基于Co-Training的协同目标跟踪  

Collaborative Object Tracking Based on Co-Training

作　　者：王路[1] 卓晴[1] 王文渊[1] 

机构地区：[1]清华大学自动化系,北京100084

出　　处：《计算机工程》2009年第3期202-204,共3页Computer Engineering

摘　　要：运动目标跟踪是计算机视觉的核心问题之一,广泛应用于诸多领域。该文提出一种基于Co-Training半监督学习框架的目标跟踪方法。该方法融合2种互相独立的特征信息来描述目标模型,采用Co-Training来协同更新模型,有效避免了现有方法的误差累积问题。实验结果证明,该方法在复杂场景下仍能实现稳定有效的跟踪。Moving object tracking is a key problem in computer vision and has many applications in various fields. This paper proposes a collaborative tracking method based on Co-Training frame work. The method fuses information from two types of features space to describe the object. The model is updated with Co-Training, which avoids the error accumulation problem. The experiment demonstrates the performance of the method under complex scenarios.

关 键 词：目标跟踪 联合训练 半监督学习 特征融合 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]