• 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¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Çѱ¹Á¤º¸Åë½ÅÇÐȸ ³í¹®Áö (Journal of the Korea Institute of Information and Communication Engineering)

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ½Å°æ¸Á¿¡ ÀÇÇÑ ¹ÌÁöÀÇ ´ÙÁß ¼öÁß À̵¿¹°Ã¼ÀÇ ÆǺ° ¹× ÃßÀû
¿µ¹®Á¦¸ñ(English Title) Classification and Tracking of Unknown Multiple Underwater Moving Objects Using Neural Networks
ÀúÀÚ(Author) Çϼ®¿î   Seok-Wun Ha  
¿ø¹®¼ö·Ïó(Citation) VOL 03 NO. 02 PP. 0389 ~ 0396 (1999. 06)
Çѱ۳»¿ë
(Korean Abstract)
º» ¿¬±¸¿¡¼­´Â ¼öÁß¿¡¼­ ÁøÇàÇÏ´Â ¹°Ã¼¿¡¼­ Àü´ÞµÇ´Â ¹æ»ç½ÅÈ£ÀÇ ÁÖÆļö½ºÆåÆ®·³À¸·ÎºÎÅÍ ÃßÃâµÇ´Â Åä³Î°ú ÁÖÆļö¼±°ú °°Àº Çù´ë¿ª Ư¡À» ÀÌ¿ëÇÏ¿© ¹ÌÁöÀÇ ´ÙÁß ¼öÁß À̵¿¹°Ã¼¸¦ È¿À²ÀûÀ¸·Î ÆǺ°ÇÏ°í ÃßÀûÇϱâ À§ÇÑ ¾Ë°í¸®ÁòÀ» Á¦½ÃÇÑ´Ù. Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀº °èÃþ ±¸Á¶ÀÇ ½Å°æ¸ÁÀ¸·Î ±¸¼ºµÈ´Ù. Á¶Çâ ¹æÀ§°¢¿¡ ´ëÇÑ ±¤´ë¿ª¿¡³ÊÁö¿Í ¹æÀ§º° Çù´ë¿ª ¿¡³ÊÁö¸¦ °ËÃâÇÏ¿© ¹ÌÁöÀÇ ¼öÁßÀ̵¿¹°Ã¼ÀÇ ÃâÇö ¹æÀ§°¢À» ÃßÁ¤ÇÏ°í À̸¦ Åä´ë·Î ¹°Ã¼¸¦ ÃßÀûÇÏ´Â ±âÁ¸ÀÇ ±â¹ýÀ¸·Î´Â ¹°Ã¼µéÀÌ ¼­·Î ÀÎÁ¢Çϰųª ±³Â÷ÇÏ´Â °æ¿ì¿¡ ÃßÀû¿¡ ½ÇÆÐÇÒ °¡´É¼ºÀÌ ³ô´Ù. ±×·¯³ª Á¦¾ÈÇÑ ¾Ë°í¸®ÁòÀ» »ç¿ëÇÏ¿© ½ÇÁ¦ ½ÅÈ£¸¦ Æ÷ÇÔÇÏ´Â ½Ã¹Ä·¹ÀÌ¼Ç ½Ã³ª¸®¿À¿¡ ´ëÇØ ¹°Ã¼ ÃßÀû ½ÇÇèÀ» ÇàÇÑ °á°ú, ƯÈ÷ ÀÎÁ¢Çϰųª ±³Â÷ÇÏ´Â ¹°Ã¼µéÀÇ ÃßÀû¿¡ ¼º°øÀûÀÎ ¼º´ÉÀ» ³ªÅ¸³»¾ú´Ù.
¿µ¹®³»¿ë
(English Abstract)
In this paper, we propose a multiple underwater object classification and tracking algorithm using the narrowband tonal and frequency line features extracted from the frequency spectrum of the acoustic signal. The general algorithm using the wideband and narrowband energy has a high tracking error when objects are close and cross each other. But the proposed algorithm shows a good tracking performance for the simulation scenarios generated by the real acoustic data.
Å°¿öµå(Keyword) underwater   object   object tracking   neural networks   tonal and frequency lines   frequency features  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå