本論文提出一個實用的棒球比賽精華片段擷取與分類的方法。由於棒球比賽時間較久，若使用者需要在短時間內瀏覽多場比賽，一個自動的精華片段擷取將帶來許多便利。值得注意的是，精華片段擷取可視為一個數位錄影機的附屬功能，因此，它所耗費的計算資源應該遠少於數位視訊的解壓縮過程以符合實際應用的需求。我們所提出的系統首先將偵測所謂串場效果的位置。由於棒球比賽精彩片段重播出現的前後，通常會由電視台加入串場效果以告知觀眾，我們利用串場效果獨特的視覺特性，準確偵測其位置，即重播畫面出現處。接著，我們以SVM　(Support　Vector　Machine)分類器找出投打對決畫面，作為此段重播實際畫面的起點。再來，我們對於這些精彩畫面以HMM　(Hidden　Markov　Model)加以分析與分類，將內外野精采畫面的情境擷取出來，讓使用者更容易得到所需的內容。本系統主要是建構在MPEG2數位視訊壓縮格式上，即我們有效利用壓縮後的MPEG串流資訊，做為後續分析與處理的主要參考依據。如此設計不僅有效降低系統運算的複雜度，也讓我們的系統與其它已提出的方法相較，更具有實用性。實驗結果顯示，我們所提出的系統具有相當高的準確度。

This　paper　presents　a　practical　highlight　extraction　and　classification　schemes　for　baseball　videos.　The　approach　relies　on　precise　detections　of　transition　effects　inserted　at　the　beginning　and　the　end　of　the　replays　in　the　game,　which　demonstrate　the　game　highlights.　It　is　worth　noting　that　the　complexity　of　the　highlight　extraction　procedure　should　be　limited　since　it　is　an　auxiliary　function　of　a　digital　video　recorder.　Therefore,　in　the　proposed　system,　the　features　of　MPEG　compressed　videos　are　used　for　subsequent　processing　to　archive　efficiency.　The　properties　of　transition　effects　are　exploited　so　that　the　effects　can　be　accurately　retrieved　for　locating　the　video　segments　of　replays.　Next,　the　pitching　view,　which　is　the　starting　point　of　every　play　in　baseball　games,　will　be　extracted　via　Support　Vector　Machine　(SVM).　The　contents　of　the　play　can　then　be　analyzed　and　classified　to　determine　their　types　or　exciting　levels.　We　classify　the　extracted　highlight　segments　by　using　Hidden　Markov　model　(HMM).　Experimental　results　show　that　the　accuracy　is　good　enough　to　achieve　the　practical　highlight　extraction　for　baseball　videos.

[1] V.　Tovinkere　and　R.　J.　Qian,　“Detecting　semantic　events　in　soccer　games:　toward　a　complete　solution,”　Proc.　IEEE　International　Conference　on　Multimedia　&　Expo.　2001.
[2] A.　Hanjalic,　“Adaptive　extraction　of　highlights　from　a　sport　video　based　on　excitement　modeling,”　Proc.　IEEE　Transactions　on　Multimedia,　vol.　7,　no.　6,　Dec.　2005.
[3] J.　Assfalg,　M.　Bertini,　C.　Colombo,　A.　del　Bimbo,　and　W.　Nunziati,　“Semantic　annotation　of　soccer　videos:　Automatic　highlights　identification,”　Proc.　Computer　Vision　and　Image　Understanding,　vol.　92,　no.　2-3,　Nov.　2003.
[4] D.　Tjondronegoro,　Y.　–P.　Chen,　and　B.　Pham,　“Integrating　highlights　for　more　complete　sports　video　summarization,”　Proc.　IEEE　Multimedia,　vol.　11,　no.　4,　Oct.-Dec.　2004.
[5] J.　Assfalg,　M.　Bertini,　A.　D.　Bimbo,　W.　Nunziati　and　P.　Pala,　“Soccer　highlights　detection　and　recognition　using　HMMs,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo.,　Lausanne,　Aug.　2002.
