୷ܭຎޑًၰୀෳᆶଓᙫᄽᆉݤ!
բޣǺֆࣂ०ǴբޣΒΒǺ݅ӄ !!
୍ܺൂՏǺ୯ҥҬ೯εᏢ!
ႝᐒᆶڋᏢس!
e-mail:[email protected] [email protected]
բޣΟǺഋࡏᓄ!
୍ܺൂՏǺ٥ࢪεᏢ!
!!!!!!!!!!ၗૻπำᏢس!!!!!!!!!!!
e-mail: [email protected]
ᄔा!
ҁፕЎගрঁཥޑًၰୀෳϷଓᙫ ޑБݤǶճҔ൳ՖӀᏢޑБԄёаी
ᆉၡय़ޑᗺܭቹႽ০ޑՏǴ ӢԜճҔीޑًၰϷًၰጕቨࡋёаႣ
ෳቹႽύԜٿޣޑ࣬ჹՏϷቻǴ ԜԖշܭזೲЪ҅ዴޑୀෳډًၰጕޑՏ
Ƕ٠ЪǴճҔᄊਠ҅ޑБԄёа҅ዴ ޑڗளྣ࣬ᐒޑ௹فϷჴሞޑًၰቨ ࡋǶќѦǴҁፕЎගраঁᘏڗًၰጕ ޑރᄊᐒٰڗளቹႽύڀԖًၰጕޑቻ ޑՏǴ٠аኳጋᡄᒠٰղᘐځύব٤ω
ࢂًၰጕޑᗺǴ٠ᒧځύҽޑᗺࣁ
ᗺ(knot)-а B-spline ޑϣකٰံىًၰ ᜐࣚޑ܌ԖᗺǴฅࡕаѰѓٿచԔጕඔ
ॊًၰጄൎǶҁًၰୀෳБݤճҔႣً
ၰቨࡋаϷଓᙫޑБԄǴૈගଯՉ
ୀෳًၰޑೲࡋϷᛙ଼܄Ǵ٠ૈӧᜐً
ၰጕጨਔǴϝૈԖਏࡰрٿᜐًၰጕ ޑՏǶǶ!
ᜢᗖຒǺًၰୀෳǵᄊਠ҅ǵᎯᎭᇶշ سǵރᄊᐒ!
ǵᏤፕʳ
ᎯᎭᇶշسᆶคΓᎯᎭًޑࣴزሡ Ԗًၰၗૻٰղᘐً፶ၡጕǴځதሡ ଛӝምᛖނୀෳٰղᘐব٤ӦБԖምᛖ ނǴёૈቹៜՉӼӄ\2^.\5^ǶӢࣁѝ ԖًၰϣޑምᛖނωࢂձाݙཀޑǴӢ ԜምᛖނᆶًၰޑၗૻࣣѸڗளǴа،
ۓБምᛖނࢂցቹៜՉӼӄǶฅ ԶǴምᛖނჹًၰޑጨததቹៜًၰୀ
ෳޑ҅ዴ܄ǴӢԜǴًၰୀෳޑঁख़ᗺ
ࢂाૈլܺጨݩǴҁፕЎගрճҔ൳ ՖቹϷᄊਠ҅БԄаڗளًၰၗૻǴ ٠ճҔރᄊᐒᘏڗًၰጕቻǴӆଛӝً
ၰጕଓᙫޑБԄǴջ٬ӧచًၰጕ
ጨޑΠǴճҔќచ҂ጨޑًၰ ጕϝฅёаԖਏޑڗளֹޑًၰၗૻǶ!
୷ܭຎޑᎯᎭᇶշسճҔྣ࣬ᐒ ڗளҬ೯ၗૻǴа෧ᇸᎯᎭޣॄᏼ٠ගଯ Ӽӄ܄ǶճҔًၰୀෳسёаҔܭڗள ඵችًБًၰޑՏǴѬࢂճҔးӧ ඵችًޑྣ࣬ᐒٰܡឪًቹႽǴฅࡕ ճҔቹႽೀמೌٰ൨פၰၡᜐࣚ܈ًၰ ጕǴаځٰۓကБًၰޑՏǴаᗉխ ඵችًୃᚆًၰǶ!
ୀෳًၰޑБݤࢂӃڗளًၰޑ
ቻǴӭኧޑًၰӧѰѓٿᜐӚԖ
చًၰጕጕǴՠԖਔѝԖၰၡᜐጔǶً
ၰጕ࣮ଆٰႽԖᗺᡂϯޑٿచறǴٯ ӵԖਔࢂޔጕԶԖਔԔጕǴԖਔࢂೱុޑ
చߏጕǴԖਔࢂࢤࢤޑԖڰۓ໔႖ޑ อጕǴᚑՅ߾ԖਔқՅǵՅ܈आՅǶନ ԜϐѦǴၡय़ምᛖނаϷځቹԖਔ
ጨًၰጕǵᕉნߝࡋޑׯᡂ܌ԋً
ၰጕߝࡋޑᡂϯதቚуୀෳًၰጕޑ֚
ᜤ\6^.\9^Ƕ!
