Abnormal Behavior Recognition Based on Features Fusion

Yu Tao; Yong Chao Wei

doi:10.4028/www.scientific.net/AMR.694-697.1949

Paper Titles

The Location of Quadruped Robot with Hand-Fused-Foot Based on Binocular Vision
p.1925

Stereo Vision Based Localization Method for Intelligent Vehicle
p.1931

Real-Time Objects Detection Using Layered Codebook Model
p.1937

Algorithm Research of Two-Dimensional Size Measurement on Parts Based on Machine Vision
p.1945

Abnormal Behavior Recognition Based on Features Fusion
p.1949

A Novel Architecture of Smart Camera
p.1953

Study for Workpiece Identity Based on the BP Neural Network and the Zernike Moment
p.1958

Number and Colors Recognition for the Beaded Pad
p.1964

Research Status on Road Information Extraction from High Resolution Imagery
p.1970

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 694-697Abnormal Behavior Recognition Based on Features...

Abnormal Behavior Recognition Based on Features Fusion

Abstract:

One framework that fuses features for abnormal behavior recognition in videos was proposed, which provides increased robustness to noise and pose variation. First, ROI division of suspected pedestrian is achieved by optical flow method, which greatly reduces the dimensions of training data. After that, the proposed method uses the adaboost training to recognize pedestrian effectively. To capture the imaging variations and attributes of individuals, we use types of features: center track and inclination angle. Finally, D-S evidence theory is used to combine these features, which aims to recognize the abnormal behavior correctly. The results demonstrate that the recognition rate can be improved by the fusion of features.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 694-697)

Pages:

1949-1952

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.694-697.1949

Citation:

Cite this paper

Online since:

May 2013

Authors:

Yu Tao, Yong Chao Wei

Keywords:

Abnormal Behavior, Information Fusion, Intelligent Monitoring, Target Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Jingen Liu, Saad Ali, Mubarak Shah. Recognizing Human Actions Using Multiple Features[C].IEEE CVPR 2011.

DOI: 10.1109/cvpr.2008.4587527

Google Scholar

[2] K Schindler, L.V Gool．Action Snippets: How many frames does human action recognition require[C]．IEEE CVPR，2008．

DOI: 10.1109/cvpr.2008.4587730

Google Scholar

[3] F. Lv and R. Nevatia, Single View Human Action Recognition using Key Pose Matching and Viterbi Path Searching[C], IEEE ICCV, 2007.

DOI: 10.1109/cvpr.2007.383131

Google Scholar

[4] Y. Ke, R. Sukthankar and M. Hebert, Efficient Visual Event Detection using Volumetric Features[C], IEEE ICCV, 2005.

DOI: 10.1109/iccv.2005.85

Google Scholar

[5] E. Shechtman and M. Irani, Space-Time Behavior Based Correlation[C], IEEE CVPR, 2005.

Google Scholar

[6] J. C. Niebles,H. Wang and L. Fei-Fei, Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words[C], BMVC,2006.

DOI: 10.5244/c.20.127

Google Scholar

[7] P. Dollar, V. Rabaud, G. Cottrell and S. Belongieet, Behavior Recognition via Sparse Spatio-Temporal Features[C],IEEE International Workshop on VS-PETS, 2005.

DOI: 10.1109/vspets.2005.1570899

Google Scholar

[8] C. Carlsson, S. Carlsson and J. Sullivan, Action Recognition by Shape Matching to Key Frames[C], Workshop on Models Versus Exemplarsin Compuetr Vision, 2001.

Google Scholar

[9] G. Mori, X. Ren, A. A. Efros and J. Malik., Recovering Human Body Configurations: Combining Segmentation and Recognition[C],CVPR, 2004.

DOI: 10.1109/cvpr.2004.1315182

Google Scholar

[10] K.M. Cheung,S. Baker and T. Kanade, Shape-From-Silhouette of Articulated Objects and its Use for Human Body Kinematics Estimation and Motion Capture[C], IEEE CVPR, 2003.

DOI: 10.1109/cvpr.2003.1211340

Google Scholar