Study of moving object detection in intelligent video surveillance system

With the “green”projects such as the construction of China's gradual penetration into the network video monitoring system in the maintenance of social security, the fight against crime, an increasingly prominent role. Faced with a deluge of live and recorded video content, relying solely on manual observation and to distinguish between the traditional monitoring methods can no longer meet the application requirements, needed a way to video content and the vehicles and features of the key goals of the algorithm for automatic analysis system for efficiency and engineering requirements from the point of view, target detection technology is relatively more complex, the current network video monitoring system is basically still not target detection technology into the actual intelligent video surveillance system. This paper presents a different pitch angle and different rotation angles and different axis rotation angle, the sample of HOG features direct conversion algorithm to improve the HOG test the effectiveness and robustness, to improve SVM classification results, reducing classifier training need to collect the number of positive and negative samples.

[1]  R. E. Kalman,et al.  A New Approach to Linear Filtering and Prediction Problems , 2002 .

[2]  Jianbo Shi,et al.  Detecting unusual activity in video , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[3]  T. Başar,et al.  A New Approach to Linear Filtering and Prediction Problems , 2001 .

[4]  Michael Isard,et al.  BraMBLe: a Bayesian multiple-blob tracker , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[5]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[6]  Gérard G. Medioni,et al.  Detecting and tracking moving objects for video surveillance , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[7]  M. Ibrahim Sezan,et al.  A computational approach to semantic event detection , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[8]  A. J. Lipton.  Keynote: intelligent video as a force multiplier for crime detection and prevention , 2005 .

[9]  Alan J. Lipton,et al.  Automated video protection, monitoring & detection , 2003 .

[10]  Terrance E. Boult,et al.  Frame-rate omnidirectional surveillance and tracking of camouflaged and occluded targets , 1999, Proceedings Second IEEE Workshop on Visual Surveillance (VS'99) (Cat. No.98-89223).

[11]  Dorin Comaniciu,et al.  Real-time tracking of non-rigid objects using mean shift , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).