٤ࣴزޣޑୀෳًၰБݤࣁӃᜐ ጔୀෳǴӵԜёаӃפډЪҢрቹႽύ ނҹޑᜐጔǴځύх֖ΑًၰаϷߚًၰ [9]ǶӢࣁًၰጕޑቻϐࢂೱុޑጕǴ ӢԜёаӃճҔ!Hough transform פډቹ Ⴝύޑޔጕ[10]ǴԜѦǴճҔًၰቨࡋ೯
தڰۓϷٿᜐًၰጕѳՉޑቻǴҗ൳
ՖޑᙯඤǴ೭٤җ Hough transform פ ډޑޔጕёаӆϩрব٤ωࢂًၰጕ [11] -[13]ǶӢࣁၰၡதԖᐋቹ܈ځѬނ ҹޑጨቹៜྣ࣬ᐒܡឪډޑًၰޑѦ ᢀǴӢԜפډޑၰၡᜐጔ೯த٠όֹǶ ӢԜѸ٬Ҕϣකݤ܈ԔጕᔕӝޑБݤٰ
ஒًၰٿᜐޑᜐጔՏֹޑᗺрٰǴ!
Chris et al.!ճҔঁёᡂޑኬ݈ኳࠠ
(deformable template shape model)ٰୀෳ
ًၰǴдॺᇡࣁၰၡޑٿᜐᜐࣚރ߈՟
ٿచΒԛБำԄǴӧᆉр߯ኧࡕǴёа ҔΒԛБำԄ߄Ңًၰᜐࣚ[14][15]ǴՠԖ ٤ T ၰ٠ߚΒԛБำԄёаډԔጕ ᔕӝǶWang et al.ගрճҔጕϣක (spline interpolation)ǴёаඔᛤӚᅿݩޑ
ၰǶӢԜǴБًၰޑՏёаҔ
ጕಔԋޑٿచԔጕҢܭቹႽύ[16][17]Ƕ!
ၰၡቻޑڗளБݤύǴࡐӭࣴزޣ
٬ҔᜐጔୀෳޑБԄ[15]ǴӵԜளډޑᗺ ӆϒаϩᜪǴаϩрًၰቻǶԜᓬᗺ ࣁջ٬ؒԖًၰጕǴѝाԖၰၡᜐጔ൩ё аפډًၰǴՠΨԖ٤ୢᚒǴӵᜐጔୀ
ෳதӢεໆޑीᆉԶਔǴቹៜࢂୀෳ
ًၰޑೲࡋࢂցזǴќѦǴۘሡլܺᚇ
ૻޑୢᚒǴӵምᛖނޑቹϷҁيΨё
ૈԋୀෳޑᒱᇤǶԶЪǴ٬Ҕᜐጔୀ
ෳޑБݤதሡӕਔճҔٿᜐًၰᜐጔޑ
ቻǴऩԖБً፶ምᛖނጨΑځύ
ᜐǴ೯த൩ԋୀෳᒱᇤǶҁፕЎගр ճҔًၰጕᘏڗރᄊᐒёаזೲЪྗዴפ ډ ً ၰ ጕ ޑ ቻ Ǵ ӆ ճ Ҕ ൳ Ֆ ᙯ ඤ (geometry transformation)ёаႣًၰጕ ёૈޑՏϷځӧόӕՏஒևޑόӕ ε λ Ƕ ٠ Ъ ճ Ҕ ᄊ ਠ ҅ (dynamic calibration)Ǵ٬ளྣ࣬ᐒୖኧϷၰၡቨࡋ
ၗૻᒿਔёа׳ཥǶճҔኳጋᡄᒠޑБԄ ᒣୀෳډނҹᆶًၰቻޑ࣬՟ำࡋǴ ӆаଓᙫޑБԄ෧Ͽཛྷ൨ጄൎǴ٠ቚуୀ
ෳځᛙ଼܄ǴӢԜǴջ٬Ԗምᛖނጨځ ύޑᜐًၰጕǴϝฅёаפډ҅ዴޑً
ၰՏǶ!
ҁፕЎޑಔᙃӵΠǺಃΒക௶ॊҔྣ
࣬ᐒኳٰࠠϩቹႽǹಃΟകගрճҔ
ঁًၰጕᘏڗރᄊᐒٰפًၰጕቻǹಃ
ѤകගрճҔᄊਠ҅ޑБݤٰլܺྣ࣬
ᐒਗԶׯᡂ௹فࡋޑୢᚒǹಃϖകࢂ
ًၰጕୀෳޑ่݀ǹಃϤകࢂ่ፕǶ!
!
