摘要
提出了一种基于粒子滤波和GVF-Snake的自适应目标跟踪算法。该算法首先采用背景差分法获取目标初始轮廓,利用改进的GVF-Snake的强大搜索能力,使Snake收敛至运动目标的真实轮廓;然后根据控制点的距离增删控制点,达到自适应地跟踪运动和变形目标的目的;最后通过结合粒子滤波和改进的GVF-Snake,得到一种能量粒子滤波(EPF)目标跟踪算法,并利用提出的的跟踪策略,改进其抗遮挡能力。实验结果表明,被跟踪目标在遮挡情况下也能够保持良好的跟踪效果。
An adaptive object tracking algorithm based on particle filtering and GVF-Snake is proposed. Firstly, the original contours of the objects are acquired using the background differencing method, and the true contours of the objects can be converged by means of the powerful searching ability of GVF-Snake. Secondly, by increasing or decreasing the contour points, the proposed algorithm can track moving and deformable objects adaptively. Finally, an energetic particle filtering （EPF） object tracking algorithm is proposed by combining particle filtering and GVF-Snake, and the proposed tracking tactics can effectively overcome the occlusions. Experiments show that the proposed algorithm can realize better tracking effect even though the tracked object is occluded.
出处
《仪器仪表学报》
EI
CAS
CSCD
北大核心
2009年第4期828-833,共6页
Chinese Journal of Scientific Instrument
基金
教育部科学技术研究重点项目(205060)
江苏省高校自然科学重大基础研究项目(07KJA51006)
江苏省计算机信息处理技术重点实验室苏州大学开放基金(KJS0712)
华为公司科技基金资助项目
