Á¤º¸°úÇÐȸ ³í¹®Áö B : ¼ÒÇÁÆ®¿þ¾î ¹× ÀÀ¿ë
Current Result Document : 3 / 3
ÀÌÀü°Ç
ÇѱÛÁ¦¸ñ(Korean Title) |
³»¿ë±â¹Ý ºñµð¿À °Ë»öÀ» À§ÇÑ ¿òÁ÷ÀÓ º¤ÅÍ Æ¯Â¡ ÃßÃâ ¾Ë°í¸®Áò |
¿µ¹®Á¦¸ñ(English Title) |
Efficient Methods for Detecting Frame Characteristics and Objects in Video Sequences |
ÀúÀÚ(Author) |
ÀÌÇöâ
ÀÌÀçÇö
Àå¿Á¹è
HyunChang Lee
JaeHyun Lee
OkBae Jang
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 35 NO. 01 PP. 0001 ~ 0011 (2008. 01) |
Çѱ۳»¿ë (Korean Abstract) |
ºñµð¿ÀÀÇ È¿À²ÀûÀÎ ³»¿ë±â¹Ý °Ë»öÀ» Áö¿øÇϱâ À§ÇØ ¿òÁ÷ÀÓº¤ÅÍÀÇ Æ¯Â¡À» °ËÃâÇÏ¿´´Ù. À̸¦ À§ÇØ ºñµð¿ÀÀÇ ÇöÀç ÇÁ·¹ÀÓÀ» ÀÏÁ¤ÇÑ Å©±âÀÇ ºí·ÏÀ¸·Î ³ª´©°í ½Ã°£ Ãà»ó ±âÁØÀÌ µÇ´Â ÇÁ·¹ÀÓ¿¡¼ °¢ ºí·ÏÀÇ ¿òÁ÷ÀÓÀ» ÃßÁ¤ÇÏ´Â ºí·ÏÁ¤ÇÕ ¾Ë°í¸®ÁòÀ» ÀÌ¿ëÇÏ¿´´Ù. ÇÏÁö¸¸ ºí·Ï Á¤ÇÕ¹ýÀÇ °æ¿ì ¿©·¯ °¡Áö Á¦¾à Á¶°Ç°ú ÇÔ²² ºí·Ï Á¤ÇÕ¹ý¿¡ ÀÇÇØ ¾ò¾îÁö´Â º¤ÅÍ°¡ ½ÇÁ¦ ¿òÁ÷ÀÓ°ú »óÀÌÇÑ °æ¿ìµµ ¹ß»ýÇÑ´Ù. ÀÌ·¯ÇÑ ¹®Á¦Á¡À» ÇØ°áÇϱâ À§Çؼ Àü¿ªÅ½»ö¹æ½ÄÀ» ÀÀ¿ëÇßÀ¸³ª ÀÌ ¹æ¹ýÀº °è»ê·®ÀÌ ¸¹´Ù´Â ´ÜÁ¡ÀÌ ÀÖ´Ù. ±× ´ë¾ÈÀ¸·Î º» ³í¹®¿¡¼´Â ¿òÁ÷ÀÓ º¤ÅÍÀÇ ½Ã°ø°£ »ó°ü¼º(MVSTC : Motion Vector Spatio-Temporal Correlations)ÀÇ ½Ã°£Àû °ø°£Àû Ư¡À» ÃßÃâÇÏ¿´´Ù. ±× °á°ú º» ³í¹®¿¡¼´Â ÀÎÁ¢ ºí·ÏÀÇ ¿òÁ÷ÀÓ º¤Å͸¦ ÀÌ¿ëÇÏ¿© Á» ´õ Á¤È®ÇÑ ¿òÁ÷ÀÓ º¤ÅÍÀÇ ¿¹ÃøÀ» ¼öÇàÇÒ ¼ö ÀÖ¾ú´Ù. ÇÏÁö¸¸ ÂüÁ¶µÇ´Â ºí·Ï º¤ÅÍÀÇ ¼ö°¡ ¿©·¯°³ ¹ß»ýµÇ±â ¶§¹®¿¡ ÀÌ·¯ÇÑ ºÎ°¡ Á¤º¸¸¦ ¼ö½Å´Ü¿¡ Àü¼ÛÇØ¾ß ÇÏ´Â ºÎ´ãÀ» ÃÊ·¡ÇÏ°Ô µÈ´Ù. µû¶ó¼ °¢ ºí·ÏÀÇ ¿òÁ÷ÀÓ Æ¯Â¡À» ¿¹ÃøÇÏ°í ÀÌ¿¡ ¾Ë¸ÂÀº Ž»ö ¹üÀ§¸¦ ¼³Á¤ÇÏ´Â ¹®Á¦µµ °í·ÁÇØ¾ß ÇÑ´Ù. Á¦½ÃµÈ ¾Ë°í¸®ÁòÀ» ¹ÙÅÁÀ¸·Î ¿òÁ÷ÀÓ º¸»óÀ» À§ÇÑ ¿òÁ÷ÀÓ ÃßÁ¤ ±â¹ýÀ» °íÂûÇÏ°í À̸¦ Àû¿ëÇÑ °á°ú¸¦ Á¦½ÃÇÏ°íÀÚ ÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
This paper detected the characteristics of motion vector to support efficient content- based video search of video. Traditionally, the present frame of a video was divided into blocks of equal size and BMA (block matching algorithm) was used, which predicts the motion of each block in the reference frame on the time axis. However, BMA has several restrictions and vectors obtained by BMA are sometimes different from actual motions. To solve this problem, the full search method was applied but this method is disadvantageous in that it has to make a large volume of calculation. Thus, as an alternative, the present study extracted the Spatio-Temporal characteristics of Motion Vector Spatio-Temporal Correlations (MVSTC). As a result, we could predict motion vectors more accurately using the motion vectors of neighboring blocks. However, because there are multiple reference block vectors, such additional information should be sent to the receiving end. Thus, we need to consider how to predict the motion characteristics of each block and how to define the appropriate scope of search. Based on the proposed algorithm, we examined motion prediction techniques for motion compensation and presented results of applying the techniques.
|
Å°¿öµå(Keyword) |
³»¿ë±â¹Ý °Ë»ö
¸ÖƼ¹Ìµð¾î
¿¡ÀÌÄ¡¾¾¾ÆÀÌ
¿ÉƼÄà Ç÷οì
ºñµð¿À À妽º
ºñÁê¾ó ÀÎÅÍÆäÀ̽º
Content-Based Retrieval
Multimedia
HCI
Optical Flow
Video Index
Visual Interface
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|