A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection
	Wang, Min1 ; Qiao, Hong1 ; Zhang, Bo 2,3
发表期刊	IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
	2011-12-01
卷号	12 期号:4 页码:1195-1208
文章类型	Article
摘要	Manifold learning has been a popular method in many areas such as classification and recognition. In this paper, we propose a novel algorithm for pedestrian tracking based on our previous work on manifold learning. A new kind of manifold subspace is introduced, in which the intrinsic features of the target's motion can be best preserved, and the dimensionality of feature is very low. In the proposed subspace, variations of continuous pedestrian postures can be represented well by these intrinsic features. This also validates our conjecture that the movement of pedestrians can be described by some intrinsic and low-dimensional features, which are significant for tracking. Although intrinsic features are useful for tracking, algorithms that directly apply intrinsic features could not guarantee stable performance due to the influence from a complicated background. To address this issue, a foreground extraction method is introduced to enhance tracking stability by selecting the most discriminative color features to automatically distinguish the foreground from the candidate image. This preprocessing stage is proven to promote the accuracy of low-dimensional feature representation in pedestrian tracking. The whole tracking procedure, particularly dimensionality reduction, is linear and fast without complicated calculations. The experimental results validate the effectiveness of our algorithm under challenging conditions, such as a complex background, various pedestrian postures, and even occlusion.
关键词	Feature Extraction Manifold Learning Tracking
WOS标题词	Science & Technology ; Technology
关键词[WOS]	NONLINEAR DIMENSIONALITY REDUCTION ; FACE RECOGNITION ; VISUAL TRACKING ; OBJECT TRACKING ; MODELS ; LAPLACIANFACES
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000297588500025
引用统计	被引频次：17[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/3005
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
作者单位	1.Chinese Acad Sci, Lab Complex Syst & Intelligent Sci, Inst Automat, Beijing 100190, Peoples R China 2.Chinese Acad Sci, State Key Lab Sci & Engn Comp, Acad Math & Syst Sci, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Inst Appl Math, Acad Math & Syst Sci, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Wang, Min,Qiao, Hong,Zhang, Bo. A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2011,12(4):1195-1208.
APA	Wang, Min,Qiao, Hong,&Zhang, Bo.(2011).A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12(4),1195-1208.
MLA	Wang, Min,et al."A New Algorithm for Robust Pedestrian Tracking Based on Manifold Learning and Feature Selection".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 12.4(2011):1195-1208.