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

»çÀÌÆ®¸Ê

Loading..

Please wait....

Çмú´ëȸ ÇÁ·Î½Ãµù

Ȩ Ȩ > ¿¬±¸¹®Çå > Çмú´ëȸ ÇÁ·Î½Ãµù > Çѱ¹Á¤º¸Åë½ÅÇÐȸ Çмú´ëȸ > 2019³â Ãß°èÇмú´ëȸ

2019³â Ãß°èÇмú´ëȸ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) Dalal & Triggs º¸ÇàÀÚ °ËÃâ ¾Ë°í¸®ÁòÀÇ ¼º´É ºÐ¼®
¿µ¹®Á¦¸ñ(English Title) Performance Analysis of Dalal & Triggs Pedestrian Detection Algorithm
ÀúÀÚ(Author) ±è´ëȯ   ¿ÀÁ¤¼ö   Dae-hwan Kim   Jeong-su Oh  
¿ø¹®¼ö·Ïó(Citation) VOL 23 NO. 02 PP. 0518 ~ 0521 (2019. 10)
Çѱ۳»¿ë
(Korean Abstract)
Dalal°ú Triggs°¡ ¹ßÇ¥ÇÑ º¸ÇàÀÚ °ËÃâ ¾Ë°í¸®ÁòÀº ´ëÇ¥ÀûÀÎ º¸ÇàÀÚ °ËÃâ ¾Ë°í¸®ÁòÀÌ´Ù. ÀÌ ¾Ë°í¸®ÁòÀº º¸ÇàÀÚ¸¦ Ç¥ÇöÇϱâ À§ÇØ HOG Ư¡ º¤Å͸¦ »ç¿ëÇÏ°í, º¸ÇàÀÚ¿Í ºñº¸ÇàÀÚ¸¦ ºÐ·ùÇϱâ À§ÇØ HOG Ư¡ º¤Å͸¦ ÀÌ¿ëÇÑ SVM ¾Ë°í¸®ÁòÀ» »ç¿ëÇÏ°í ÀÖ´Ù. È¿À²ÀûÀÎ ¾Ë°í¸®ÁòÀÇ ±¸ÇöÀ» À§ÇØ ¸î °³ÀÇ º¯¼ö ¼³Á¤ÀÌ ¿ä±¸µÇ°í ¼³Á¤µÈ °ªµéÀº ¾Ë°í¸®Áò ¼º´É¿¡ ¿µÇâÀ» ÁØ´Ù. º» ³í¹®Àº Dalal & Triggs º¸ÇàÀÚ °ËÃâ ¾Ë°í¸®Áò¿¡¼­ º¯¼ö hitThreshold, winStride, scale, finalThresholdÀÇ ¼³Á¤ °ª¿¡ µû¸¥ º¸ÇàÀÚ °ËÃâ ¼º´ÉÀ» ºÐ¼®ÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
The pedestrian detection algorithm presented by Dalal and Triggs is a representative pedestrian detection algorithm. This algorithm uses HOG feature vectors to represent pedestrians and SVM algorithm using HOG feature vectors to classify pedestrians and non-pedestrians. Several variable settings are required to implement an efficient algorithm, and the set values affect the algorithm performance. This paper analyzes the pedestrian detection performance according to the set values of hitThreshold, winStride, scale and finalThreshold in Dalal & Triggs pedestrian detection algorithm.
Å°¿öµå(Keyword) pedestrian detection   HOG   SVM  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå