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

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Çѱ¹ÀÎÅͳÝÁ¤º¸ÇÐȸ ³í¹®Áö

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) °ø°£ Ŭ·¡½º ´Ü¼øÈ­¸¦ ÀÌ¿ëÇÑ Àǹ̷ÐÀû ½Ç³» ¿µ»ó ºÐÇÒ
¿µ¹®Á¦¸ñ(English Title) Semantic Indoor Image Segmentation using Spatial Class Simplification
ÀúÀÚ(Author) ±èÁ¤È¯   ÃÖÇüÀÏ   Jung-hwan Kim   Hyung-il Choi  
¿ø¹®¼ö·Ïó(Citation) VOL 20 NO. 03 PP. 0033 ~ 0041 (2019. 06)
Çѱ۳»¿ë
(Korean Abstract)
º» ³í¹®¿¡¼­´Â ½Ç³» °ø°£ À̹ÌÁöÀÇ Àǹ̷ÐÀû ¿µ»ó ºÐÇÒÀ» À§ÇØ ¹è°æ°ú ¹°Ã¼·Î Àç¼³°èµÈ Ŭ·¡½º¸¦ ÇнÀÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. Àǹ̷ÐÀû ¿µ»ó ºÐÇÒÀº À̹ÌÁöÀÇ º®À̳ª ħ´ë µî Àǹ̸¦ °®´Â ºÎºÐµéÀ» Çȼ¿ ´ÜÀ§·Î ³ª´©´Â ±â¼úÀÌ´Ù. ±âÁ¸ Àǹ̷ÐÀû ¿µ»ó ºÐÇÒ¿¡ ´ëÇÑ ¿¬±¸µéÀº ½Å°æ¸ÁÀ» ÅëÇØ À̹ÌÁöÀÇ ´Ù¾çÇÑ °´Ã¼ Ŭ·¡½ºµéÀ» ÇнÀÇÏ´Â ¹æ¹ýµéÀ» Á¦½ÃÇØ¿Ô°í, ±ä ÇнÀ ½Ã°£¿¡ ºñÇØ Á¤È®µµ°¡ ºÎÁ·ÇÏ´Ù´Â ¹®Á¦°¡ ÁöÀûµÇ¾ú´Ù. ±×·¯³ª ¹°Ã¼¿Í ¹è°æÀ» ºÐ¸®ÇÏ´Â ¹®Á¦¿¡¼­´Â, ´Ù¾çÇÑ °´Ã¼ Ŭ·¡½º¸¦ ÇнÀÇÒ ÇÊ¿ä°¡ ¾ø´Ù. µû¶ó¼­ ¿ì¸®´Â ÀÌ ¹®Á¦¿¡ ÁýÁßÇØ, Ŭ·¡½º¸¦ ´Ü¼øÈ­ ÈÄ¿¡ ÇнÀÇÏ´Â ¹æ¹ýÀ» Á¦¾ÈÇÑ´Ù. ÇнÀ ¹æ¹ýÀÇ ½ÇÇè °á°ú·Î ±âÁ¸ ¹æ¹ýµéº¸´Ù Á¤È®µµ°¡ ¾à 5~12% Á¤µµ ³ô¾Ò´Ù. ±×¸®°í °°Àº ȯ°æ¿¡¼­ Ŭ·¡½º¸¦ ´Þ¸® ±¸¼ºÇßÀ» ¶§ ÇнÀ ½Ã°£ÀÌ ¾à 14 ~ 60ºÐ Á¤µµ ´ÜÃàµÆÀ¸¸ç, ÀÌ¿¡ µû¶ó ¹°Ã¼¿Í ¹è°æÀ» ºÐ¸®ÇÏ´Â ¹®Á¦¿¡ ´ëÇØ Á¦¾ÈÇÏ´Â ¹æ¹ýÀÌ È¿À²ÀûÀÓÀ» º¸ÀδÙ.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a method to learn the redesigned class with background and object for semantic segmentation of indoor scene image. Semantic image segmentation is a technique that divides meaningful parts of an image, such as walls and beds, into pixels. Previous work of semantic image segmentation has proposed methods of learning various object classes of images through neural networks, and it has been pointed out that there is insufficient accuracy compared to long learning time. However, in the problem of separating objects and backgrounds, there is no need to learn various object classes. So we concentrate on separating objects and backgrounds, and propose method to learn after class simplification. The accuracy of the proposed learning method is about 5 ~ 12% higher than the existing methods. In addition, the learning time is reduced by about 14 ~ 60 minutes when the class is configured differently In the same environment, and it shows that it is possible to efficiently learn about the problem of separating the object and the background.
Å°¿öµå(Keyword) Àǹ̷ÐÀû ¿µ»ó ºÐÇÒ   ½Ç³» °ø°£ ±¸Á¶   ±â°è ÇнÀ   Semantic image segmentation   Indoor space structure   Machine Learning  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå