. . . "\uD30C\uD2F0\uD074 \uD544\uD130(\uC601\uC5B4: Particle filter)\uB294 \uC2DC\uBBAC\uB808\uC774\uC158\uC5D0 \uAE30\uBC18\uC744 \uB454 \uC608\uCE21\uAE30\uC220\uC758 \uD558\uB098\uB85C \uACC4\uC18D\uC801\uC778 \uBAAC\uD14C\uCE74\uB97C\uB85C \uBC29\uBC95\uC774\uB77C\uACE0\uB3C4 \uD55C\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uB294 \uACC4\uB7C9\uACBD\uC81C\uD559\uC5D0\uC11C \uC911\uC694\uD558\uAC8C \uC4F0\uC778\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uB294 \uBCF4\uD1B5 \uBCA0\uC774\uC988 \uBAA8\uB378\uC744 \uCD94\uC815\uD558\uAE30 \uC704\uD574 \uC0AC\uC6A9\uB41C\uB2E4. \uC774\uB294 \uC7A0\uC7AC\uBCC0\uC218\uAC00 \uB9C8\uB974\uCF54\uD504 \uC5F0\uC1C4\uB85C \uC11C\uB85C \uAD00\uB828\uB418\uC5B4 \uC788\uB294 \uACBD\uC6B0\uB85C \uC740\uB2C9 \uB9C8\uB974\uCF54\uD504 \uBAA8\uB378(HMM)\uACFC \uBE44\uC2B7\uD558\uC9C0\uB9CC \uBCF4\uD1B5 \uB4DC\uB7EC\uB098\uC9C0 \uC54A\uC740 \uBCC0\uC218\uC758 \uC0C1\uD0DC \uACF5\uAC04\uC774 \uC5F0\uC18D\uC801\uC774\uACE0, \uC815\uD655\uD558\uAC8C \uCD94\uC815\uD560 \uC218 \uC788\uC744 \uB9CC\uD07C \uD55C\uC815\uC801\uC774\uC9C0 \uC54A\uB2E4. \uC608\uB97C \uB4E4\uC5B4, \uC120\uD615 \uB3D9\uC801 \uC2DC\uC2A4\uD15C\uC5D0\uC11C\uB294, \uC7A0\uC7AC\uBCC0\uC218\uC758 \uC0C1\uD0DC \uACF5\uAC04\uC774 \uAC00\uC6B0\uC2A4 \uBD84\uD3EC\uC5D0 \uD55C\uC815\uB418\uB294\uB370, \uB530\uB77C\uC11C \uC815\uD655\uD55C \uCD94\uC815\uC774 \uD6A8\uACFC\uC801\uC73C\uB85C \uCE7C\uB9CC \uD544\uD130\uB9CC\uC73C\uB85C \uC774\uB8E8\uC5B4\uC9C8 \uC218 \uC788\uB2E4. HMM, \uADF8\uB9AC\uACE0 \uAD00\uB828\uB41C \uBAA8\uB378\uC758 \uB9E5\uB77D\uC5D0\uC11C \uBCF4\uBA74, \uD544\uD130\uB9C1\uC740 \uC5B4\uB5A4 \uD2B9\uC815 \uC2DC\uAC04\uC5D0 \uC7A0\uC7AC\uBCC0\uC218\uC758 \uBD84\uD3EC\uB97C \uACB0\uC815\uD558\uB418, \uAD00\uCE21 \uAC12\uC740 \uADF8 \uC2DC\uAC04 \uAE4C\uC9C0\uB9CC \uC8FC\uC5B4\uC9C4\uB2E4; \uD30C\uD2F0\uD074 \uD544\uD130\uB77C\uB294 \uC774\uB984\uC744 \uC5BB\uAC8C \uB41C \uAE4C\uB2ED\uC740 \uADFC\uC0AC\uAC12\uC744 (\uC544\uAE4C \uB9D0\uD55C \uC758\uBBF8\uC5D0\uC11C) \"\uD544\uD130\uB9C1\"\uD558\uB294\uB370 \uD55C \uBB34\uB9AC\uC758 (\uB2E4\uB978 \uAC00\uC911\uCE58\uB97C \uAC00\uC9C4 \uBD84\uD3EC\uC758 \uC608) \"\uC785\uC790\"\uB97C \uC0AC\uC6A9\uD558\uAE30 \uB54C\uBB38\uC774\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uB294 \uB9C8\uB974\uCF54\uD504 \uC5F0\uC1C4 \uBAAC\uD14C \uCE74\uB97C\uB85C(MCMC) \uC77C\uAD04\uCC98\uB9AC\uBC95\uC744 \uC73C\uB85C \uC720\uC0AC\uD558\uAC8C \uB9CC\uB4E0 \uAC83\uC73C\uB85C \uB54C\uB85C \uACFC \uC720\uC0AC\uD558\uB2E4. \uC785\uC790 \uD544\uD130\uB97C \uC798 \uB9CC\uB4E4\uBA74 MCMC\uBCF4\uB2E4 \uD6E8\uC52C \uBE60\uB974\uB2E4. \uB54C\uB54C\uB85C \uD655\uC7A5 \uCE7C\uB9CC \uD544\uD130(EKF) \uB610\uB294 \uBB34\uD5A5 \uCE7C\uB9CC \uD544\uD130(UKF) \uB300\uC2E0 \uC0AC\uC6A9\uB41C\uB2E4. EKF\uB098 UKF\uC5D0 \uBE44\uD574 \uC787\uC810\uC740, \uC0D8\uD50C\uC774 \uCDA9\uBD84\uD558\uB2E4\uBA74, \uBC30\uC774\uC9C0\uC5B8 \uCD5C\uC801 \uCD94\uC815\uCE58\uC5D0 \uC811\uADFC\uD558\uBBC0\uB85C EKF\uB098 UKF\uBCF4\uB2E4 \uC815\uD655\uD558\uB2E4. \uADF8\uB7EC\uB098, \uC0D8\uD50C\uC758 \uC218\uAC00 \uCDA9\uBD84\uD558\uC9C0 \uC54A\uB2E4\uBA74 \uBB38\uC81C\uAC00 \uC0DD\uAE38 \uC218 \uC788\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uC640 \uCE7C\uB9CC \uD544\uD130\uB97C \uBCF5\uD569\uD558\uC5EC \uC0AC\uC6A9\uD560 \uC218\uB3C4 \uC788\uB294\uB370, \uC77C\uC885\uC758 \uCE7C\uB9CC \uD544\uD130\uB97C \uC0AC\uC6A9\uD558\uC5EC \uD30C\uD2F0\uD074 \uD544\uD130\uB97C \uC704\uD55C \uBD84\uD3EC\uB97C \uC81C\uC548\uD558\uAC8C \uD558\uB294 \uBC29\uC2DD\uC774\uB2E4."@ko . . . . . . . . . "Sequenzielle Monte-Carlo-Methoden (SMC-Methoden) geh\u00F6ren zur Klasse der stochastischen Verfahren zur Zustandssch\u00E4tzung in einem dynamischen Prozess (z. B. in der mobilen Robotik), dessen Dynamik nur im statistischen Mittel bekannt ist (wesentliche St\u00F6rgr\u00F6\u00DFen) und der nur unvollst\u00E4ndig beobachtet werden kann (Unterteilung in innere, verborgene und \u00E4u\u00DFere, sichtbare Variable). Ein Anwendungsbeispiel ist die genaue und kontinuierlich aktualisierte Bestimmung des Ortes und der Geschwindigkeit eines Objektes aufgrund einer ungenauen und fehlerhaften Messung des Ortes (vgl. Tracking). SMC-Filter sind auch bekannt als Partikel-Filter, sampling importance resampling (SIR), sequential