摘要
讨论了一种红外图像序列的运动目标跟踪算法。以mean shift为核心,即在连续图像序列中对比运动目标的直方图。在可见光的视频中,利用目标的颜色直方图进行跟踪。在前视红外图像序列中,直方图由像素值和高通滤波后的值共同构成。为较好地处理非线性非平稳信号,引用LMS自适应滤波可以对目标的位置做出合理的估计,以维持对目标的正常的检测跟踪。
A moving object tracking algorithm for infrared image sequences is presented. This algorithm is based on mean shift tracking method, namely, comparing the histograms of moving objects in consecutive image frames. In visible light video, the color histogram of the object is used for tracking. In forward looking infrared image sequences, the histogram is constructed not only by the pixel values but also by a high-pass filtered version of the original image. In order to process effectively the nonlinear and non-steady signal, LMS adaptive filter can reasonably estimate the target position in the current image to improve the matching precision and reduce the computation.
出处
《现代防御技术》
北大核心
2009年第5期109-112,共4页
Modern Defence Technology
