基于核密度估计的前视红外小目标跟踪
DOI: 10.3969/j.issn.1006-7043.2009.07.008
Keywords: 小目标跟踪 核密度估计 局部加权灰度信息熵 模板更新
Abstract:
针对前视红外图像中小目标较难跟踪的问题,提出了一种基于核密度估计的跟踪方法.融合灰度与局部加权灰度信息熵特征,对目标模板与候选目标区域进行核密度估计,通过均值偏移算法最小化目标候选区域的核密度分布与模板的核密度分布之间的距离来实现跟踪.跟踪过程中,由于受光照、遮挡等因素影响,目标特征可能发生渐变或突变,以Bhattacharyya系数为准则,对目标模板进行自动更新,解决了不能及时更新或过更新引起跟踪失败的问题.实验验证了所提出方法能够对前视红外小目标进行鲁棒的跟踪.
| [1] | 1. BAL A.ALAM M S Automatic target tracking in FLIR image sequences 2004(5426)
|
| [2] | 2. YILMAZ A.SHAFIQUE K.SHAH M Target tracking in airborne forward looking infrared imagery 2003(7)
|
| [3] | 3. LI Z Z.JIN G.DONG N L Novel approach for tracking and recognizing dim small moving targets based on probabilistic data association filter 2007(1)
|
| [4] | 4. 杨磊.杨杰.凌建国.刘尔琦 基于背景复杂程度估计的红外图像预处理 [期刊论文] -系统工程与电子技术2006(8)
|
| [5] | 5. CHENG Y Z Mean shift,mode seeking,and clustering 1995(8)
|
| [6] | 6. COMANICIU D.RAMESH V.MEER P Kernel-based object tracking 2003(25)
|
| [7] | 7. FUKANAGA K.HOSTETLER L D The estimation of the gradient of a density function,with applications in pattern recognition 1975(1)
|
| [8] | 8. COMANICIU D.RAMESH V.MEER P Real-time tracking of non-rigid objects using mean shift 2000
|
| [9] | 9. DAWOUD A.ALAM M S.BAL A Decision fusion algorithm for target tracking in infrared imagery 2005(2)
|
Full-Text