importance sampling (SIS), bootstrap filters, condensation trackers, interacting particle approximations oder survi"@de . . . . . . "Filtr cz\u0105steczkowy (sekwencyjna metoda Monte Carlo, SMC) \u2013 metoda nieliniowej filtracji, polegaj\u0105ca na oszacowaniu rozk\u0142ad\u00F3w prawdopodobie\u0144stwa docelowego przez rozk\u0142ady empiryczne, skupione na zestawie pr\u00F3bek zwanych cz\u0105steczkami. Pr\u00F3bki wyznaczane s\u0105 przez algorytm sekwencyjny, \u0142\u0105cz\u0105cy metody losowania istotnego (ang. importance sampling) z technikami ponownego pr\u00F3bkowania (ang. resampling). Nazw\u0119 filtr cz\u0105steczkowy zaproponowa\u0142 , natomiast sekwencyjn\u0105 metod\u0119 Monte Carlo i , oba terminy u\u017Cywane s\u0105 zamiennie."@pl . . "Les filtres particulaires, aussi connus sous le nom de m\u00E9thodes de Monte-Carlo s\u00E9quentielles, sont des techniques sophistiqu\u00E9es d'estimation de mod\u00E8les fond\u00E9es sur la simulation. Les filtres particulaires sont g\u00E9n\u00E9ralement utilis\u00E9s pour estimer des r\u00E9seaux bay\u00E9siens et constituent des m\u00E9thodes 'en-ligne' analogues aux m\u00E9thodes de Monte-Carlo par cha\u00EEnes de Markov qui elles sont des m\u00E9thodes 'hors-ligne' (donc a posteriori) et souvent similaires aux m\u00E9thodes d'\u00E9chantillonnage pr\u00E9f\u00E9rentiel."@fr . . . . . . . . . "\u041C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440"@ru . . . "Sequenzielle Monte-Carlo-Methoden (SMC-Methoden) geh\u00F6ren zur Klasse der stochastischen Verfahren zur Zustandssch\u00E4tzung in einem dynamischen Prozess (z. B. in der mobilen Robotik), dessen Dynamik nur im statistischen Mittel bekannt ist (wesentliche St\u00F6rgr\u00F6\u00DFen) und der nur unvollst\u00E4ndig beobachtet werden kann (Unterteilung in innere, verborgene und \u00E4u\u00DFere, sichtbare Variable). Ein Anwendungsbeispiel ist die genaue und kontinuierlich aktualisierte Bestimmung des Ortes und der Geschwindigkeit eines Objektes aufgrund einer ungenauen und fehlerhaften Messung des Ortes (vgl. Tracking). SMC-Filter sind auch bekannt als Partikel-Filter, sampling importance resampling (SIR), sequential importance sampling (SIS), bootstrap filters, condensation trackers, interacting particle approximations oder survival of the fittest."@de . "Particle filter"@en . . . . "\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\uFF08\u308A\u3085\u3046\u3057\u30D5\u30A3\u30EB\u30BF\u3001\u82F1: particle filter\uFF09\u3084\u9010\u6B21\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u6CD5 (\u3061\u304F\u3058\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u307B\u3046\u3001\u82F1: sequential Monte Carlo; SMC)\u3068\u306F\u3001\u30B7\u30DF\u30E5\u30EC\u30FC\u30B7\u30E7\u30F3\u306B\u57FA\u3065\u304F\u8907\u96D1\u306A\u30E2\u30C7\u30EB\u306E\u63A8\u5B9A\u6CD5\u3067\u3042\u308B\u30021993\u5E741\u6708\u306B\u5317\u5DDD\u6E90\u56DB\u90CE\u304C\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u30D5\u30A3\u30EB\u30BF\u306E\u540D\u79F0\u3067\u30011993\u5E744\u6708\u306BN.J. Gordon\u3089\u304C\u30D6\u30FC\u30C8\u30B9\u30C8\u30E9\u30C3\u30D7\u30D5\u30A3\u30EB\u30BF\u306E\u540D\u79F0\u3067\u540C\u6642\u671F\u306B\u540C\u3058\u3082\u306E\u3092\u767A\u8868\u3057\u305F\u3002 \u3053\u306E\u624B\u6CD5\u306F\u3075\u3064\u3046\u30D9\u30A4\u30BA\u30E2\u30C7\u30EB\u3092\u63A8\u5B9A\u3059\u308B\u306E\u306B\u7528\u3044\u3089\u308C\u3001\u30D0\u30C3\u30C1\u51E6\u7406\u3067\u3042\u308B\u30DE\u30EB\u30B3\u30D5\u9023\u9396\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u6CD5 (MCMC) \u306E\u9010\u6B21 (\u30AA\u30F3\u30E9\u30A4\u30F3) \u7248\u3067\u3042\u308B\u3002\u307E\u305F\u3053\u306E\u624B\u6CD5\u306F\u6CD5\u306B\u3082\u4F3C\u305F\u3068\u3053\u308D\u304C\u3042\u308B\u3002\u3046\u307E\u304F\u8A2D\u8A08\u3059\u308B\u3068\u3001\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\u306FMCMC\u3088\u308A\u3082\u9AD8\u901F\u3067\u3042\u308B\u3002\u62E1\u5F35\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF\u3084\u7121\u9999\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF (Unscented \u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF) \u306B\u6BD4\u3079\u3066\u3001\u30B5\u30F3\u30D7\u30EB\u70B9\u304C\u5341\u5206\u591A\u304F\u306A\u308B\u3068\u30D9\u30A4\u30BA\u6700\u9069\u63A8\u5B9A\u306B\u8FD1\u4ED8\u304F\u3053\u3068\u304B\u3089\u3088\u308A\u9AD8\u3044\u7CBE\u5EA6\u306E\u89E3\u304C\u5F97\u3089\u308C\u308B\u306E\u3067\u3001\u3053\u308C\u3089\u306E\u4EE3\u308F\u308A\u306B\u7528\u3044\u3089\u308C\u308B\u3053\u3068\u304C\u3042\u308B\u3002\u307E\u305F\u624B\u6CD5\u3092\u7D44\u307F\u5408\u308F\u305B\u3066\u3001\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF\u3092\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\u306E\u63D0\u6848\u5206\u5E03\u3068\u3057\u3066\u4F7F\u3046\u3053\u3068\u3082\u3067\u304D\u308B\u3002"@ja . . . . . . "\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF"@ja . . . . . . "1124331198"^^ . . . . . . . . . . . . . "Sequenzielle Monte-Carlo-Methode"@de . . "Particle filters, or sequential Monte Carlo methods, are a set of Monte Carlo algorithms used to solve filtering problems arising in signal processing and Bayesian statistical inference. The filtering problem consists of estimating the internal states in dynamical systems when partial observations are made and random perturbations are present in the sensors as well as in the dynamical system. The objective is to compute the posterior distributions of the states of a Markov process, given the noisy and partial observations. The term \"particle filters\" was first coined in 1996 by Del Moral about mean-field interacting particle methods used in fluid mechanics since the beginning of the 1960s. The term \"Sequential Monte Carlo\" was coined by Liu and Chen in 1998."@en . . . "Filtre particulaire"@fr . "\u041C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0301\u0447\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440 (\u041C\u0427\u0424, \u0430\u043D\u0433\u043B. particle filter \u2014 \u00AB\u0444\u0438\u043B\u044C\u0442\u0440 \u0447\u0430\u0441\u0442\u0438\u0446\u00BB, \u00AB\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440\u00BB, \u00AB\u043A\u043E\u0440\u043F\u0443\u0441\u043A\u0443\u043B\u044F\u0440\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440\u00BB) \u2014 \u043F\u043E\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u0442\u0435\u043B\u044C\u043D\u044B\u0439 \u043C\u0435\u0442\u043E\u0434 \u041C\u043E\u043D\u0442\u0435-\u041A\u0430\u0440\u043B\u043E \u2014 \u0440\u0435\u043A\u0443\u0440\u0441\u0438\u0432\u043D\u044B\u0439 \u0430\u043B\u0433\u043E\u0440\u0438\u0442\u043C \u0434\u043B\u044F \u0447\u0438\u0441\u043B\u0435\u043D\u043D\u043E\u0433\u043E \u0440\u0435\u0448\u0435\u043D\u0438\u044F \u043F\u0440\u043E\u0431\u043B\u0435\u043C \u043E\u0446\u0435\u043D\u0438\u0432\u0430\u043D\u0438\u044F (\u0444\u0438\u043B\u044C\u0442\u0440\u0430\u0446\u0438\u0438, \u0441\u0433\u043B\u0430\u0436\u0438\u0432\u0430\u043D\u0438\u044F), \u043E\u0441\u043E\u0431\u0435\u043D\u043D\u043E \u0434\u043B\u044F \u043D\u0435\u043B\u0438\u043D\u0435\u0439\u043D\u044B\u0445 \u0438 \u043D\u0435-\u0433\u0430\u0443\u0441\u0441\u043E\u0432\u0441\u043A\u0438\u0445 \u0441\u043B\u0443\u0447\u0430\u0435\u0432. \u0421\u043E \u0432\u0440\u0435\u043C\u0435\u043D\u0438 \u043E\u043F\u0438\u0441\u0430\u043D\u0438\u044F \u0432 1993 \u0433\u043E\u0434\u0443 \u041D. \u0413\u043E\u0440\u0434\u043E\u043D\u043E\u043C, \u0414. \u0421\u0430\u043B\u043C\u043E\u043D\u0434\u043E\u043C \u0438 \u0410. \u0421\u043C\u0438\u0442\u043E\u043C \u0438\u0441\u043F\u043E\u043B\u044C\u0437\u0443\u0435\u0442\u0441\u044F \u0432 \u0440\u0430\u0437\u043B\u0438\u0447\u043D\u044B\u0445 \u043E\u0431\u043B\u0430\u0441\u0442\u044F\u0445 \u2014 \u043D\u0430\u0432\u0438\u0433\u0430\u0446\u0438\u0438, \u0440\u043E\u0431\u043E\u0442\u043E\u0442\u0435\u0445\u043D\u0438\u043A\u0435, \u043A\u043E\u043C\u043F\u044C\u044E\u0442\u0435\u0440\u043D\u043E\u043C \u0437\u0440\u0435\u043D\u0438\u0438. \u0422\u0435\u0440\u043C\u0438\u043D \u00ABparticle filter\u00BB \u0431\u044B\u043B \u0434\u0430\u043D \u0414\u0435\u043B \u041C\u043E\u0440\u0430\u043B\u043E\u043C \u0432 1996 \u0433\u043E\u0434\u0443, \u0430 \u00ABsequential Monte Carlo\u00BB \u2014 \u041B\u044E (Liu) \u0438 \u0427\u0435\u043D\u043E\u043C (Chen) \u0432 1998."