Á¤º¸°úÇÐȸ ÄÄÇ»ÆÃÀÇ ½ÇÁ¦ ³í¹®Áö (KIISE Transactions on Computing Practices)
ÇѱÛÁ¦¸ñ(Korean Title) |
»ç°¢Áö¿ª°æº¸½Ã½ºÅÛÀ» À§ÇÑ ½Ç½Ã°£ ÃøÈĹæ Â÷·®°ËÃâ ¾Ë°í¸®Áò |
¿µ¹®Á¦¸ñ(English Title) |
Real-Time Side-Rear Vehicle Detection Algorithm for Blind Spot Warning Systems |
ÀúÀÚ(Author) |
À±±¤¿í
ÃÖ¼®È¯
¾È»ó¾ð
±èÁ¤±¸
ÃÖÀ±È£
Kwang-Wook Yun
Suck-Hwan Choi
Sang-Un An
Jeong-Goo Kim
Yoon-Ho Choi
°Çö¿ì
¹éÀå¿î
ÇѺ´±æ
Á¤À±¼ö
Hyunwoo Kang
Jang Woon Baek
Byung-Gil Han
Yoonsu Chung
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 23 NO. 07 PP. 0408 ~ 0416 (2017. 07) |
Çѱ۳»¿ë (Korean Abstract) |
º» ³í¹®¿¡¼´Â ÁÖÇà Áß »ç°¢Áö¿ª³»ÀÇ Â÷·®À» ºü¸£°í Á¤È®ÇÏ°Ô ½Ç½Ã°£À¸·Î °ËÃâÇÏ´Â ÃøÈĹæ Â÷·®°ËÃâ ¾Ë°í¸®ÁòÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ¾Ë°í¸®ÁòÀº ½Ç½Ã°£ 󸮸¦ À§ÇØ MCT(Modified Census Transformation) Ư¡º¤Å͸¦ ±â¹ÝÀ¸·Î ¿¡À̴ٺνºÆ® ÇнÀÀ» ÅëÇØ »ý¼ºµÇ´Â ij½ºÄÉÀÌµå ºÐ·ù±â¸¦ »ç¿ëÇÑ´Ù. MCT ºÐ·ù±â´Â °ËÃâÀ©µµ¿ì°¡ ÀÛÀ»¼ö·Ï 󸮼ӵµ°¡ ºü¸£°í, °ËÃâÀ©µµ¿ì°¡ Ŭ¼ö·Ï Á¤È®µµ°¡ Áõ°¡ÇÑ´Ù. Á¦¾È ¾Ë°í¸®ÁòÀº ÀÌ·¯ÇÑ Æ¯Â¡À» ÀÌ¿ëÇÏ¿© °ËÃâÀ©µµ¿ì°¡ ÀÛÀº ºÐ·ù±â·Î Â÷·®È常¦ ºü¸£°Ô »ý¼ºÇÑ ÈÄ º¸´Ù Å« »çÀÌÁîÀÇ °ËÃâ À©µµ¿ì¸¦ °¡Áö´Â ºÐ·ù±â·Î »ý¼ºµÈ Â÷·®Èĺ¸¿¡ ´ëÇØ Á¤È®ÇÏ°Ô Â÷·®ÀÎÁö °ËÁõÇÑ´Ù. ¶ÇÇÑ, Â÷·®ºÐ·ù±â¿Í ¹ÙÄû ºÐ·ù±â¸¦ µ¿½Ã¿¡ »ç¿ëÇÏ¿© »ç°¢Áö¿ª³»·Î ÁøÀÔÇÏ´Â Â÷·®°ú »ç°¢Áö¿ª³»ÀÇ ÀÎÁ¢Â÷·®À» È¿°úÀûÀ¸·Î °ËÃâÇÑ´Ù.
|
¿µ¹®³»¿ë (English Abstract) |
This paper proposes a real-time side-rear vehicle detection algorithm that detects vehicles quickly and accurately in blind spot areas when driving. The proposed algorithm uses a cascade classifier created by AdaBoost Learning using the MCT (modified census transformation) feature vector. Using this classifier, the smaller the detection window, the faster the processing speed of the MCT classifier, and the larger the detection window, the greater the accuracy of the MCT classifier. By considering these characteristics, the proposed algorithm uses two classifiers with different detection window sizes . The first classifier quickly generates candidates with a small detection window. The second classifier accurately verifies the generated candidates with a large detection window. Furthermore, the vehicle classifier and the wheel classifier are simultaneously used to effectively detect a vehicle entering the blind spot area, along with an adjacent vehicle in the blind spot area.
|
Å°¿öµå(Keyword) |
¹«¼± ³×Æ®¿öÅ©
WIPS
ħÀÔŽÁö
ħÀÔÂ÷´Ü
wireless network
WIPS
intrusion detection
intrusion protection
Â÷·®°ËÃâ
»ç°¢Áö¿ª°æº¸
ij½ºÄÉÀÌµå ºÐ·ù±â
¿¡À̴ٺνºÆ®
MCT(modified census transformation)
vehicle detection
blind spot
cascade classifier
AdaBoost
modified census transform
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|