Βǵྣ࣬ᐒኳࠠʳ
ճҔຎᙯඤёаीᆉрҺՖ 3D Ш
ࣚ০ޑᗺ(X, Y, Z)ډ 2D ቹႽ০(u, v)ޑՏ[8]Ƕஒ 4E ޑඳޑᗺჹࢀډ 3E ޑቹႽѳय़ޑᗺࢂӭჹޑᙯඤǴډ v ০ޑᗺᆶ Y, Z ০࣬ᜢǴԶډ u ০ޑᗺᆶ X, Z ০࣬ᜢǶฅԶǴऩࢂӦ ѳय़ᆶቹႽ০ޑჹࢀ߾ࢂჹޑᙯ ඤǶӢࣁឦܭӦѳय़ޑᗺޑ Y ০ࢂςޕ ޑǴӢԜѬޑ Z ০Տޔௗቹៜډ
ܭ v ০ޑՏǶӢԜǴճҔ೭ঁБݤё аҔܭໆෳྣ࣬ᐒᆶӦय़Һཀᗺ P1 ϐ ໔ޑຯᚆǶԜѦǴӦय़ނҹޑቨࡋ ΨёаճҔБԄٰᆉǶ!
)*Ӧѳय़ޑ൳Ֆ!
ҁࣴز܌Ҕޑྣ࣬ᐒ০ᆶШࣚ০
ࢂឦܭѓЋ০سǶკ܌Ңࣁྣ࣬ᐒ ޑԋႽၸำǴځύ Ow߄ҢШࣚ০(X, Y, Z) ޑচᗺǴOi߄ҢቹႽ০(u, v, w)ޑচᗺǶ з Ȝ ߄Ңྣ࣬ᐒޑขຯǹp ߄Ң᜔ТύЈǹ i߄Ңྣ࣬ᐒଯࡋǶ߾Шࣚ০(0, h, 0)!ջ ࣁ᜔ТύЈǶୖኧ ij ࢂw.x০ືᙯޑ
௹فǹș ࢂ w-u ০ືᙯޑѳ౽فǹȥ
ࢂ u-v ০ືᙯޑའᘍفǹԜΟঁفࡋ ޑελࢂаݙຎচᗺޑБӛਔដᙯ ԶளǶკΒ(a)߄Ңྣ࣬ᐒБӦѳय़ޑ Y, Z০ډ v ০ޑᜢ߯Ǵკύ ij=-Įǹ ș=0ǹ ȥ=0ǹ!Į ߄Ңྣ࣬ᐒޑ९فǴջ w
ືᆶӀືqFޑ֨فǶკΒ(a)ύǴзШࣚ০
ᗺ P1ډቹႽ০ᗺ y1Ǵ߾ P1ᆶྣ
࣬ᐒϐ໔ޑຯᚆO Pw 1ёаҔ(1)ٰीᆉԶ ளǶ!
!
1 1
1 tan - tan
w 2
O P h §§ · § y ·· ¨¨ ¸ ¨ ¸¸
© ¹ © ¹
© ¹
͘ ͉
͓ !(1)!
ʳ
)Β*ًၰቨࡋޑᆉ!
ӵკΒ(b)܌ҢǴA1!ǵB1 ϩձࢂѰϷ ѓًၰጕޑᗺǶӧςޕࠟޔຯᚆO Pw 1-ޑ చҹΠǴA1!ǵB1!ޑ Y ০ॶஒ،ۓځ
ܭ u ০ޑՏǴӢԜًၰቨࡋё аҗᆉளޕǶკΒ(a)ύޑًၰቨࡋࢂ
1 1
A BǴځϐቨࡋࣁ!a b1 1ǴOw ک!A B1 1ϐ ໔ޑࠟޔຯᚆёаҗ(1)ٰीᆉǴਥᏵ࣬
՟Οف܄፦ǴA B1 1کa b1 1ޑᜢ߯ӵ(2)܌
ҢǶ!
1 1 1 1 1 /
A B a b uP p ͓!!!!!!!!!(2)!
ਥᏵ(2)ёޕ-!ًၰᒿຯᚆྣ࣬ᐒ ޑᇻ߈ԋόӕޑቨࡋǴځύ v ০،
ۓځຯᚆǴԶ u ০ё،ۓځቨࡋǶ ӕǴًၰጕޑቨࡋΨёीǶ!
Οǵًၰጕᘏڗᄽᆉݤ!
ًၰጕҁي߈՟ٿచѳՉޑறǴҁ
ҽஒගрճҔԜቻٰᘏڗًၰጕޑБ ݤǶ!
)*ًၰޑቻ!
