Title :
Violent video detection based on MoSIFT feature and sparse coding
Author :
Long Xu ; Chen Gong ; Jie Yang ; Qiang Wu ; Lixiu Yao
Author_Institution :
Instn. of Image Process. & Pattern Recognition, Shanghai Jiao Tong Univ., Shanghai, China
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 :
image denoising; object detection; spatiotemporal phenomena; transforms; video coding; BoW model; KDE; MoSIFT descriptor; MoSIFT feature; bag-of-words model; discriminative video feature; feature noise elimination; feature selection; feature vector; kernel density estimation; local spatio-temporal description; motion SIFT algorithm; quantization error; query video; scale-invariant feature transform; sparse coding scheme; video description method; violent video detection; visual word; Dictionaries; Encoding; Feature extraction; Image coding; Kernel; Probability density function; Vectors; Motion SIFT; kernel density estimation; max pooling; sparse coding; violent video detection;
Conference_Titel :
Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on
Conference_Location :
Florence
DOI :
10.1109/ICASSP.2014.6854259