• 한국전자통신학회논문지
• /
• 제10권2호
• /
• pp.183-188
• /
• 2015

본 논문에서는 야간 CCTV 영상을 활용하여 보행자를 검출하고 추적하는 방법을 제안하고 추적 성능을 분석한다. 유사 Haar 특징을 이용하여 Adaboost 알고리즘으로 학습하고 종속분류기로 객체를 검출한다. 파티클 필터를 활용하여 검출된 보행자를 추적한다. 야간 CCTV영상에 대하여 파티클 필터의 객체 추적에 효율적인 파티클 수와 분포를 실험을 통하여 제시하였다. 골목길 등에서 취득한 야간 CCTV영상에 대하여 검출과 추적성능을 검증하였다.

• 한국환경과학회지
• /
• 제24권4호
• /
• pp.359-369
• /
• 2015

This study analyzed the velocimetry of runoff and measured the flood discharge by applying the SIV (Surface Image Velocimetrer) to the daytime and nighttime flow image data with special reference to Seong-eup Bridge at Cheonmi stream of Jeju during the flow by the severe rainstorm on May 27, 2013. A 1000W lighting apparatus with more than 150 lux was installed in order to collect proper nighttime flow image applied to the SIV. Its value was compared and analyzed with the velocity value of the fixed electromagnetic wave surface velocimetry (Kalesto) at the same point to check the accuracy and applicability of the measured velocity of flow. As a result, determination coefficient $R^2$ values were 0.891 and 0.848 respectively in line with the velocity distribution of the daytime and nighttime image and the flow volume measured with Kalesto was approximately 18.2% larger than the value measured with the SIV.