@ru . . . . . . "\u7C92\u5B50\u6EE4\u6CE2\u5668\uFF08\u82F1\u8A9E\uFF1Aparticle filter\uFF09\u662F\u4E00\u79CD\u4F7F\u7528\u8499\u7279\u5361\u7F57\u65B9\u6CD5\u7684\u9012\u5F52\u6EE4\u6CE2\u5668\uFF0C\u900F\u8FC7\u4E00\u7EC4\u5177\u6709\u6743\u91CD\u7684\u968F\u673A\u6837\u672C\uFF08\u7C92\u5B50\uFF09\u4F86\u8868\u793A\u96A8\u6A5F\u4E8B\u4EF6\u7684\u5F8C\u9A57\u6A5F\u7387\uFF0C\u5F9E\u542B\u6709\u96DC\u8A0A\u6216\u4E0D\u5B8C\u6574\u7684\u89C0\u6E2C\u5E8F\u5217\uFF0C\u4F30\u8A08\u51FA\u52D5\u614B\u7CFB\u7D71\u7684\u72C0\u614B\uFF0C\u7C92\u5B50\u6FFE\u6CE2\u5668\u53EF\u4EE5\u904B\u7528\u5728\u4EFB\u4F55\u72C0\u614B\u7A7A\u9593\u7684\u6A21\u578B\u4E0A\u3002\u7C92\u5B50\u6FFE\u6CE2\u5668\u662F\u5361\u723E\u66FC\u6FFE\u6CE2\u5668\u7684\u4E00\u822C\u5316\u65B9\u6CD5\uFF0C\u5361\u723E\u66FC\u6FFE\u6CE2\u5668\u5EFA\u7ACB\u5728\u7DDA\u6027\u7684\u72C0\u614B\u7A7A\u9593\u548C\u9AD8\u65AF\u5206\u5E03\u7684\u96DC\u8A0A\u4E0A\uFF1B\u800C\u7C92\u5B50\u6FFE\u6CE2\u5668\u7684\u72C0\u614B\u7A7A\u9593\u6A21\u578B\u53EF\u4EE5\u662F\u975E\u7DDA\u6027\uFF0C\u4E14\u96DC\u8A0A\u5206\u5E03\u53EF\u4EE5\u662F\u4EFB\u4F55\u578B\u5F0F\u3002"@zh . . . . "El \"filtro de part\u00EDculas\" es un m\u00E9todo empleado para estimar el estado de un sistema que cambia a lo largo del tiempo. M\u00E1s concretamente, es un m\u00E9todo de Montecarlo (secuencial) usado com\u00FAnmente en visi\u00F3n artificial para el seguimiento de objetos en secuencias de im\u00E1genes. Fue propuesto en 1993 por , y como filtro bootstrap para implementar filtros bayesianos recursivos. B\u00E1sicamente, el filtro de part\u00EDculas se compone de un conjunto de muestras (las part\u00EDculas) y unos valores, o pesos, asociados a cada una de esas muestras. Las part\u00EDculas son estados posibles del proceso, que se pueden representar como puntos en el espacio de estados de dicho proceso. Posee cuatro etapas principales: \n* Inicializaci\u00F3n. \n* Actualizaci\u00F3n. \n* Estimaci\u00F3n. \n* Predicci\u00F3n. Para realizar el seguimiento de un objeto sobre una secuencia de im\u00E1genes, el filtro de part\u00EDculas \"lanza\" al azar un conjunto de puntos sobre la imagen (etapa de inicializaci\u00F3n, se crea un conjunto de part\u00EDculas con un estado aleatorio), realizando c\u00E1lculos se le asignar\u00E1 un valor, o valores, a cada uno de esos puntos (etapa de actualizaci\u00F3n). A partir de estos valores, se crear\u00E1 un nuevo conjunto de puntos que reemplazar\u00E1 al anterior. Esta elecci\u00F3n tambi\u00E9n ser\u00E1 al azar, pero los valores que se han adjudicado a cada uno de los puntos provocar\u00E1n que sea m\u00E1s probable de elegir aquellos puntos que hayan capturado al objeto sobre el que quiere realizar el seguimiento (etapa de estimaci\u00F3n). Una vez que se crea el nuevo conjunto de puntos, se realiza una leve modificaci\u00F3n al estado (posici\u00F3n) de cada uno de ellos, con el fin de estimar el estado del objeto en el instante siguiente (etapa de predicci\u00F3n). Al terminar la etapa de predicci\u00F3n, se obtiene un nuevo conjunto de puntos al que se le vuelve a aplicar la etapa de actualizaci\u00F3n, repiti\u00E9ndose este bucle hasta que termine la secuencia o desaparezca el objeto, caso en el cual se volver\u00EDa a la etapa de inicializaci\u00F3n."@es . . . "El \"filtro de part\u00EDculas\" es un m\u00E9todo empleado para estimar el estado de un sistema que cambia a lo largo del tiempo. M\u00E1s concretamente, es un m\u00E9todo de Montecarlo (secuencial) usado com\u00FAnmente en visi\u00F3n artificial para el seguimiento de objetos en secuencias de im\u00E1genes. Posee cuatro etapas principales: \n* Inicializaci\u00F3n. \n* Actualizaci\u00F3n. \n* Estimaci\u00F3n. \n* Predicci\u00F3n."@es . "Filtr cz\u0105steczkowy"@pl . . . . . . . . . . . . . . . . . . . . "\uD30C\uD2F0\uD074 \uD544\uD130"@ko . . . . . . . . . "Filtro de part\u00EDculas"@es . . . "93192"^^ . . "1396948"^^ . . . . . . . "Particle filters, or sequential Monte Carlo methods, are a set of Monte Carlo algorithms used to solve filtering problems arising in signal processing and Bayesian statistical inference. The filtering problem consists of estimating the internal states in dynamical systems when partial observations are made and random perturbations are present in the sensors as well as in the dynamical system. The objective is to compute the posterior distributions of the states of a Markov process, given the noisy and partial observations. The term \"particle filters\" was first coined in 1996 by Del Moral about mean-field interacting particle methods used in fluid mechanics since the