2/!Ԫ໘ॶቻǺًၰጕ೯தҗқՅǵ
Յ܈आՅޑݨᅊᅊԋԔጕ܈ޔጕǴӢځ
ၨӦय़ޑԪՅܰϸӀǴӢԜځӧቹႽύ ޑԪ໘ॶ೯தၨӦय़ࣁଯǶӵკΟࣁًၰ ጕቹӧቹႽύǴӈԪ໘ॶޑᡂϯǶ M০߄ҢቹႽᐉ০ǴаቹႽനѰᜐࣁ M০ॶࣁ႟Ǵӛѓ M ০ॶቚуǶ!Wim
߄ҢًၰጕቹޑቨࡋǶg1-g2ϩձࣁӦय़ ᆶًၰጕޑԪ໘ॶǶќѦǴӢࣁႽৡޑቹ ៜԶ٬ًၰጕᜐጔᆶӦय़ޑҬௗೀޑԪ໘ ॶࣁᅌቚу܈ᅌቚуǶM1ᆶ M2ϐ໔ ߄ҢًၰጕޑѰᜐᆶӦय़Ԫ໘ॶҬࣚୱ
ౢғᅌϲޑԪ໘ॶᡂϯǴM3ᆶ M4߾ ࣁًၰѓᜐࣚᆶӦय़ϐҬࣚࣁᅌΠफ़Ƕ ӢԜा൨פًၰጕޑቻёаӈ൨פቹ ႽύԪ໘ॶޑᡂϯᆶკΟᜪ՟ޣǴځёૈ
ࣁًၰጕǶ!
3/ቨࡋቻǺӧӕచၰၡޑًၰ ቨࡋᆶًၰጕቨࡋ೯தᡂϯࡐλǴਥᏵ൳ Ֆቹёаीᆉٿచًၰጕቹޑቨࡋε λǴԜቻԖշܭפр҅ዴޑًၰՏǶ!
)Β*ًၰጕᘏڗރᄊᐒ!
ҁЎගраঁًၰጕᘏڗރᄊᐒ (Lane Marking Extraction (LME) Finite State Machine (FSM))!ѐڗளቹႽύًၰ ጕޑՏǶӧቹႽύӈ(row)ۓٿঁ
ୀෳᗺ PAᆶ PBǴٿᗺϐ໔ຯᚆࣁ dmǴӵ )4*܌ҢǶԜٿᗺ PAᆶ PBޑՏӕਔҗ ѰԶѓ౽ਔǴٿᗺޑԪ໘ॶϐৡ Gdᒿ
PAᆶ PBޑѓ౽ԶᡂϯǶѓ౽ঁႽ નǴ߾Ԗঁཥޑ GdǴᆀ GinǴёஒځ ຎࣁًၰጕᘏڗރᄊᐒޑঁᒡΕߞဦǴ ऩӧځ౽ޑୱϣԖًၰጕቻޑӸ ӧǴ߾ᒿ Gin ޑᒡΕ٬ًၰጕᘏڗރ ᄊᐒޑރᄊҗރᄊ 1 ٩ׇᡂϯډރᄊ 6Ǵ ӢԜǴਥᏵރᄊޑᡂϯёаୀෳӈً
ၰጕቻޑՏϷελǶ!
კѤ܌ҢࣁቹႽύԖًၰጕޑቻ ਔǴᒿ PAᆶ PBޑӛѓ౽Ǵځᆶًၰ ጕቻޑ࣬ჹՏёаԖ 6 ᅿރᄊǶ߄
߄ҢӧόӕރᄊਔǴGd ॶޑጄൎёаႣ
Ǵځύ th1ǵ!th2ǵ!th3ǵ!th4-!ࣁҗी
܌ளޑᖏࣚॶ(threshold)! Gin>Gd1ਔǴ߄ Ң Ginॶ಄ӝabs G( d) th1చҹǴӕёளځ ᎩచҹǶ߄Β߄Ңًၰጕᘏڗރᄊᐒޑރ ᄊ߄Ƕკϖ!܌Ңࣁًၰጕᘏڗރᄊᐒޑރ ᄊკǴӚᅿރᄊޑᇥܴӵΠǺ!
ރᄊ 1Ǻًၰጕᘏڗރᄊᐒޑ߃ۈރ ᄊǴԜਔۘ҂Ԗёૈޑًၰጕቻว
Ǵ Gin=Gd1 ਔǴ߄ҢԖᜪ՟ًၰጕ
ቻวǴԜਔރᄊᐒΕރᄊ 2Ƕ!
ރᄊ 2Ǻ Gin=Gd1 ਔǴΠঁރᄊ (Next State)ϝࣁރᄊ 2ǴԶ Gin=Gd2ਔǴ ރᄊᐒΕރᄊ 3Ǵց߾ރᄊᐒӣډރ ᄊ!1Ƕ!
ރᄊ 3Ǻ Gin=Gd2ਔǴΠރᄊϝࣁ ރᄊ 3ǴԶ Gin=Gd3ਔǴރᄊᐒΕރᄊ 4Ǵց߾ރᄊᐒӣډރᄊ!1Ƕރᄊᐒখ
Εރᄊ 3 ਔǴ߄Ң PAҞՏёૈډၲ
კΟ!ޑ M1ᆶ M2ϐ໔ǴԜՏࣁًၰጕ ᆶӦय़ௗޑѰᜐጔǶԜਔ PAޑԪ໘ॶ
εܭ PBǶ!
ރᄊ 4Ǻ Gin=Gd3ਔǴΠރᄊϝࣁ ރᄊ 4ǴԶ Gin=Gd4ਔǴރᄊᐒΕރᄊ 5Ǵց߾ރᄊᐒӣډރᄊ 1Ƕ!ރᄊᐒ খΕރᄊ 4 ਔǴ߄Ң PAՏёૈѓ౽ډ კΟޑ M2ᆶ M3ϐ໔ǴԜਔ PAޑԪ໘ॶ
ᆶ PB/࣬߈Ƕ!
ރᄊ 5Ǻ Gin=Gd4ਔǴΠރᄊϝࣁ ރᄊ 5ǴԶ Gin=Gd1ਔǴރᄊᐒΕރᄊ 6Ǵց߾ރᄊᐒӣډރᄊ 1Ƕ!ރᄊᐒ খΕރᄊ 5 ਔǴ߄Ң PAՏёૈѓ౽ډ კΟޑ M3ᆶ M4ϐ໔ǴԜՏࣁًၰጕᆶ Ӧय़ௗޑѓᜐጔǶԜਔ PAޑԪ໘ॶλ ܭ PBǶ!
ރᄊ 6ǺރᄊᐒΕރᄊ 6 ߄Ңว
ΑًၰጕޑቻǴ٠ܭΠঁ Gin Ε ਔǴރᄊᐒӣډރᄊ!1Ƕ಄ӝًၰጕᘏ ڗރᄊᐒୀෳځёૈࢂًၰጕޑᗺᆀࣁ!
PLMEǶ!
m m( )
d ratio w Nu !!!!!!!!!(3)!
ځύ dm ߄Ң PAPB ϐ໔ޑຯᚆ-!
PA ০ࣁ(N, M)ਔǴPB ০ࣁ(N, M-dm) Ratio ࣁঁதኧǴλܭ 2Ǵw Nm( )߄Ң
ቹܭ N ০ޑًၰጕቨࡋǴёҗቹीᆉ ԶளǶʳ
)Ο*ኳጋᡄᒠፕ!
җރᄊᐒёаפډёૈޑًၰጕՏ
٠ीᆉځቨࡋǴԶճҔ(2)ϐቹБԄΨ ёीᆉًၰጕϐቨࡋǴԜٿᅿीᆉ่݀ᔈ ၀ा࣬߈ǶќѦǴރᄊᐒӧӕӈύୀෳ
ډޑٿঁًၰጕቻǴځ໔ޑቨࡋऩΨૈ
಄ӝቹीᆉޑቨࡋǴٗΨ׳ૈ߄Ң၀ٿ
ঁًၰጕቻϩձࣁѰϷѓًၰጕޑ
ҽǶӧԜǴճҔኳጋᡄᒠޑБԄٰ๏ϒୀ
ෳډޑًၰጕቻঁ࣬՟ࡋޑୖԵॶǴ Ҕаᘠନ٤ᆶًၰጕቻ࣬՟ޑᚇૻǶ!
ӵკϤ܌ҢǴWicLM߄Ңރᄊᐒӧಃ n ӈ܌ୀෳډࢌঁًၰጕޑቨࡋǴWiLM߄
ҢճҔ(2)ीᆉளډϐًၰጕӧಃ n ӈ܌
ޑߏࡋǴu1n ߄Ңٿޣϐ࣬՟ำࡋǶӕ
ǴკΎ܌Ң-!WicL߄Ңރᄊᐒӧಃ n ӈ
܌ୀෳٿঁًၰጕቻᗺϐ໔ޑຯᚆǴWiL
߄ҢճҔ(2)ीᆉளډϐًၰӧಃ n ӈ ޑቨࡋǴu2n߄Ңٿޣϐ࣬՟ำࡋǶ!
ճҔԜБݤפрӚӈύ u1n+u2n ॶന εޣǴຎځࣁӚӈϐനԖёૈޑًၰቻǶ!
Ѥǵᄊਠ҅ᆶଓᙫᄽᆉݤ!
ԜҽϟಏӵՖճҔᄊਠ҅ᆶଓᙫ ᄽᆉݤٰ෧λᇤৡϷуೲୀෳǶ!
)*!ᄊਠ҅ᄽᆉݤ!
а൳ՖቹीᆉًၰቨࡋਔǴऩคݤ ڗள҅ዴޑ௹فǴஒԖࡐεᇤৡǶ!ฅ ԶǴӢࣁၡय़٠ߚֹӄѳڶаϷً፶Չ
ਁǴջ٬ޕၰྣ࣬ᐒӼးޑ௹فǴځ ϝᒿً፶ޑՉԶׯᡂǴӢԜԋ
ीᆉޑᇤৡǶҁፕЎ٬Ҕᄊਠ҅ޑБݤ аᒿਔளډ҅ዴޑ௹فǴ෧ϿᇤৡǶ!
