Abstract | ||
---|---|---|
This paper proposes a new method for abnormal behavior detection in surveillance videos via sparse reconstruction analysis. The motion trajectories of objects are firstly defined as fixed-length parametric vectors based on approximating cubic B-spline curves. Then the vectors are classified as behavior patterns and finally distinguished between normal and abnormal behaviors based on sparse reconstruction analysis, in which a classifier is constructed with sparse linear reconstruction coefficients by computing L1-norm minimization and sparse reconstruction residuals learning from labeled training samples. Experimental results on public dataset show the effectiveness of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ICIG.2011.104 | ICIG |
Keywords | Field | DocType |
vector classification,sparse reconstruction residuals learning,cubic b-spline curve approximation,approximation theory,l1-norm minimization,sparse reconstruction,abnormal behavior detection,behavior pattern,fixed-length parametric vector,trajectory analysis,sparse linear reconstruction coefficient,image reconstruction,sparse reconstruction analysis,image classification,trajectory representation,surveillance videos,motion trajectory,splines (mathematics),cubic b-spline curve,abnormal behavior,fixed-length parametric,vectors,behavior detection,video surveillance,image motion analysis,trajectory,spline,support vector machine,minimization | Iterative reconstruction,Spline (mathematics),Computer vision,Pattern recognition,Computer science,Sparse approximation,Approximation theory,Parametric statistics,Artificial intelligence,Contextual image classification,Classifier (linguistics),Trajectory | Conference |
ISBN | Citations | PageRank |
978-0-7695-4541-7 | 20 | 0.70 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ce Li | 1 | 37 | 8.03 |
Zhenjun Han | 2 | 176 | 16.40 |
Qixiang Ye | 3 | 913 | 64.51 |
Jianbin Jiao | 4 | 367 | 32.61 |