ( − x2 + y2 2σ2 ) 12
Τοδͷݕग़ thinning ∇2Gσ(x) ͷΛແࢹˠ LoG(Laplacian of Gaussian) ϑΟϧλ LoG(x) =
( x2 + y2 − 2σ2 σ4 ) exp ( − x2 + y2 2σ2 ) 13
Τοδͷݕग़ thinning Sσ(x) ͷූ߸͕มԽ ˠ૬ରతͳ໌Δ͕͞มԽ Sσ(x) ͷθϩަࠩΛ୳ͤ Α͍ 14
Τοδͷݕग़ thinning sign(Sσ(xi)) ̸= sign(Sσ(xj)) ͱͳΔྡϐΫηϧ xi, xj ͓Αͼθ ϩަࠩ
xz Λ୳͢ Sσ(xi) ͱ Sσ(xj) ͱΛ݁Ϳઢ͕θϩͱަࠩ͢Δ xz ΛٻΊΔ 15
Τοδͷݕग़ thinning Sσ(xj) − Sσ(xi) xj − xi (xz −
xi) + Sσ(xi) = 0 ∴ xz = xiSσ(xj) + xjSσ(xi) Sσ(xj) + Sσ(xi) ͕ಘΒΕΔɽ3 ࣍ݩҎ্ͷ߹ಉ༷ʹ xz = xiSσ(xj) + xjSσ(xi) Sσ(xj) + Sσ(xi) (4.25) Ͱ͋Δ 16
Τοδͷݕग़ εέʔϧબͱϘέྔਪఆ LoG ʹదͳ σ ΛઃఆˠӶ͍/ಷ͍ΤοδΛநग़ (ਤ 4.32, (b), (c))
17
Τοδͷݕग़ εέʔϧબͱϘέྔਪఆ ͍ײͰΤοδΛͱΓ͍ͨͳΒʁ ˠεέʔϧεϖʔεͷΞϓϩʔν 1. ͍͔ͭ͘ͷ σ Λ༻ҙ 2. ͦΕͧΕͷ
σ ʹ͍ͭͯޯ ͱ 2 ֊ඍΛܭࢉ 3. ҆ఆʹΤοδΛݕग़Ͱ͖Δ ࠷খͷ σ ΛબɼͦΕΑΓ େ͖͍ σ Ͱݕग़͞ΕͨΤο δΛՃ 18
Τοδͷݕग़ εέʔϧબͱϘέྔਪఆ ͍ σ ͰΤοδΛநग़ (ਤ 4.32, (f)) 19
Τοδͷݕग़ Χϥʔը૾ͰͷΤοδݕग़ Χϥʔը૾ͰΤοδݕग़Λ͍ͨ͠ ୯७ʹًޯΛݟΔͱɼً৭ؒͷΤοδΛݕग़Ͱ͖ͳ͍ ղܾҊ 1ɿRGB ֤͝ͱʹًޯΛܭࢉ͢Δ • ֤৭Ͱූ߸ͷҟͳΔޯ͕ग़Δͱɼ୯७ͳ͠߹ΘͤͰ૬ ࡴ͕ى͜Δ
ղܾҊ 2ɿ֤ըૉͷपลͰہॴతͳ౷ܭྔΛ͍Ζ͍ΖௐΔ • ୯७ͳًɾ໌ɾ৭͚ͩͰͳ͘ɼςΫενϟͷมԽͳͲ ଊ͑ΒΕΔ 20
Τοδͷݕग़ ਤ 4.33ɽBGɿ໌ɼCGɿ৭ɼTGɿςΫενϟ 21
Τοδͷ࿈݁
Τοδͷ࿈݁ நग़͞ΕͨΤοδΛ࿈݁ͯ͠Ұܨ͗ʹ͍ͨ͠ thinning ͞ΕͨΤοδͷըૉใΛ͍࣋ͬͯΔͱָ ˠ͍ۙΛ୳ࡧͯ͠ܨ͛Α͍ ΤοδΛ࿈݁͢ΔͱΑΓѹॖͨ͠දݱ͕ՄೳʹͳΔ 22
Τοδͷ࿈݁ νΣΠϯίʔυ 8 ͭͷํ֯ (N, NE, E, SE, S, SW,
W, NW) Λ 3bit ͰίʔυԽ (ਤ 4.34) 23
Τοδͷ࿈݁ νΣΠϯίʔυ νΣΠϯίʔυͰͷΤϯίʔυޙɼϥϯϨϯάεූ߸Ͱ͞Βʹѹ ॖͰ͖Δ ϥϯϨϯάεූ߸ ܁Γฦ͠ͷจࣈΛͦͷճͰදݱ AAAABBBCCCCC ˠ A4B3C5 24
Τοδͷ࿈݁ arc-length parameterization ʮހʯͷ͞ͱΤοδ࠲ඪΛ༻͍ͯදݱ (ਤ 4.35) 1. x0 = (1,
0.5)⊤ ͔Βελʔτ 2. s = 0 ʹ x0 ͷ࠲ඪΛͦΕͧΕϓϩοτ 3. x1 = (2, 0.5)⊤ 4. s = ∥x1 − x0∥ = 1 ʹ x1 ͷ࠲ඪΛͦΕͧΕϓϩοτ 5. ࢝ʹΔ·Ͱ܁Γฦ͢ 25
Τοδͷ࿈݁ arc-length parameterization Q. Կ͕͏Ε͍͠ͷ͔ʁ A. ϚονϯάฏԽͳͲͷॲཧ͕༰қʹͳΔ ܗঢ়ͷࣅͨΤοδΛߟ͑Δ (ਤ 4.36)
26
Τοδͷ࿈݁ arc-length parameterization 1. Τοδͷ࠲ඪͷฏۉ ¯ x0 = ∫ S
x(s)ds Λݮࢉ 2. s Λ 0 ∼ S ͔Β 0 ∼ 1 ʹਖ਼نԽ 3. ͦΕͧΕʹ͍ͭͯϑʔϦΤม 27
Τοδͷ࿈݁ arc-length parameterization ͱͷΤοδಉ͕࢜εέʔϦϯάͱճసͷҧ͍͔͠ͳ͍ ˠϑʔϦΤมͷ݁ՌڧͱҐ૬ͷζϨ͔͠ҟͳΒͳ͍ͣ (։͕࢝ҟͳΔͱઢܗͷҐ૬ͷζϨग़Δ) 28
Τοδͷ࿈݁ arc-length parameterization ࢄԽ࣌ʹੜ͡ΔϊΠζͷฏԽʹ༗ޮ ͔͠͠ී௨ʹฏԽϑΟϧλΛ͔͚Δͱॖখͯ͠ฏԽ͞ΕΔ ਤ 4.37(a), ԁͷܘ͕ॖখ͍ͯ͠Δ 29
Τοδͷ࿈݁ arc-length parameterization 2 ֊ඍʹجͮ͘Φϑηοτ߲Λ͔͢ɼΑΓେ͖ͳ (ͦ͢ͷ ͍ʁ) ฏԽϑΟϧλΛ༻͍Δ ਤ 4.37(b)
30
·ͱΊ • άϨʔεέʔϧը૾ͰًޯͰΤοδΛݕग़ ϊΠζআڈಉ࣌ʹߦ͏ͨΊʹΨγΞϯϑΟϧλͷ 1 ֊ඍ ͱͨͨΈࠐΉ • thinning ͍ͨ͠߹
LoG ϑΟϧλΛ͔͚ͯθϩަࠩΛٻ ΊΔ • Χϥʔը૾ͷΤοδݕग़໌ɾ৭ɾςΫενϟͳͲͷ౷ܭ ྔ͕༗ޮ • thinning ͞ΕͨΤοδͷ࿈݁νΣΠϯίʔυ arc-length parameterization ͕༗ޮ • arc-length parameterization ޙϚονϯάϊΠζআڈΛ͠ ͍͢ 31
References I [1] R. Rao. Image sampling, pyramids, and edge
detection. https://courses.cs.washington.edu/courses/cse455/ 09wi/Lects/lect3.pdf, 2009.