[6] M.　Petkovic,　V.　Mihajlovic,　W.　Jonker　and　S.　Djordjevic-Kajan,　“Multi-modal　extraction　of　highlights　from　tv　formula　1　Programs,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo.,　Lausanne,　Aug.　2002.
[7] C.-C.　Cheng　and　C.-T.　Hsu,　“Fusion　of　audio　and　motion　information　on　HMM-based　highlight　extraction　for　baseball　games,”　Proc.　IEEE　Transactions　on　Multimedia,　vol.　8,　no.　3,　Jun.　2006.
[8] T.　Mochizuki,　M.　Tadenuma　and　N.　Yagi,　“Baseball　video　indexing　using　patternization　of　scenes　and　hidden　Markov　model,”　Proc.　IEEE　International　Conference　on　Image　Processing,　2005.
[9] P.　Chang,　M.　Han,　and　Y.　Gong,　“Extract　highlights　from　baseball　game　video　with　hidden　Markov　models,”　Proc.　IEEE　International　Conference　on　Image　Processing,　2002.
[10] L.　Rabiner,　“A　tutorial　on　hidden　Markov　models　and　selected　applications　in　speech　recognition,”　Proc.　IEEE,　vol.　77,　no.　2,　Feb.　1999.
[11] D.　Tjondornrgoro,　Y.-P.　Phoebe.　Chen,　and　B.　Pham,　“Sports　video　summarization　using　highlights　and　play-breaks,”　Proc.　The　5th　International　ACM　Multimedia　Information　Retrieval　Workshop,　address　Berkeley　USA,　Nov.　2003.
[12] A.　Kokaram,　N.　Rea,　R.　Dahyot,　M.　Tekalp,　P.　Bouthemy,　P.　Gros　and　I.　Sezan,　“Browsing　sports　video:　Trends　in　sports-related　indexing　and　retrieval　work,”　Proc.　IEEE　signal　Processing　Mag.,　vol.　23,　no.　2,　page　47-58,　2006.
[13] D.　Zhong　and　S.F.　Chang,　“Structure　analysis　of　sports　video　using　domain　models,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo.　’01,　2001.
[14] A.　Ekin,　A.　Muart　Tekalp　and　R.　Mehrotra,　“Automatic　soccer　video　analysis　and　summarization,”Proc.　IEEE　Transaction　on　Image　Processing,　vol.　12,　no.　7,page　796-807,　　Jul.　2003.
[15] Y.　Gong,　L.T.　Sin,　C.H.　Chuan,　H.　Zhang　and　M.　Sakauchi,　“Automatic　parsing　of　TV　soccer　programs,”　Proc.　IEEE　International　Conference　on　Multimedia　Computing　and　Systems,　vol.　7,　page　167-174,　May　1995.
[16] L.-Y.　Duan,　M.　Xu,　X.-D.　Yu　and　Q.　Tian,　“A　unified　framework　for　semantic　shot　classification　in　sports　videos,”　Proc.　IEEE　Transaction　on　Multimedia,　vol.　7,　no.　6,　page　1066-1083,　Dec.　2005.
[17] Y.P.　Tan,　D.D.　Saur,　S.R.　Kulkarni　and　P.J.　Ramadge,　“Rapid　Estimation　of　camera　motion　from　compressed　video　with　application　to　video　annotation,”　Proc.　IEEE　Transaction　on　Circuits　and　Video　Technology,　vol.　10,　no.　1,　Feb.　2000.
[18] A.　Bonzanini,　R.　Leonardi　and　P.　Migliorati,　“Event　recognition　in　sport　programs　using　Low-Level　motion　indices,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo,　2001.
[19] D.　Zang,　and　S.F.　Chang,　“Event　detecting　in　baseball　video　using　superimposed　caption　recognition,”　Proc.　ACM　Multimedia　2002,　Juan　Les　Paris,　France,　Dec.　2002.
[20] D.　Zang,　R.K.　Rajendran,　and　S.F.　Chang,　“General　and　domain-specific　techniques　for　detecting　and　recognizing　superimposed　text　in　video,”　Proc.　IEEE　International　Conference　on　Image　Processing,　Sep.　2002.
[21] J.C.　Boulton,　“Two　mechanisms　for　detection　of　slow　motion,”　Proc.　Journal　of　the　Optical　Society　of　America　A:　Optics,　Image　Science,　and　Vision,　vol.　4,　page1634-1642,　Aug.　1987.
[22] V.　Kobla,　D.　DeMoenthon　and　D.　Doermann,　“Detection　of　slow-motion　replay　sequences　for　identifying　sports　videos,”　Proc.　IEEE　Workshop　on　Multimedia　Signal　Processing,　1999.
[23] L.　Gu,　D.　Bone　and　G.　Reynolds,　“Replay　detection　in　sports　video　sequences,”　Proc.　the　Eurographics　Workshop　on　Multimedia,　Multimedia''99,　Eds.　Correia　N.,　Chambel　T.　and　Davenport　D.,　Springer　Verlag,　pp.　3-12,　Milan,　Italy,　Sep.　1999.
[24] J.　Wang,　E.　Chng　and　C.　Xu,　“Soccer　Replay　Detection　using　Scene　Transition　Structure　Analysis,”　Proc.　IEEE　International　Conference　on　Acoustics,　Speech,　and　Signal　Processing　(ICASSP''2005),　vol.　2,　pp.　433-436　Pennsylvania,　USA,　Mar.　2005.
[25] H.　Pan,　P.　Van　Beek　and　M.I.　Sezan,　“Detection　of　slow-motion　replay　segments　in　sports　video　for　highlights　generation,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing,　vol.　3,　pp.　1649-1652,　2001.
[26] L.　Wang,　X.　Liu,　S.　Lin,　G.-Y.　Xu　and　H.-Y.　Shum,　“Generic　slow-motion　replay　detection　in　sports　video,”　Proc.　IEEE　International　Conference　on　Image　Processing,　vol.　3,　pp.　1585-1588,　Oct.　2004.
[27] E.J.　Farn,　L.H.　Chen　and　J.H.　Liou,　“A　new　slow-motion　replay　extractor　for　soccer　game　videos,”　Proc.　International　Journal　of　Pattern　Recognition　and　Artificial　Intelligence,　vol.　17,　pp.　1467-1481,　2003.
[28] H.　Jiang,　L.　Lu,　and　H.J.　Zhang,　“A　robust　audio　classification　and　segmentation　method,”　Proc.　ACM　International　Conference　on　Multimedia,　Ottawa,　Ontario,　Canada,　vol.　9,　pp.203-211,　Sep.　2001.
[29] Y.　Rui,　A.　Gupta　and　A.　Acero,　“Automatically　extracting　highlights　for　TV　baseball　programs,”　Eighth　ACM　International　Conference　on　Multimedia,　pp.105-115,　2000.
[30] Z.　Xiong,　R.　Radhakrishnan,　A.　Divakaran　and　T.　Huang,　“Audio　events　detection　based　highlights　extraction　from　baseball,　golf　and　soccer　games　in　a　unified　framework,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing　2003,　Apr.　2003.
[31] R.　Leonardi,　P.　Migliorati　and　M.　Prandini,　“Sematic　indexing　of　sports　program　sequences　by　Audio-Visual　analysis,”　Proc.　IEEE　International　Conference　on　Image　Processing,　Sep.　2003.
[32] Y.-L.　Chang,　W.　Zeng,　I.　Kamel　and　R.　Alonso,　“Integrated　image　and　speech　analysis　for　content-based　video　indexing,”　Proc.　IEEE　International　Conference　on　Multimedia　Computing　and　Systems,　1996.
[33] S.-C.　Chen,　M.-L.　Shyu,　W.　Liao　and　C.　Zhang,　“Scene　change　detection　by　audio　and　video　clues,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo,　2002.
[34] A.　Albiol,　L.　Torres　and　J.　Delp,　“The　indexing　of　persons　in　news　sequences　using　audio-visual　data,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing,　2003.
[35] W.　Hua,　M.　Han　and　Y.　Gong,　“Baseball　scene　classification　using　multimedia　features,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo,　2002.
