PMID- 30281588
OWN - NLM
STAT- MEDLINE
DCOM- 20190306
LR  - 20190306
IS  - 1932-6203 (Electronic)
IS  - 1932-6203 (Linking)
VI  - 13
IP  - 10
DP  - 2018
TI  - Violence detection in surveillance video using low-level features.
PG  - e0203668
LID - 10.1371/journal.pone.0203668 [doi]
LID - e0203668
AB  - It is very important to automatically detect violent behaviors in video 
      surveillance scenarios, for instance, railway stations, gymnasiums and 
      psychiatric centers. However, the previous detection methods usually extract 
      descriptors around the spatiotemporal interesting points or extract statistic 
      features in the motion regions, leading to limited abilities to effectively 
      detect video-based violence activities. To address this issue, we propose a novel 
      method to detect violence sequences. Firstly, the motion regions are segmented 
      according to the distribution of optical flow fields. Secondly, in the motion 
      regions, we propose to extract two kinds of low-level features to represent the 
      appearance and dynamics for violent behaviors. The proposed low-level features 
      are the Local Histogram of Oriented Gradient (LHOG) descriptor extracted from RGB 
      images and the Local Histogram of Optical Flow (LHOF) descriptor extracted from 
      optical flow images. Thirdly, the extracted features are coded using Bag of Words 
      (BoW) model to eliminate redundant information and a specific-length vector is 
      obtained for each video clip. At last, the video-level vectors are classified by 
      Support Vector Machine (SVM). Experimental results on three challenging benchmark 
      datasets demonstrate that the proposed detection approach is superior to the 
      previous methods.
FAU - Zhou, Peipei
AU  - Zhou P
AUID- ORCID: 0000-0003-1370-5627
AD  - Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 
      Province, China.
AD  - University of Chinese Academy of Sciences, Beijing, China.
AD  - Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, Liaoning 
      Province, China.
AD  - The Key Lab of Image Understanding and Computer Vision, Liaoning Province, China.
FAU - Ding, Qinghai
AU  - Ding Q
AD  - Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 
      Province, China.
AD  - Space Star Technology Company Limited, Beijing, China.
FAU - Luo, Haibo
AU  - Luo H
AD  - Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 
      Province, China.
AD  - Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, Liaoning 
      Province, China.
AD  - The Key Lab of Image Understanding and Computer Vision, Liaoning Province, China.
FAU - Hou, Xinglin
AU  - Hou X
AD  - Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang, Liaoning 
      Province, China.
AD  - University of Chinese Academy of Sciences, Beijing, China.
AD  - Key Laboratory of Opto-Electronic Information Processing, CAS, Shenyang, Liaoning 
      Province, China.
AD  - The Key Lab of Image Understanding and Computer Vision, Liaoning Province, China.
LA  - eng
PT  - Journal Article
DEP - 20181003
PL  - United States
TA  - PLoS One
JT  - PloS one
JID - 101285081
SB  - IM
MH  - Algorithms
MH  - Humans
MH  - Motion
MH  - Pattern Recognition, Automated/*methods
MH  - Support Vector Machine
MH  - *Video Recording
MH  - Violence/*psychology
PMC - PMC6169868
COIS- We have the following interests: Author Qinghai Ding is employed by Space Star 
      Technology Company Limited. There are no patents, products in development or 
      marketed products to declare involving this manuscript. This does not alter our 
      adherence to all the PLOS ONE policies on sharing data and materials.
EDAT- 2018/10/04 06:00
MHDA- 2019/03/07 06:00
PMCR- 2018/10/03
CRDT- 2018/10/04 06:00
PHST- 2017/10/26 00:00 [received]
PHST- 2018/08/26 00:00 [accepted]
PHST- 2018/10/04 06:00 [entrez]
PHST- 2018/10/04 06:00 [pubmed]
PHST- 2019/03/07 06:00 [medline]
PHST- 2018/10/03 00:00 [pmc-release]
AID - PONE-D-17-38284 [pii]
AID - 10.1371/journal.pone.0203668 [doi]
PST - epublish
SO  - PLoS One. 2018 Oct 3;13(10):e0203668. doi: 10.1371/journal.pone.0203668. 
      eCollection 2018.