beginning of the 1960s. The term \"Sequential Monte Carlo\" was coined by Liu and Chen in 1998. Particle filtering uses a set of particles (also called samples) to represent the posterior distribution of a stochastic process given the noisy and/or partial observations. The state-space model can be nonlinear and the initial state and noise distributions can take any form required. Particle filter techniques provide a well-established methodology for generating samples from the required distribution without requiring assumptions about the state-space model or the state distributions. However, these methods do not perform well when applied to very high-dimensional systems. Particle filters update their prediction in an approximate (statistical) manner. The samples from the distribution are represented by a set of particles; each particle has a likelihood weight assigned to it that represents the probability of that particle being sampled from the probability density function. Weight disparity leading to weight collapse is a common issue encountered in these filtering algorithms, however, it can be mitigated by including a resampling step before the weights become uneven. Several adaptive resampling criteria can be used including the variance of the weights and the relative entropy concerning the uniform distribution. In the resampling step, the particles with negligible weights are replaced by the new particles in the proximity of the particles with higher weights. From the statistical and probabilistic point of view, particle filters may be interpreted as mean-field particle interpretations of Feynman-Kac probability measures. These particle integration techniques were developed in molecular chemistry and computational physics by Theodore E. Harris and Herman Kahn in 1951, Marshall N. Rosenbluth and Arianna W. Rosenbluth in 1955, and more recently by Jack H. Hetherington in 1984. In computational physics, these Feynman-Kac type path particle integration methods are also used in Quantum Monte Carlo, and more specifically Diffusion Monte Carlo methods. Feynman-Kac interacting particle methods are also strongly related to mutation-selection genetic algorithms currently used in evolutionary computing to solve complex optimization problems. The particle filter methodology is used to solve Hidden Markov Model (HMM) and nonlinear filtering problems. With the notable exception of linear-Gaussian signal-observation models (Kalman filter) or wider classes of models (Benes filter), Mireille Chaleyat-Maurel and Dominique Michel proved in 1984 that the sequence of posterior distributions of the random states of a signal, given the observations (a.k.a. optimal filter), has no finite recursion. Various other numerical methods based on fixed grid approximations, Markov Chain Monte Carlo techniques, conventional linearization, extended Kalman filters, or determining the best linear system (in the expected cost-error sense) are unable to cope with large-scale systems, unstable processes, or when the nonlinearities are not sufficiently smooth. Particle filters and Feynman-Kac particle methodologies find application in signal and image processing, Bayesian inference, machine learning, risk analysis and rare event sampling, engineering and robotics, artificial intelligence, bioinformatics, phylogenetics, computational science, economics and mathematical finance, molecular chemistry, computational physics, pharmacokinetics, and other fields."@en . . . . "\u7C92\u5B50\u6FFE\u6CE2\u5668"@zh . . . . . "\u7C92\u5B50\u6EE4\u6CE2\u5668\uFF08\u82F1\u8A9E\uFF1Aparticle filter\uFF09\u662F\u4E00\u79CD\u4F7F\u7528\u8499\u7279\u5361\u7F57\u65B9\u6CD5\u7684\u9012\u5F52\u6EE4\u6CE2\u5668\uFF0C\u900F\u8FC7\u4E00\u7EC4\u5177\u6709\u6743\u91CD\u7684\u968F\u673A\u6837\u672C\uFF08\u7C92\u5B50\uFF09\u4F86\u8868\u793A\u96A8\u6A5F\u4E8B\u4EF6\u7684\u5F8C\u9A57\u6A5F\u7387\uFF0C\u5F9E\u542B\u6709\u96DC\u8A0A\u6216\u4E0D\u5B8C\u6574\u7684\u89C0\u6E2C\u5E8F\u5217\uFF0C\u4F30\u8A08\u51FA\u52D5\u614B\u7CFB\u7D71\u7684\u72C0\u614B\uFF0C\u7C92\u5B50\u6FFE\u6CE2\u5668\u53EF\u4EE5\u904B\u7528\u5728\u4EFB\u4F55\u72C0\u614B\u7A7A\u9593\u7684\u6A21\u578B\u4E0A\u3002\u7C92\u5B50\u6FFE\u6CE2\u5668\u662F\u5361\u723E\u66FC\u6FFE\u6CE2\u5668\u7684\u4E00\u822C\u5316\u65B9\u6CD5\uFF0C\u5361\u723E\u66FC\u6FFE\u6CE2\u5668\u5EFA\u7ACB\u5728\u7DDA\u6027\u7684\u72C0\u614B\u7A7A\u9593\u548C\u9AD8\u65AF\u5206\u5E03\u7684\u96DC\u8A0A\u4E0A\uFF1B\u800C\u7C92\u5B50\u6FFE\u6CE2\u5668\u7684\u72C0\u614B\u7A7A\u9593\u6A21\u578B\u53EF\u4EE5\u662F\u975E\u7DDA\u6027\uFF0C\u4E14\u96DC\u8A0A\u5206\u5E03\u53EF\u4EE5\u662F\u4EFB\u4F55\u578B\u5F0F\u3002"@zh . . . . . . . . . . . . . . . . . . . . "\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\uFF08\u308A\u3085\u3046\u3057\u30D5\u30A3\u30EB\u30BF\u3001\u82F1: particle filter\uFF09\u3084\u9010\u6B21\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u6CD5 (\u3061\u304F\u3058\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u307B\u3046\u3001\u82F1: sequential Monte Carlo; SMC)\u3068\u306F\u3001\u30B7\u30DF\u30E5\u30EC\u30FC\u30B7\u30E7\u30F3\u306B\u57FA\u3065\u304F\u8907\u96D1\u306A\u30E2\u30C7\u30EB\u306E\u63A8\u5B9A\u6CD5\u3067\u3042\u308B\u30021993\u5E741\u6708\u306B\u5317\u5DDD\u6E90\u56DB\u90CE\u304C\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u30D5\u30A3\u30EB\u30BF\u306E\u540D\u79F0\u3067\u30011993\u5E744\u6708\u306BN.J. Gordon\u3089\u304C\u30D6\u30FC\u30C8\u30B9\u30C8\u30E9\u30C3\u30D7\u30D5\u30A3\u30EB\u30BF\u306E\u540D\u79F0\u3067\u540C\u6642\u671F\u306B\u540C\u3058\u3082\u306E\u3092\u767A\u8868\u3057\u305F\u3002 \u3053\u306E\u624B\u6CD5\u306F\u3075\u3064\u3046\u30D9\u30A4\u30BA\u30E2\u30C7\u30EB\u3092\u63A8\u5B9A\u3059\u308B\u306E\u306B\u7528\u3044\u3089\u308C\u3001\u30D0\u30C3\u30C1\u51E6\u7406\u3067\u3042\u308B\u30DE\u30EB\u30B3\u30D5\u9023\u9396\u30E2\u30F3\u30C6\u30AB\u30EB\u30ED\u6CD5 (MCMC) \u306E\u9010\u6B21 (\u30AA\u30F3\u30E9\u30A4\u30F3) \u7248\u3067\u3042\u308B\u3002\u307E\u305F\u3053\u306E\u624B\u6CD5\u306F\u6CD5\u306B\u3082\u4F3C\u305F\u3068\u3053\u308D\u304C\u3042\u308B\u3002\u3046\u307E\u304F\u8A2D\u8A08\u3059\u308B\u3068\u3001\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\u306FMCMC\u3088\u308A\u3082\u9AD8\u901F\u3067\u3042\u308B\u3002\u62E1\u5F35\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF\u3084\u7121\u9999\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF (Unscented \u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF) \u306B\u6BD4\u3079\u3066\u3001\u30B5\u30F3\u30D7\u30EB\u70B9\u304C\u5341\u5206\u591A\u304F\u306A\u308B\u3068\u30D9\u30A4\u30BA\u6700\u9069\u63A8\u5B9A\u306B\u8FD1\u4ED8\u304F\u3053\u3068\u304B\u3089\u3088\u308A\u9AD8\u3044\u7CBE\u5EA6\u306E\u89E3\u304C\u5F97\u3089\u308C\u308B\u306E\u3067\u3001\u3053\u308C\u3089\u306E\u4EE3\u308F\u308A\u306B\u7528\u3044\u3089\u308C\u308B\u3053\u3068\u304C\u3042\u308B\u3002\u307E\u305F\u624B\u6CD5\u3092\u7D44\u307F\u5408\u308F\u305B\u3066\u3001\u30AB\u30EB\u30DE\u30F3\u30D5\u30A3\u30EB\u30BF\u3092\u7C92\u5B50\u30D5\u30A3\u30EB\u30BF\u306E\u63D0\u6848\u5206\u5E03\u3068\u3057\u3066\u4F7F\u3046\u3053\u3068\u3082\u3067\u304D\u308B\u3002"@ja . . . . . . . "Filtr cz\u0105steczkowy (sekwencyjna metoda Monte Carlo, SMC) \u2013 metoda nieliniowej filtracji, polegaj\u0105ca na oszacowaniu rozk\u0142ad\u00F3w prawdopodobie\u0144stwa docelowego przez rozk\u0142ady empiryczne, skupione na zestawie pr\u00F3bek zwanych cz\u0105steczkami. Pr\u00F3bki wyznaczane s\u0105 przez algorytm sekwencyjny, \u0142\u0105cz\u0105cy metody losowania istotnego (ang. importance sampling) z technikami ponownego pr\u00F3bkowania (ang. resampling). Nazw\u0119 filtr cz\u0105steczkowy zaproponowa\u0142 , natomiast sekwencyjn\u0105 metod\u0119 Monte Carlo i , oba terminy u\u017Cywane s\u0105 zamiennie."@pl . . . . . . . . . . "\u041C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0301\u0447\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440 (\u041C\u0427\u0424, \u0430\u043D\u0433\u043B. particle filter \u2014 \u00AB\u0444\u0438\u043B\u044C\u0442\u0440 \u0447\u0430\u0441\u0442\u0438\u0446\u00BB, \u00AB\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440\u00BB, \u00AB\u043A\u043E\u0440\u043F\u0443\u0441\u043A\u0443\u043B\u044F\u0440\u043D\u044B\u0439 \u0444\u0438\u043B\u044C\u0442\u0440\u00BB) \u2014 \u043F\u043E\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u0442\u0435\u043B\u044C\u043D\u044B\u0439 \u043C\u0435\u0442\u043E\u0434 \u041C\u043E\u043D\u0442\u0435-\u041A\u0430\u0440\u043B\u043E \u2014 \u0440\u0435\u043A\u0443\u0440\u0441\u0438\u0432\u043D\u044B\u0439 \u0430\u043B\u0433\u043E\u0440\u0438\u0442\u043C \u0434\u043B\u044F \u0447\u0438\u0441\u043B\u0435\u043D\u043D\u043E\u0433\u043E \u0440\u0435\u0448\u0435\u043D\u0438\u044F \u043F\u0440\u043E\u0431\u043B\u0435\u043C \u043E\u0446\u0435\u043D\u0438\u0432\u0430\u043D\u0438\u044F (\u0444\u0438\u043B\u044C\u0442\u0440\u0430\u0446\u0438\u0438, \u0441\u0433\u043B\u0430\u0436\u0438\u0432\u0430\u043D\u0438\u044F), \u043E\u0441\u043E\u0431\u0435\u043D\u043D\u043E \u0434\u043B\u044F \u043D\u0435\u043B\u0438\u043D\u0435\u0439\u043D\u044B\u0445 \u0438 \u043D\u0435-\u0433\u0430\u0443\u0441\u0441\u043E\u0432\u0441\u043A\u0438\u0445 \u0441\u043B\u0443\u0447\u0430\u0435\u0432. \u0421\u043E \u0432\u0440\u0435\u043C\u0435\u043D\u0438 \u043E\u043F\u0438\u0441\u0430\u043D\u0438\u044F \u0432 1993 \u0433\u043E\u0434\u0443 \u041D. \u0413\u043E\u0440\u0434\u043E\u043D\u043E\u043C, \u0414. \u0421\u0430\u043B\u043C\u043E\u043D\u0434\u043E\u043C \u0438 \u0410. \u0421\u043C\u0438\u0442\u043E\u043C \u0438\u0441\u043F\u043E\u043B\u044C\u0437\u0443\u0435\u0442\u0441\u044F \u0432 \u0440\u0430\u0437\u043B\u0438\u0447\u043D\u044B\u0445 \u043E\u0431\u043B\u0430\u0441\u0442\u044F\u0445 \u2014 \u043D\u0430\u0432\u0438\u0433\u0430\u0446\u0438\u0438, \u0440\u043E\u0431\u043E\u0442\u043E\u0442\u0435\u0445\u043D\u0438\u043A\u0435, \u043A\u043E\u043C\u043F\u044C\u044E\u0442\u0435\u0440\u043D\u043E\u043C \u0437\u0440\u0435\u043D\u0438\u0438. \u0412 \u0441\u0440\u0430\u0432\u043D\u0435\u043D\u0438\u0438 \u0441 \u043E\u0431\u044B\u0447\u043D\u043E \u043F\u0440\u0438\u043C\u0435\u043D\u044F\u0435\u043C\u044B\u043C\u0438 \u0434\u043B\u044F \u043F\u043E\u0434\u043E\u0431\u043D\u044B\u0445 \u0437\u0430\u0434\u0430\u0447 \u043C\u0435\u0442\u043E\u0434\u0430\u043C\u0438 \u2014 \u0440\u0430\u0441\u0448\u0438\u0440\u0435\u043D\u043D\u044B\u043C\u0438 \u0444\u0438\u043B\u044C\u0442\u0440\u0430\u043C\u0438 \u041A\u0430\u043B\u044C\u043C\u0430\u043D\u0430 (EKF) \u2014 \u043C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0435 \u0444\u0438\u043B\u044C\u0442\u0440\u044B \u043D\u0435 \u0437\u0430\u0432\u0438\u0441\u044F\u0442 \u043E\u0442 \u043C\u0435\u0442\u043E\u0434\u043E\u0432 \u043B\u0438\u043D\u0435\u0430\u0440\u0438\u0437\u0430\u0446\u0438\u0438 \u0438\u043B\u0438 \u0430\u043F\u0440\u043E\u043A\u0441\u0438\u043C\u0430\u0446\u0438\u0438. \u041E\u0431\u044B\u0447\u043D\u044B\u0439 EKF \u043F\u043B\u043E\u0445\u043E \u0441\u043F\u0440\u0430\u0432\u043B\u044F\u0435\u0442\u0441\u044F \u0441 \u0441\u0443\u0449\u0435\u0441\u0442\u0432\u0435\u043D\u043D\u043E \u043D\u0435\u043B\u0438\u043D\u0435\u0439\u043D\u044B\u043C\u0438 \u043C\u043E\u0434\u0435\u043B\u044F\u043C\u0438, \u0430 \u0442\u0430\u043A\u0436\u0435 \u0432 \u0441\u043B\u0443\u0447\u0430\u0435 \u0448\u0443\u043C\u043E\u0432 \u0441\u0438\u0441\u0442\u0435\u043C\u044B \u0438 \u0438\u0437\u043C\u0435\u0440\u0435\u043D\u0438\u0439, \u0441\u0438\u043B\u044C\u043D\u043E \u043E\u0442\u043B\u0438\u0447\u0430\u044E\u0449\u0438\u0445\u0441\u044F \u043E\u0442 \u0433\u0430\u0443\u0441\u0441\u043E\u0432\u044B\u0445, \u043F\u043E\u044D\u0442\u043E\u043C\u0443 \u0431\u044B\u043B\u0438 \u0440\u0430\u0437\u0440\u0430\u0431\u043E\u0442\u0430\u043D\u044B \u0440\u0430\u0437\u043B\u0438\u0447\u043D\u044B\u0435 \u043C\u043E\u0434\u0438\u0444\u0438\u043A\u0430\u0446\u0438\u0438, \u0442\u0430\u043A\u0438\u0435 \u043A\u0430\u043A UKF (\u0430\u043D\u0433\u043B. unscented KF), QKF (\u0430\u043D\u0433\u043B. Quadrature KF) \u0438 \u0442. \u043F.. \u0421\u043B\u0435\u0434\u0443\u0435\u0442 \u043E\u0442\u043C\u0435\u0442\u0438\u0442\u044C, \u0447\u0442\u043E \u0432 \u0441\u0432\u043E\u044E \u043E\u0447\u0435\u0440\u0435\u0434\u044C \u043C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0435 \u0444\u0438\u043B\u044C\u0442\u0440\u044B \u0431\u043E\u043B\u0435\u0435 \u0442\u0440\u0435\u0431\u043E\u0432\u0430\u0442\u0435\u043B\u044C\u043D\u044B \u043A \u0432\u044B\u0447\u0438\u0441\u043B\u0438\u0442\u0435\u043B\u044C\u043D\u044B\u043C \u0440\u0435\u0441\u0443\u0440\u0441\u0430\u043C. \u0422\u0435\u0440\u043C\u0438\u043D \u00ABparticle filter\u00BB \u0431\u044B\u043B \u0434\u0430\u043D \u0414\u0435\u043B \u041C\u043E\u0440\u0430\u043B\u043E\u043C \u0432 1996 \u0433\u043E\u0434\u0443, \u0430 \u00ABsequential Monte Carlo\u00BB \u2014 \u041B\u044E (Liu) \u0438 \u0427\u0435\u043D\u043E\u043C (Chen) \u0432 