[36] A.　Hanjalic,　“Generic　approach　to　highlight　extraction　from　a　sport　video,”　Proc.　IEEE　International　Conference　on　Image　Processing,　Sep.　2003.
[37] Z.　Xong,　R.Radhakrishnan　and　A.　Divakaran,　“Generation　of　sports　highlights　using　motion　activity　in　combination　with　a　common　audio　feature　extraction　framework,”　Proc.　IEEE　International　Conference　on　Image　Processing,　Sep.　2003.
[38] M.　Petkovic,　V.　Mihajlovic　and　W.　Jonker,　“Techniques　for　automatic　video　content　derivation,”　Proc.　IEEE　International　Conference　on　Image　Processing,　Sep.　2003.
[39] R.　Dahyot,　A.　Kokaram,　N.　Rea　and　H.　Denman,　“Joint　audio　visual　retrieval　for　tennis　broadcasts,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing,　2003.
[40] Y.　Gong,　X.　Liu　and　W.　Hua,　“Creating　motion　video　summaries　with　partial　audio-visual　alignment,”　Proc.　IEEE　International　Conference　on　Multimedia　and　Expo,　2002.
[41] H.-T.　Chen,　M.-H.　Hsiao,　H.-S.　Chen,　W.-J.　Tsai　and　S.-Y　Lee,　“A　baseball　exploration　system　using　spatial　pattern　recognition,”　Proc.　IEEE　International　Symposium　on　Circuits　and　Systems,　May　2008.
[42] M.　Fleischman,　B.　Roy　and　D.　Roy,　“Temporal　feature　induction　for　baseball　highlight　classification,”　Proc.　ACM　Multimedia　Conference,　Augsburg,　Germany,　2007.
[43] B.　Moghaddam　and　A.　Pentland,　“Probabilistic　visual　learning　for　object　recognition,”　Proc.　IEEE　Transactions　on　Pattern　Analysis　and　Machine　Intelligence,　vol.　19,　no.7,　pp.　696-710,　Juillet　1997.
[44] L.　Xie,　S.-F.　Chang,　A.　Divakaran　and　H.　Sun,　“Structure　analysis　of　sports　video　with　hidden　Markov　models,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing,　2002.
[45] P.　Chang,　M.　Han　and　Y.　Gong,　“Extract　highlights　from　baseball　game　video　with　hidden　Markov　models,”　Proc.　IEEE　International　Conference　on　Image　Processing,　2002.
[46] G.　Xu,　Y.-F.　Ma,　H.-J.　Zhang　and　S.-Q.　Yang,　“Motion-based　event　recognition　using　HMM,”　Proc.　IEEE　International　Conference　on　Pattern　Recognition,　2002.
[47] G.　Xu,　Y.-F.　Ma,　H.-J.　Zhang　and　S.-Q.　Yang,　“A　HMM　based　semantic　analysis　framework　for　sports　game　event　detection,”　Proc.　IEEE　International　Conference　on　Image　Processing,　2003.
[48] G.　Xu,　Y.-F.　Ma,　H.-J　Zhang　and　S.-Q.　Yang,　“An　HMM　based　framework　for　video　semantic　analysis,”　Proc.　IEEE　Transactions　on　Circuits　and　Systems　for　Video　Technology,　vol.　15,　no.　11,　Nov.　2005.
[49] J.　Assfalg,　M.　Bertini,　A.　Del　Bimbo,　W.　Nunziati　and　O.　Pala,　“Detection　and　recognition　of　football　highlights　using　HMM,”　Proc.　IEEE　International　Conference　on　Electronics,　Circuits,　and　Systems,　2002.
[50] N.　Rea,　R.　Dahyot,　and　A.　Kokaramn,　“Modeling　high　level　structure　in　sports　with　motion　driven　HMM,”　Proc.　IEEE　International　Conference　on　Acoustic,　Speech　and　Signal　Processing,　vol.　3,　pp.　621-624,　May　2004.
[51] G.　Jin,　L.　Tao　and　G.　Xu,　“Hidden　Markov　model　based　events　detection　in　soccer　video,”　Proc.　International　Conference　on　Image　Analysis　and　Recognition,　2004.