ًၰጕࣁٿచѳՉጕǴӦय़ٿచѳ ՉጕޑҬᗺӧคज़ᇻೀǴࣁ ZiǶӢ ԜӧቹႽύǴٿًၰጕޑۯ՜ጕޑҬᗺ ᆀࣁѨᗺ VP(uvp, vvp)Ǵ၀ᗺջё߄Ңค ज़ᇻޑӦय़ޑᗺ Zi ޑቹǶҗ(1)ёள
͉ǵZi Ϸ vvp ޑᜢ߯ӵ(4)܌ҢǴऩஒຯᚆ Zi ௗ߈คज़ᇻжΕ(4)Ǵҗ(5)ёޕ͉ӵ(6)
܌ҢǶ
1 1
tan vvp/ tan Zi/
͉>͘03. ͓ i (4)
lim tan 1 /
i
Z Zi
of! i ͘03 (5)
tan1 vvp/
͉> . ͓ (6)
೯த͉ϷჴሞًၰቨࡋA B1 1ޑᡂໆ όϼεǴӢԜًၰୀෳำׇӧ໒ۈӃ аسۓϐ͉!ک!A B1 1ٰीᆉǴӧֹԋ
ಃԛًၰୀෳϐࡕǴ߾а܌ளډϐًၰ
ၗૻीᆉѨᗺǴ٠ीᆉ͉аϷճҔୀෳ
ϐѳ֡a b1 1ٰीᆉჴሞًၰቨࡋA B1 1ǴӢ Ԝջ٬໒ۈόޕჴሞًၰቨࡋǴΨёҗ ԜٰளޕჴሞًၰቨࡋǶӵԜϸᙟਠ҅ё
٬ୀෳ׳ࣁྗዴǶ!
)Β*ٿᅿୀෳኳԄ!
ًၰጕᘏڗޑБԄϩࣁൂኳԄᆶଓ ᙫኳԄǶӧൂኳԄਔǴཛྷ൨ጄൎࣁ
ቹႽǴԜਔճҔኳጋᡄᒠޑБԄ൨פന࣬
՟ܭًၰጕޑቻǴפډࡕ߾җᄊ ਠ҅ीᆉ҅ዴޑ௹فϷًၰቨࡋᆶًၰ ጕቨࡋǴӵԜӆख़ཥ൨פԛǴӢԜளډ ޑ่݀ஒ׳ࣁ҅ዴǶӢࣁਠ҅فࡋϷًၰ ቨࡋሡाٿచًၰޑၗૻǴӧԜჄϩБ
ҽጄൎޑًၰ)ऊ 31n ϣ*ࣁਠ҅ϐ ҔǶӢԜӧൂኳԄਔǴБௗ߈ྣ࣬ᐒ ޑҽጄൎϝሡԖٿచًၰጕޑၗૻǶ!
ӢࣁԖ٤ًၰጕࢂጕǴЪԖਔًၰ ጕጨǴӢԜǴפډޑًၰጕቻᗺ ٠όૈж߄ӄୱޑًၰǴۘሡೱጕѰᜐ ϷѓᜐޑًၰጕቻᗺǴωૈඔॊֹޑ
ًၰǴҁЎ٬Ҕ B-spline ٰϣකًၰጕޑ
ቻ ᗺ Ǵ а ள ډ ֹ ޑ ً ၰ ጕ Ƕ Cubic B-splineࢂѳྖԔጕ(smooth curve)ǴԶ ЪԖೱុޑΒ໘Ꮴኧ!\28^\29^Ƕёаֹ
ඔॊӚᅿόӕޑًၰǶ!
ֹԋൂኳԄޑୀෳϐࡕǴௗΠٰ
߾ΕଓᙫኳԄǶӢࣁӧೱុޑቹႽύǴ
ًၰጕޑᡂϯ೯தࡐλǴӢԜଓᙫኳԄ ਔǴཛྷ൨ًၰጕቻޑጄൎ߾ज़ۓӧ
܌פډޑጄൎߕ߈ǴӵԜёуזୀෳೲ ࡋϷ෧λᚇૻǶӧଓᙫኳԄΠǴऩפډޑ
ًၰጕቻᆶीᆉޑቻ࣬՟ࡋλܭۓ ޑᖏࣚॶਔǴ߾ӆӣډൂኳԄޑୀෳ
БԄǶ!
ϖǵჴᡍ่݀!
Ԝ ࣴ ز ܌ Ҕ ޑ ྣ ࣬ ᐒ ࢂ Hitachi KP-F3 Ǵ Ѭ ޑ ঁ Ⴝ ન ޑ ε λ ࢂ 7.4(H)u7.4(V) ȝmǴှࡋࣁ 644u493Ƕ
ྣ࣬ᐒޑӼးଯࡋࣁ 1.32 mǶ!!!
!
)*!ًၰጕᘏڗ่݀!
