Overview.

Sum of difference for static seams.

Seam searching.

Step by step results.

 

Exploring Spatial and Temporal Coherence to Strengthen Seam Carving in Video Retargeting

(§Q¥ÎªÅ¶¡»P®É¶¡¤@­P©Ê¥h¼W±jÁ_¨èªº¼v¤ùÁY©ñ)

http://www.cs.ccu.edu.tw/~damon/research/101/601410058/main.files/image015.png

ABSTRACT:

Number of various display screens and mobile devices has increased significantly. Unfortunately, showing a fixed size picture or video is often limited by the aspect ratio of different displays. In recent years, many content-aware retargeting techniques have been proposed. Among them, Seam carving is a novel and efficient method, but it may distort the object¡¦s structure.

For enlarging an image, we tend to make it larger and undistorted by first magnifying the image, and shrink it to the target size using Seam carving. Thus, in this thesis, we focus on shrinking. For spatial coherence, we emphasize the object shape and protect significant content. We also combine Seam carving and Scaling operator, trying to avoid the bad results due to content distortion. Moreover, we extend our method to video retargeting, which formerly caused the jittery artifacts without exploring temporal information. We classify the videos into those taken by the static camera setup and the others by the moving camera setup. Then we explore temporal coherence to decrease the jittery artifacts. Finally, the experimental results demonstrate our approach can raise the quality in video retargeting.

 

SUMMARY (¤¤¤åÁ`µ²):

ÀHµÛ»È¹õÅã¥Ü¾¹³vº¥ªº¦h¼Ë¤Æ¡A­n®i¥Ü¤Ø¤o©T©wªº¹Ï¤ù©Î¼v¤ù¡A©¹©¹¨ü­­©ó¤£¦PÅã¥Ü¾¹ªº¤j¤p¡C¦bªñ´X¦~¨Ó¡A¤º®e·Pª¾ªºÁY©ñ¤èªk¤é¯q¼W¥[¡A¦ÓÁ_¨è¬O¤@ºØ·s¿o¥B¦³®Äªº¤èªk¡A¦ý¬O¦¹¤èªk¥i¯à¯}Ãaª«Å骺µ²ºc©Ê¨Ã³y¦¨§á¦±²{¶H¡C

§Ú­Ì¦b¼v¤ù©ñ¤jªº³¡¤À¨Ï¥Îµ¥¤ñ¨Ò©ñ¤j«á¡A¦A±Ä¥ÎÁ_¨è¨ÓÁY´î¨ì¥Ø¼Ð¤j¤p¡C¦]¦¹¦b¥»½g½×¤å¡A·|µÛ­«©óÁY´î³¡¤À¡A¦bªÅ¶¡ªº¤@­P©Ê¤W¡A±j½Õ½ü¹ø©M¥DÅ餺®eªº«OÅ@¡A¨Ã¥Bµ²¦XÁ_¨è©M«Dµ¥¤ñ¨Ò¹Bºâ¤l¨Ó¹F¨ì¬üÆ[ªº®ÄªG¡C³Ì«á±N¦¹¤èªk©µ¦ù¦Ü¼v¤ù¡A¦]¬°¨C­Ó¼v®æ¤§¶¡³£¦³®É¶¡ªº³sÄò©Ê¡A­Yª½±µ®M¥Î­ì¤èªk·|³y¦¨¼v¤ù¸õ°Êªº°ÝÃD¡C§Ú­Ì§â¼v¤ù¤À¦¨ÀRºA¬Û¾÷¸ò°ÊºA¬Û¾÷¨âºØÃþ«¬¡A§Q¥Î®É¶¡ªº¤@­P©Ê¨Ó´î¤Ö¸õ°Ê°ÝÃDªº²£¥Í¡A¨Ã¥B®Ú¾Ú¹êÅçµ²ªGÅçÃÒ¡A§Ú­Ìªº¤èªk¥i¥H´£¤É¼v¤ùÁY©ñ«áªº«~½è¡C

 

 

§Ú­Ìªº¨t²Î¥Ñ¥D­n¨â­Ó³¡¤À©Ò²Õ¦¨:

1.Spatial coherence cost

  §Ú­Ì´£¥X¤FCompound energy function¡A¤À§O¦³Forward energy¡ASaliency map©M Canny detector¡AÂǥѦU¤èªkªº¦n³B¨Ó­°§C¤º®e§á¦±¥H¤Î«OÅ@­«­nª«¥óªº®ÄªG¡F¬°¤F¨¾¤î¨Ï¥ÎªÌ»Ýµ¥«Ý¹L¦h®É¶¡¨Ó°õ¦æseam carving¡A¤S±o¤£¨ì¹w´Áªº¦nµ²ªG¡A§Ú­Ì¦b¨C­Ó§R°£seamªº¶¥¬q³£·|°õ¦æ«~½èªºµû¦ô¡A­Y¬O¬Û¦ü«×ÅܧC¤F¡A§Ú­Ì±N¨Ï¥Îscale ¹Bºâ¤l¨ÓÁY¤p¨ì¥Ø¼Ð¤j¤p¡C

 

2.Temporal coherence cost

  ¦b¼v¤ùªº¤ÀÃþ¤W¡A§Ú­Ì¤j­P¤À¦¨¨âºØÃþ«¬(static camera¡Bmoving camera)¨Ó°µ³B²z¡C¦bstatic cameraªº¼v¤ù¡A§Ú­Ì±N¨Ï¥Îsum of difference¨Ó°O¿ýª«¥ó²¾°Êªº­y¸ñ¡A¨Ã¥[¤J²Ä¤@­Óframeªºenergy¨Ó­pºâ¥Xstatic seams¡A¤§«áªºframes´N¥i¥H§Q¥Î¬dªíªº¤è¦¡¨Óª½±µ²¾°£seams¡A¦]¦¹¥i¥H´î¤Ö­pºâªº®É¶¡©M­°§C¼v¤ù§Ý°Êªº²{¶H¡F¦bmoving cameraªº¼v¤ù¡A§Ú­Ì¨Ï¥Î¦¬´Mseamªº¤èªk¡A§ä¨ì·í«eframe»P¤W¤@­Óframeªºseam³Ì¬Û¦üªºseam¡A¦pªG¦¬´M¤£¨ì§Ú­Ì·|ÃB¥~¥[¤Jtemporal coherence cost¡A¨Ó­«·s­pºâ¥X¤@±ø³Ì±µªñªºseam¡A³Ì«á¡A§Ú­Ì´N¯à´î¤Ö§Ý°Êªº²{¶H¡A¨Ã±o¨ì¦nªºµ²ªG¡C

 

 

¡±  Video results.

¡±    µ²ªG®i¥Ü