• Journal of KIISE:Software and Applications
• /
• v.36 no.12
• /
• pp.977-985
• /
• 2009

This paper proposes a real-time algorithm for tracking the fast moving human body. Although Iterative closest point (ICP) algorithm is suitable for real-time tracking due to its efficiency and low computational complexity, ICP often fails to converge when the human body moves fast because the closest point may be mistakenly selected and trapped in a local minimum. To overcome such limitation, we combine a particle filter based on a motion history information with the ICP. The proposed human body motion tracking algorithm reduces the search space for each limb by employing a hierarchical tree structure, and enables tracking of the fast moving human bodies by using the motion prediction based on the motion history. Experimental results show that the proposed human body motion tracking provides accurate tracking performance and fast convergence rate.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.805-807
• /
• 2016

본 논문에서는 영상처리기술을 이용하여 축산농가에 설치된 카메라를 통해, 소의 움직임량을 측정하여 수정적기를 파악하는 시스템을 제안한다. 제안하는 시스템에서는 움직임 이력 영상 기법을 이용하여 시간에 따른 움직임량을 측정하였으며, 이를 통계적으로 분석하여 정확한 소의 발정 상태를 검출하게 된다.