Violent video detection based on MoSIFT feature and sparse coding
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 3538-3542
Abstract
To detect violence in a video, a common video description method is to apply local spatio-temporal description on the query video. Then, the low-level description is further summarized onto the high-level feature based on Bag-of-Words (BoW) model. However, traditional spatio-temporal descriptors are not discriminative enough. Moreover, BoW model roughly assigns each feature vector to only one visual word, therefore inevitably causing quantization error. To tackle the constrains, this paper employs Motion SIFT (MoSIFT) algorithm to extract the low-level description of a query video. To eliminate the feature noise, Kernel Density Estimation (KDE) is exploited for feature selection on the MoSIFT descriptor. In order to obtain the highly discriminative video feature, this paper adopts sparse coding scheme to further process the selected MoSIFTs. Encouraging experimental results are obtained based on two challenging datasets which record both crowded scenes and non-crowded scenes.Keywords
This publication has 18 references indexed in Scilit:
- Violent flows: Real-time detection of violent crowd behavior2012
- Unsupervised feature selection by kernel density estimation in wavelet-based spike sortingBiomedical Signal Processing and Control, 2012
- LIBSVMACM Transactions on Intelligent Systems and Technology, 2011
- Violence Detection in Video Using Computer Vision Techniques2011
- Kernel density estimation via diffusionThe Annals of Statistics, 2010
- Behavior Recognition via Sparse Spatio-Temporal Features2006
- On Space-Time Interest PointsInternational Journal of Computer Vision, 2005
- Actions as space-time shapes2005
- Distinctive Image Features from Scale-Invariant KeypointsInternational Journal of Computer Vision, 2004
- Least angle regressionThe Annals of Statistics, 2004