კΖ܌Ңࣁ 20m ϐϣًၰጕቻᗺ ޑᘏڗǴځύٿᜐًၰጕӕਔӸӧޑᗺω
ᒧڗǴკΖ(a)߄ҢၰၡޑᘏڗǴ კΖ(b)߄ҢύጕࣁᚈጕਔޑᘏڗǴᒧ
ًၰύޑၨ္य़ޑጕǶҗკё࣮рᘏڗϐ ᗺεҽࣁ҅ዴǶځҗኳጋᡄᒠޑ࣬՟
܄КၨϐࡕǴᒧځύΒӈǴԜёளډѤ
ঁᗺǴL1ǵL2ǵ L3ǵ L4Ǵӵკΐ܌ҢǴ ۯ՜L L1 3-!L L2 4ٿచޔጕǴځҬᗺࣁ
ѨᗺǴҗ(3)ёள͉ǴӕǴL1ᆶ L2ϐຯ ᚆࣁቹႽύϐًၰቨࡋǴӆаԄ(2)ёаள ډШࣚ০ϐًၰቨࡋǴӵԜਠ҅ёаள ډ҅ዴޑفࡋϷًၰቨࡋǶ!
)Β*!ًၰୀෳ่݀!!!
კΜࣁًၰୀෳ่݀ǴҗკύёޕǴѓБ
ًၰጕޑᇻᆄ٠คًၰጕၗૻǴԶѰБ ԖǴӢԜճҔًၰቨࡋၗૻёаڗளѓБ
࣬ჹՏޑًၰጕǶ
!
Ϥǵ่ፕ!
! ًၰୀෳسёаࣁᇶշᎯᎭߥ
ً፶ՉᎭӧًၰϣǴଷᎯᎭ໒ًಕΑ܈
ޣόλЈୃᚆًၰύጕǴ߾Ԝسёౢғ
ߞဦගᒬᎯᎭޣǴаቚуՉًӼӄǶ!
ًၰୀෳ่݀தڙډምᛖނጨޑ ቹႽԶԖᒱᇤǶԾًޑࣴزሡԖًၰୀ
ෳٰ،ۓً፶ၡጕǴϷምᛖނୀෳٰ
ղᘐব٤ӦБԖምᛖނቹៜՉӼӄǶฅ ԶǴѝԖًၰϣޑምᛖނωࢂձाݙཀ ޑǴӢԜምᛖނᆶًၰޑၗૻࣣѸڗ ளǶฅԶምᛖނჹًၰޑጨததቹៜً
ၰୀෳޑ҅ዴ܄ǴӢԜǴًၰୀෳޑঁ
ख़ᗺࢂाૈլܺጨݩǶҁፕЎගٮ
ঁᛙ଼܄ޑᄽᆉݤǴջ٬ҽًၰምᛖ ނጨǴϝёளډ҅ዴًၰՏǴ٠Ԗਏ
ှ،ምᛖނጨًၰޑୢᚒǶԜѦǴନΑ
ሡाًၰၗૻٰёᇶշᎯᎭѦǴً፶Չ
ਔǴຼᎁϝԖӭምᛖނϷځѬً፶
ቹៜՉًӼӄǴӢԜǴ҂ٰࣴزБӛஒً
፶ୀෳޑфૈᆶምᛖނୀෳޑфૈӝٳǴ
ၲԋӭфૈޑᎯᎭᇶշسǶ
Acknowledgements
This work was supported by the National Science Council of R.O.C. under Contract No. 96-2218-E-468-006.
ΎǵୖԵЎ!
\2^! J. C. McCall and M. M. Trivedi,
“Video-based lane estimation and tracking for driver assistance: survey, system, and evaluation,” IEEE Trans.
Intell. Transp. Syst., vol. 7, no. 1, pp.20-37, March 2006.
\3^! B. F. Wu, and C. T. Lin, “Real-Time Fuzzy Vehicle Detection Based on Contour Size Similarity,” Int. J. Fuzzy Systems, vol. 7, No. 2, June 2005.
\4^! B. F. Wu, C. T. Lin, and C. J. Chen, “A Fast Lane and Vehicle Detection Approach for Autonomous Vehicles,” in Proc. the 7th IASTED International Conference Signal and Image Processing, Aug., 2005, pp. 305-310.
\5^! B. F. Wu, and C. T. Lin, “A Fuzzy Vehicle Detection Based on Contour Size Similarity,” in Proc. IEEE Intelligent Vehicles Symp., June 2005, pp. 495-500.
\6^! A. Broggi, M. Bertozzi, Lo Guarino, C.
Bianco, and A. Piazzi, “Visual perception of obstacle and vehicles for platooning,” IEEE Trans. Intelligent Transport. Syst., vol. 1, no. 3, pp.
164-176, Sept. 2000.
\7^! M. Bertozzi and A. Broggi, “GOLD: A parallel real-time stereo vision system for generic obstacle and lane detection,”
IEEE Trans. on Image Processing, vol.
7, pp. 62-81, Jan. 1998.
\8^! R. Chapuis, R. Aufrere, and F. Chausse,
“Accurate Road following and
Reconstruction by Computer Vision,”
IEEE Trans. on Intelligent Transportation Systems, vol. 3, Dec.
