• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸°úÇÐȸ ³í¹®Áö > Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ƯÀÌ°ª ºÐÇØ¿Í Á¡ÁõÀû Ŭ·¯½ºÅ͸µÀ» ÀÌ¿ëÇÑ ´º½º ºñµð¿À ¼¦ °æ°è ŽÁö
¿µ¹®Á¦¸ñ(English Title) News Video Shot Boundary Detection using Singular Value Decomposition and Incremental Clustering
ÀúÀÚ(Author) ÀÌÇѼº   ÀÓ¿µÈñ   ¹Ú´ëÈñ   À̼ºÈ¯   Hansung Lee   Younghee Im   Daihee Park   Seongwhan Lee  
¿ø¹®¼ö·Ïó(Citation) VOL 36 NO. 02 PP. 0169 ~ 0177 (2009. 02)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ´º½º ±â»ç ºÐÇÒ °üÁ¡¿¡¼­, ´º½º ºñµð¿À ¼¦ °æ°è ŽÁö ¾Ë°í¸®ÁòÀÇ Æ¯¼ºÀ» °í·ÁÇÑ ´ÙÀ½°ú °°Àº ¼³°è ±âÁØÀ» Á¦½ÃÇÏ°í, À̸¦ ¸ðµÎ ¸¸Á·ÇÏ´Â »õ·Î¿î ¼¦ °æ°è ŽÁö ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÏ°íÀÚ ÇÑ´Ù. 1) ´º½º ºñµð¿À ¼¦ °æ°è ŽÁöÀÇ ÀçÇöÀ²À» ³ôÀÓÀ¸·Î½á, ¾ÞÄ¿ ¼¦ ŽÁö ´Ü°è¿¡¼­ ÀÔ·ÂÀ¸·Î »ç¿ëµÉ µ¥ÀÌŸÀÇ ¿À·ù¸¦ ÃÖ¼ÒÈ­ÇÑ´Ù; 2) ±Þ°ÝÇÑ Àå¸é º¯È¯°ú Á¡ÁõÀû Àå¸é º¯È¯À» ÇϳªÀÇ ¾Ë°í¸®ÁòÀ¸·Î ŽÁöÇÔÀ¸·Î½á ÇÑ ¹øÀÇ µ¥ÀÌŸ Ž»öÀ¸·Î ¼¦ ºÐÇÒÀ» ¼öÇàÇÑ´Ù; 3) ºÐÇÒµÈ ¼¦µéÀ» Á¤Àû ¼¦°ú µ¿Àû ¼¦À¸·Î ºÐ·ùÇÔÀ¸·Î½á ¾ÞÄ¿ ¼¦ ŽÁö ´Ü°èÀÇ Å½»ö °ø°£À» Ãà¼ÒÇÑ´Ù. Á¦¾ÈµÈ ´º½º ºñµð¿À ¼¦ °æ°è ŽÁö ¾Ë°í¸®ÁòÀº ƯÀÌ°ª ºÐÇظ¦ ±â¹ÝÀ¸·Î Á¡ÁõÀû Ŭ·¯½ºÅ͸µ ¾Ë°í¸®Áò°ú ¸Ó¼­ Ä¿³ÎÀ» °áÇÕÇÑ ±¸Á¶·Î¼­, À§¿¡¼­ Á¦½ÃÇÑ ±âÁØÀ» ¸ðµÎ ¸¸Á·Çϵµ·Ï ¼³°èµÇ¾ú´Ù. Á¦¾ÈµÈ ¹æ¹ý·ÐÀº ƯÀÌ°ª ºÐÇظ¦ ÅëÇØ Æ¯Â¡ º¤ÅÍÀÇ Â÷¿øÃà¼Ò »Ó¸¸ ¾Æ´Ï¶ó, ´º½º ºñµð¿À¸¦ ±¸¼ºÇÏ´Â ¿¬¼ÓÀûÀÎ ÇÁ·¹ÀÓ¿¡¼­ÀÇ ÀâÀ½°ú ¾ÆÁÖ ÀÛÀº º¯È­¸¦ Á¦°ÅÇÔÀ¸·Î½á ºÐ·ù ¼º´ÉÀ» ³ôÀÏ ¼ö ÀÖ´Ù. ¶ÇÇÑ ¸Ó¼­ Ä¿³ÎÀÇ µµÀÔÀº ½±°Ô ºÐ·ùµÇÁö ¾Ê´Â µ¥ÀÌŸ¸¦ °íÂ÷¿ø °ø°£À¸·Î ¸ÅÇÎÇÔÀ¸·Î½á ±¸ºÐÇϱ⠾î·Á¿î ¼¦ °æ°èÀÇ Å½Áö °¡´É¼ºÀ» ³ô¿©ÁØ´Ù. ½ÇÇèÀ» ÅëÇÏ¿© Á¦¾ÈµÈ ¹æ¹ý·ÐÀÌ ¸Å¿ì ³ôÀº ÀçÇöÀ²À» º¸À̸ç, ¾ÞÄ¿ ¼¦ ŽÁö¸¦ À§ÇÑ Å½»ö °ø°£ Ãà¼Ò¸¦ È¿°úÀûÀ¸·Î ¼öÇàÇÔÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a new shot boundary detection method which is optimized for news video story parsing. This new news shot boundary detection method was designed to satisfy all the following requirements: 1) minimizing the incorrect data in dataset for anchor shot detection by improving the recall ratio 2) detecting abrupt cuts and gradual transitions with one single algorithm so as to divide news video into shots with one scan of dataset; 3) classifying shots into static or dynamic, therefore, reducing the search space for the subsequent stage of anchor shot detection. The proposed method, based on singular value decomposition with incremental clustering and mercer kernel, has additional desirable features. Applying singular value decomposition, the noise or trivial variations in the video sequence are removed. Therefore, the separability is improved. Mercer kernel improves the possibility of detection of shots which is not separable in input space by mapping data to high dimensional feature space. The experimental results illustrated the superiority of the proposed method with respect to recall criteria and search space reduction for anchor shot detection.
Å°¿öµå(Keyword) ¼¦ °æ°è ŽÁö   shot boundary detection   ´º½º ºñµð¿À ÆĽ̠  news video parsing   ƯÀÌ°ª ºÐÇØ   mercer kernel   Á¡ÁõÀû Ŭ·¯½ºÅ͸µ   singular value decomposition   adaptive resonance t  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå