Real Time Mean Shift Tracking using Optical Flow Distribution
Real Time Mean Shift Tracking using Optical Flow Distribution
复制标题
使用光流分布的实时均值漂移跟踪
DOI：
10.1109/sice.2006.314969
复制
发表时间：
2006
期刊：
影响因子：
--
通讯作者：
Ryosuke Konishi
中科院分区：
文献类型：
--
作者：
N. Oshima;Takeshi Saitoh;Ryosuke Konishi
介绍了一种基于Mean Shift跟踪算法的实时目标跟踪方法。Mean Shift跟踪算法是一种通过图像跟踪目标的有效技术。提出了一种基于颜色分布的彩色图像的Mean Shift跟踪方法。近红外摄像机与监控系统一起使用，以便在黑暗中拍摄。在红外等低对比度图像中，目标目标的跟踪比较困难。为了克服这个问题，我们的想法是考虑光流分布。该方法综合了颜色、流量值和流向三种分布。对彩色图像和红外图像进行了实验，并与原方法进行了比较。实验结果表明，该方法能够对低对比度图像中的目标进行跟踪
This paper describes about real-time object tracking method based on mean shift tracking algorithm. The mean shift tracking algorithm is an efficient technique for tracking object through an image. The original mean shift tracking is proposed to apply the color image based on the color distribution. A near-infrared camera is used with surveillance system to take in the dark. It is difficult to track the target object in the low contrast image such as the infrared image. To overcome this problem, our idea is to consider optical flow distribution. The proposed method is integrated three distributions (color, flow magnitude and flow direction). Experiments were conducted for the color image and the infrared image compared with the original method. It is shown that our method is able to track a target object in the low contrast image