Abnormal event detection in crowded scenes using sparse representation

We propose to detect abnormal events via a sparse reconstruction over the normal bases. Given a collection of normal training examples, e.g., an image sequence or a collection of local spatio-temporal patches, we propose the sparse reconstruction cost (SRC) over the normal dictionary to measure the...

Full description

Saved in:
Bibliographic Details
Main Authors: Cong, Yang, Yuan, Junsong, Liu, Ji
Other Authors: School of Electrical and Electronic Engineering
Format: Article
Language:English
Published: 2013
Subjects:
Online Access:https://hdl.handle.net/10356/107417
http://hdl.handle.net/10220/17702
http://dx.doi.org/10.1016/j.patcog.2012.11.021
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-107417
record_format dspace
spelling sg-ntu-dr.10356-1074172019-12-06T22:30:41Z Abnormal event detection in crowded scenes using sparse representation Cong, Yang Yuan, Junsong Liu, Ji School of Electrical and Electronic Engineering DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition We propose to detect abnormal events via a sparse reconstruction over the normal bases. Given a collection of normal training examples, e.g., an image sequence or a collection of local spatio-temporal patches, we propose the sparse reconstruction cost (SRC) over the normal dictionary to measure the normalness of the testing sample. By introducing the prior weight of each basis during sparse reconstruction, the proposed SRC is more robust compared to other outlier detection criteria. To condense the over-completed normal bases into a compact dictionary, a novel dictionary selection method with group sparsity constraint is designed, which can be solved by standard convex optimization. Observing that the group sparsity also implies a low rank structure, we reformulate the problem using matrix decomposition, which can handle large scale training samples by reducing the memory requirement at each iteration from O(k2) to O(k) where k is the number of samples. We use the columnwise coordinate descent to solve the matrix decomposition represented formulation, which empirically leads to a similar solution to the group sparsity formulation. By designing different types of spatio-temporal basis, our method can detect both local and global abnormal events. Meanwhile, as it does not rely on object detection and tracking, it can be applied to crowded video scenes. By updating the dictionary incrementally, our method can be easily extended to online event detection. Experiments on three benchmark datasets and the comparison to the state-of-the-art methods validate the advantages of our method. Accepted version 2013-11-15T06:56:22Z 2019-12-06T22:30:41Z 2013-11-15T06:56:22Z 2019-12-06T22:30:41Z 2013 2013 Journal Article Cong, Y., Yuan, J., & Liu, J. (2013). Abnormal event detection in crowded scenes using sparse representation. Pattern recognition, 46(7), 1851-1864. 0031-3203 https://hdl.handle.net/10356/107417 http://hdl.handle.net/10220/17702 http://dx.doi.org/10.1016/j.patcog.2012.11.021 en Pattern recognition © 2013 Elsevier B.V. This is the author created version of a work that has been peer reviewed and accepted for publication by Pattern recognition, Elsevier B.V. It incorporates referee’s comments but changes resulting from the publishing process, such as copyediting, structural formatting, may not be reflected in this document. The published version is available at: [http://dx.doi.org/10.1016/j.patcog.2012.11.021]. application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
spellingShingle DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Cong, Yang
Yuan, Junsong
Liu, Ji
Abnormal event detection in crowded scenes using sparse representation
description We propose to detect abnormal events via a sparse reconstruction over the normal bases. Given a collection of normal training examples, e.g., an image sequence or a collection of local spatio-temporal patches, we propose the sparse reconstruction cost (SRC) over the normal dictionary to measure the normalness of the testing sample. By introducing the prior weight of each basis during sparse reconstruction, the proposed SRC is more robust compared to other outlier detection criteria. To condense the over-completed normal bases into a compact dictionary, a novel dictionary selection method with group sparsity constraint is designed, which can be solved by standard convex optimization. Observing that the group sparsity also implies a low rank structure, we reformulate the problem using matrix decomposition, which can handle large scale training samples by reducing the memory requirement at each iteration from O(k2) to O(k) where k is the number of samples. We use the columnwise coordinate descent to solve the matrix decomposition represented formulation, which empirically leads to a similar solution to the group sparsity formulation. By designing different types of spatio-temporal basis, our method can detect both local and global abnormal events. Meanwhile, as it does not rely on object detection and tracking, it can be applied to crowded video scenes. By updating the dictionary incrementally, our method can be easily extended to online event detection. Experiments on three benchmark datasets and the comparison to the state-of-the-art methods validate the advantages of our method.
author2 School of Electrical and Electronic Engineering
author_facet School of Electrical and Electronic Engineering
Cong, Yang
Yuan, Junsong
Liu, Ji
format Article
author Cong, Yang
Yuan, Junsong
Liu, Ji
author_sort Cong, Yang
title Abnormal event detection in crowded scenes using sparse representation
title_short Abnormal event detection in crowded scenes using sparse representation
title_full Abnormal event detection in crowded scenes using sparse representation
title_fullStr Abnormal event detection in crowded scenes using sparse representation
title_full_unstemmed Abnormal event detection in crowded scenes using sparse representation
title_sort abnormal event detection in crowded scenes using sparse representation
publishDate 2013
url https://hdl.handle.net/10356/107417
http://hdl.handle.net/10220/17702
http://dx.doi.org/10.1016/j.patcog.2012.11.021
_version_ 1681038028785582080