Global and Local Training for Moving Object Classification in Surveillance-Oriented Scene

CASIA OpenIR > 智能感知与计算研究中心

	Global and Local Training for Moving Object Classification in Surveillance-Oriented Scene
	Xin Zhao; Jianwei Ding; Kaiqi Huang; Tieniu Tan
	2011
会议名称	The First Asian Conference on Pattern Recognition
会议录名称	Pattern Recognition, 2011
页码	681-685
会议日期	2011
会议地点	Beijing, China
摘要	This paper presents a new training framework for multi-class moving object classification in surveillance-oriented scene. In many practical multi-class classification tasks, the instances are close to each other in the input feature space when they have similar features. These instances may have different class labels. Since the moving objects may have various view and shape, the above phenomenon is common in multi-class moving object classification. In our framework, firstly the input feature space is divided into several local clusters. Then, global training and local training are carried out sequential with an efficient online learning based algorithm. The induced global classifier is used to assign candidate instances to the most reliable clusters. Meanwhile, the trained local classifiers within those clusters can determine which classes the candidate instances belong to. Our experimental results illustrate the effectiveness of our method for moving object classification in surveillance-oriented scene.
关键词	Image Classification image Motion Analysis learning (Artificial Intelligence
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12694
专题	智能感知与计算研究中心
通讯作者	Kaiqi Huang
作者单位	中国科学院自动化研究所
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Xin Zhao,Jianwei Ding,Kaiqi Huang,et al. Global and Local Training for Moving Object Classification in Surveillance-Oriented Scene[C],2011:681-685.