Paper Info
Title
Vector field analysis for multi-object behavior modeling
Abstract
This paper proposes an end-to-end system to recognize multi-person behaviors in video, unifying different tasks like segmentation, modeling and recognition within a single optical flow based motion analysis framework. We show how optical flow can be used for analyzing activities of individual actors, as opposed to dense crowds, which is what the existing literature has concentrated on mostly. The algorithm consists of two steps - identification of motion patterns and modeling of motion patterns. Activities are analyzed using the underlying motion patterns which are formed by the optical flow field over a period of time. Streaklines are used to capture these motion patterns via integration of the flow field. To recognize the regions of interest, we utilize the Helmholtz decomposition to compute the divergence potential. The extrema or critical points of this potential indicates regions of high activity in the video, which are then represented as motion patterns by clustering the streaklines. We then present a method to compare two videos by measuring the similarity between their motion patterns using a combination of shape theory and subspace analysis. Such an analysis allows us to represent, compare and recognize a wide range of activities. We perform experiments on state-of-the-art datasets and show that the proposed method is suitable for natural videos in the presence of noise, background clutter and high intra class variations. Our method has two significant advantages over recent related approaches - it provides a single framework that takes care of both low-level and high-level visual analysis tasks, and is computationally efficient.
Year
DOI
Venue
2013
10.1016/j.imavis.2012.08.011
Image Vision Comput.
Keywords
Field
DocType
optical flow field,flow field,motion analysis framework,multi-object behavior modeling,single optical flow,underlying motion pattern,high-level visual analysis task,motion pattern,optical flow,vector field analysis,subspace analysis
Computer vision,Pattern recognition,Subspace topology,Segmentation,Computer science,Maxima and minima,Helmholtz decomposition,Artificial intelligence,Motion estimation,Motion analysis,Cluster analysis,Optical flow
Journal
Volume
Issue
ISSN
31
6-7
0262-8856
Citations 
PageRank 
References 
4
0.40
23
Authors
3
Name
Order
Citations
PageRank
Nandita M. Nayak1784.68
Yingying Zhu241026.41
Amit K. Roy Chowdhury3115373.96