机构地区: 北京大学深圳研究生院集成微系统科学工程与应用重点实验室
出 处: 《智能系统学报》 2010年第2期95-105,共11页
摘 要: 随着信息技术与智能科学的迅速发展,计算机视觉已经成为IT产业和高新技术领域的前沿.视觉跟踪是当前计算机视觉领域的热点问题之一.阐述了视觉跟踪算法的研究现状,包括视觉跟踪算法的种类,常用数学方法,研究了基于区域的跟踪算法、基于模型的跟踪算法、基于特征的跟踪算法、基于主动轮廓的跟踪算法、参数估计方法和无参密度估计方法,并探讨了视觉跟踪算法的未来研究方向. Progress in information technology and intelligent systems has brought computer vision to the forefront of IT research. Visual tracking is currently one of the most active research topics in computer vision. The state of research in visual tracking algorithms was examined for this paper. The authors reviewed the common visual tracking algorithms and their main mathematical methods. The examination included region-based tracking algorithms, active contour-based tracking algorithms, feature-based tracking algorithms, model-based tracking algorithms, parameter estimate algorithms and non-parameter density estimate algorithms. Significant issues needing further study were then discussed.
领 域: [自动化与计算机技术]