2002.
\9^! Y. M. Liang, H. R. Tyan, S. L. Chang, H.
Y. M. Liao, and S. W. Chen, “Video Stabilization for a Camcorder Mounted on a Moving Vehicle,” IEEE
Transactions on Vehicular Technology, Vol. 53, No.6, pp.
1636-1648, Nov. 2004.
\:^! T. Liu, N. Zheng, H. Cheng, and Z.
Xing, “A novel approach of road recognition based on deformable template and genetic algorithm,” in Proc. IEEE Intelligent Transportation systems, Oct. 2003, pp. 1251-1256.
\21^!B. Fardi and G. Wanielik, “Hough transformation based approach for road border detection in infrared images,” in Proc. IEEE Intelligent Vehicles Symp., Parma, Italy, June 2004, pp. 549-554.
\22^!B. F. Wu, and C. T. Lin, “Robust Image Measurement and Analysis Based on Perspective Transformations,” in Proc.
IEEE Syst., Man, Cybern. Symp., Oct.
2006, pp.2390-2395.
\23^!T.N. Schoepflin and D.J. Dailey,
“Dynamic Camera Calibration of Roadside Traffic Management Cameras for Vehicle Speed Estimation,” IEEE Transactions on Intell. Trans. Syst., Vol.
4, No.2, pp. 90-98, June 2003.
\24^!L. L. Wang and W. H. Tsai, “Camera Calibration by Vanishing Lines for 3-D Computer Vision,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol.
13, no. 4, pp. 370-376, April 1991.
\25^!C. Kreucher and S. Lakshmanan,
“LANA: A Lane Extraction Algorithm that Uses Frequency Domain Features,”
IEEE Trans. on Robotics and Automation, vol. 15, April 1999.
\26^!Q. Li, N. Zheng, and H. Cheng,
“Springrobot A Prototype Autonomous Vehicle and Its Algorithms for Lane Detection,” IEEE Transactions on Intell.
Trans. Syst., Vol. 5, No.4, pp.
300-308, Dec. 2004.
\27^!Y. Wang, D. Shen, and E. K. Teoh,
“Lane detection using spline model,”
Pattern Recognition Letters, vol.21 , pp.
677-689, July 2000.
\28^!Y. Wang, E. Teoh, and D. shen, “Lane detection and tracking using B-Snake,”
Image Vis. Comput., vol. 22, no. 4, pp.
269-280, Apr. 2004.
\29^!M. Unser, A. Aldroubi, and M. Eden,
“B-spline signal processing: Part I-Theory,” IEEE Transactions on Signal Processing, Vol. 41, No.2, pp.
821-833, Feb. 1993.
კǺྣ࣬ᐒޑԋႽၸำ
! !
!(a)
! !
(b)
კΒǺྣ࣬ᐒኳࠠޑ൳ՖǶ(a) Y, Z ০
ډ v ০ޑᜢ߯Ƕ(b)!X, Z০
ډ u ০ޑᜢ߯Ƕ
!
! კΟǺቹႽύًၰጕޑቻ
!
! კѤǺӚᅿރᄊΠǴًၰጕᆶ PAǵPBޑ࣬
ჹՏ!
߄ǺӚᅿSTATEޑGdॶ!
!
! კϖǺًၰጕᘏڗރᄊᐒޑރᄊკ!
!
State Gd Conditions Name in Gd Conditions State 1 abs G( d) th1 Gd1
State 2 Gd !th2 Gd2 State 3 abs G( d) th3 Gd3 State 4 Gd !th4 Gd4 State 5 abs G( d) th1 Gd1
߄ 3Ǻރᄊᐒϐރᄊ߄
!
! კϤǺًၰጕᘜឦڄኧ!!
!
! კΎǺًၰᘜឦڄኧ
! (a)
! (b)
კΖǺ!20m ϐϣၗᗺޑᘏڗ!(a)!
ၰၡޑᘏڗ!(b)ύጕࣁᚈጕਔޑᘏڗ!
!
! კΐǺᒧڗԖًၰቻᗺޑ 3 ӈǴаਠ҅
Ҕ!
! კΜǺًၰୀෳ่݀!
QSFTFOU!
TUBUF! OFYU!TUBUF!
Tubuf!1! 1, 1,
0, ,
in d
State if G G Next State
State otherwise
®
¯
! Tubuf!2!
1 2
1, ,
, ,
0, ,
in d
in d
State if G G Next State State if G G
State otherwise
°
®
°
¯
! Tubuf!3!
2 3
2, ,
, ,
0, ,
in d
in d
State if G G Next State State if G G State otherwise
°
®
°
¯
! Tubuf!4!
3 4
3, ,
, ,
0, ,
in d
in d
State if G G Next State State if G G State otherwise
°
®
°
¯
! Tubuf!5!
4 1
4, ,
, ,
0, ,
in d
in d
State if G G Next State State if G G State otherwise
°
®
°
¯
!
Tubuf!6! Next State State 0 !