1998. \u041C\u043D\u043E\u0433\u0438\u0435 \u0438\u0441\u043F\u043E\u043B\u044C\u0437\u0443\u0435\u043C\u044B\u0435 \u043D\u0430 \u043F\u0440\u0430\u043A\u0442\u0438\u043A\u0435 \u043C\u043D\u043E\u0433\u043E\u0447\u0430\u0441\u0442\u0438\u0447\u043D\u044B\u0435 \u0444\u0438\u043B\u044C\u0442\u0440\u044B \u0432\u044B\u0432\u043E\u0434\u044F\u0442\u0441\u044F \u043F\u0440\u0438\u043C\u0435\u043D\u0435\u043D\u0438\u0435\u043C \u043F\u043E\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u0442\u0435\u043B\u044C\u043D\u043E\u0433\u043E \u043C\u0435\u0442\u043E\u0434\u0430 \u041C\u043E\u043D\u0442\u0435-\u041A\u0430\u0440\u043B\u043E \u043A \u043F\u043E\u0441\u043B\u0435\u0434\u043E\u0432\u0430\u0442\u0435\u043B\u044C\u043D\u043E\u0441\u0442\u0438 \u0446\u0435\u043B\u0435\u0432\u044B\u0445 \u0440\u0430\u0441\u043F\u0440\u0435\u0434\u0435\u043B\u0435\u043D\u0438\u0439."@ru . . . . . . . . "\uD30C\uD2F0\uD074 \uD544\uD130(\uC601\uC5B4: Particle filter)\uB294 \uC2DC\uBBAC\uB808\uC774\uC158\uC5D0 \uAE30\uBC18\uC744 \uB454 \uC608\uCE21\uAE30\uC220\uC758 \uD558\uB098\uB85C \uACC4\uC18D\uC801\uC778 \uBAAC\uD14C\uCE74\uB97C\uB85C \uBC29\uBC95\uC774\uB77C\uACE0\uB3C4 \uD55C\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uB294 \uACC4\uB7C9\uACBD\uC81C\uD559\uC5D0\uC11C \uC911\uC694\uD558\uAC8C \uC4F0\uC778\uB2E4. \uD30C\uD2F0\uD074 \uD544\uD130\uB294 \uBCF4\uD1B5 \uBCA0\uC774\uC988 \uBAA8\uB378\uC744 \uCD94\uC815\uD558\uAE30 \uC704\uD574 \uC0AC\uC6A9\uB41C\uB2E4. \uC774\uB294 \uC7A0\uC7AC\uBCC0\uC218\uAC00 \uB9C8\uB974\uCF54\uD504 \uC5F0\uC1C4\uB85C \uC11C\uB85C \uAD00\uB828\uB418\uC5B4 \uC788\uB294 \uACBD\uC6B0\uB85C \uC740\uB2C9 \uB9C8\uB974\uCF54\uD504 \uBAA8\uB378(HMM)\uACFC \uBE44\uC2B7\uD558\uC9C0\uB9CC \uBCF4\uD1B5 \uB4DC\uB7EC\uB098\uC9C0 \uC54A\uC740 \uBCC0\uC218\uC758 \uC0C1\uD0DC \uACF5\uAC04\uC774 \uC5F0\uC18D\uC801\uC774\uACE0, \uC815\uD655\uD558\uAC8C \uCD94\uC815\uD560 \uC218 \uC788\uC744 \uB9CC\uD07C \uD55C\uC815\uC801\uC774\uC9C0 \uC54A\uB2E4. \uC608\uB97C \uB4E4\uC5B4, \uC120\uD615 \uB3D9\uC801 \uC2DC\uC2A4\uD15C\uC5D0\uC11C\uB294, \uC7A0\uC7AC\uBCC0\uC218\uC758 \uC0C1\uD0DC \uACF5\uAC04\uC774 \uAC00\uC6B0\uC2A4 \uBD84\uD3EC\uC5D0 \uD55C\uC815\uB418\uB294\uB370, \uB530\uB77C\uC11C \uC815\uD655\uD55C \uCD94\uC815\uC774 \uD6A8\uACFC\uC801\uC73C\uB85C \uCE7C\uB9CC \uD544\uD130\uB9CC\uC73C\uB85C \uC774\uB8E8\uC5B4\uC9C8 \uC218 \uC788\uB2E4. HMM, \uADF8\uB9AC\uACE0 \uAD00\uB828\uB41C \uBAA8\uB378\uC758 \uB9E5\uB77D\uC5D0\uC11C \uBCF4\uBA74, \uD544\uD130\uB9C1\uC740 \uC5B4\uB5A4 \uD2B9\uC815 \uC2DC\uAC04\uC5D0 \uC7A0\uC7AC\uBCC0\uC218\uC758 \uBD84\uD3EC\uB97C \uACB0\uC815\uD558\uB418, \uAD00\uCE21 \uAC12\uC740 \uADF8 \uC2DC\uAC04 \uAE4C\uC9C0\uB9CC \uC8FC\uC5B4\uC9C4\uB2E4; \uD30C\uD2F0\uD074 \uD544\uD130\uB77C\uB294 \uC774\uB984\uC744 \uC5BB\uAC8C \uB41C \uAE4C\uB2ED\uC740 \uADFC\uC0AC\uAC12\uC744 (\uC544\uAE4C \uB9D0\uD55C \uC758\uBBF8\uC5D0\uC11C) \"\uD544\uD130\uB9C1\"\uD558\uB294\uB370 \uD55C \uBB34\uB9AC\uC758 (\uB2E4\uB978 \uAC00\uC911\uCE58\uB97C \uAC00\uC9C4 \uBD84\uD3EC\uC758 \uC608) \"\uC785\uC790\"\uB97C \uC0AC\uC6A9\uD558\uAE30 \uB54C\uBB38\uC774\uB2E4."@ko . . . . . . . . . . . . "Les filtres particulaires, aussi connus sous le nom de m\u00E9thodes de Monte-Carlo s\u00E9quentielles, sont des techniques sophistiqu\u00E9es d'estimation de mod\u00E8les fond\u00E9es sur la simulation. Les filtres particulaires sont g\u00E9n\u00E9ralement utilis\u00E9s pour estimer des r\u00E9seaux bay\u00E9siens et constituent des m\u00E9thodes 'en-ligne' analogues aux m\u00E9thodes de Monte-Carlo par cha\u00EEnes de Markov qui elles sont des m\u00E9thodes 'hors-ligne' (donc a posteriori) et souvent similaires aux m\u00E9thodes d'\u00E9chantillonnage pr\u00E9f\u00E9rentiel. S'ils sont con\u00E7us correctement, les filtres particulaires peuvent \u00EAtre plus rapides que les m\u00E9thodes de Monte-Carlo par cha\u00EEnes de Markov. Ils constituent souvent une alternative aux filtres de Kalman \u00E9tendus avec l'avantage qu'avec suffisamment d'\u00E9chantillons, ils approchent l'estim\u00E9 Bay\u00E9sien optimal. Ils peuvent donc \u00EAtre rendus plus pr\u00E9cis que les filtres de Kalman. Les approches peuvent aussi \u00EAtre combin\u00E9es en utilisant un filtre de Kalman comme une proposition de distribution pour le filtre particulaire."@fr . .