Real-time multi-camera video analytics system on GPU

In this article, parallel implementation of a real-time intelligent video surveillance system on Graphics Processing Unit (GPU) is described. The system is based on background subtraction and composed of motion detection, camera sabotage detection (moved camera, out-of-focus camera and covered camera detection), abandoned object detection, and object-tracking algorithms. As the algorithms have different characteristics, their GPU implementations have different speed-up rates. Test results show that when all the algorithms run concurrently, parallelization in GPU makes the system up to 21.88 times faster than the central processing unit counterpart, enabling real-time analysis of higher number of cameras.

[1]  Takeo Kanade,et al.  A System for Video Surveillance and Monitoring , 2000 .

[2]  Dar-Shyang Lee,et al.  Effective Gaussian mixture learning for video background subtraction , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Saturnino Maldonado-Bascón,et al.  Automatic Control of Video Surveillance Camera Sabotage , 2007, IWINAC.

[4]  Alptekin Temizel,et al.  Real-Time Adaptive Camera Tamper Detection for Video Surveillance , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[5]  Amir Fijany,et al.  Fast implementation of dense stereo vision algorithms on a highly parallel SIMD architecture , 2011, Journal of Real-Time Image Processing.

[6]  Massimo Massa,et al.  A New Method for Real Time Abandoned Object Detection and Owner Tracking , 2006, 2006 International Conference on Image Processing.

[7]  Takeshi Takaki,et al.  500-fps face tracking system , 2012, Journal of Real-Time Image Processing.

[8]  Nazife Baykal,et al.  THERMAL AND VISIBLE BAND IMAGE FUSION FOR ABANDONED OBJECT DETECTION , 2010 .

[9]  Alptekin Temizel,et al.  A continuous object tracking system with stationary and moving camera modes , 2012, Other Conferences.

[10]  Z. Zivkovic.  Improved adaptive Gaussian mixture model for background subtraction , 2004, ICPR 2004.

[11]  Hélène Laurent,et al.  Comparative study of background subtraction algorithms , 2010, J. Electronic Imaging.

[12]  Bedřich Beneš,et al.  Connected Component Labeling in CUDA , 2011 .

[13]  José María Martínez Sanchez,et al.  Robust Unattended and Stolen Object Detection by Fusing Simple Algorithms , 2008, 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.

[14]  Yuri Ivanov,et al.  Robust Abandoned Object Detection Using Dual Foregrounds , 2008, EURASIP J. Adv. Signal Process..

[15]  Liang Tang,et al.  A new parallel particle filter face tracking method based on heterogeneous system , 2011, Journal of Real-Time Image Processing.

[16]  Fatih Omruuzun,et al.  Experiences on Image and Video Processing with CUDA and OpenCL , 2011 .

[17]  Yi-Ping Hung,et al.  Efficient hierarchical method for background subtraction , 2007, Pattern Recognit..

[18]  Anton Obukhov,et al.  Discrete Cosine Transform for 8x8 Blocks with CUDA , 2008 .

[19]  Yiğithan Dedeoğlu,et al.  Moving object detection, tracking and classification for smart video surveillance , 2004 .

[20]  Osama Masoud,et al.  Real-Time Detection of Camera Tampering , 2006, 2006 IEEE International Conference on Video and Signal Based Surveillance.

[21]  Lucia Maddalena,et al.  A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications , 2008, IEEE Transactions on Image Processing.

[22]  Zoran Zivkovic,et al.  Improved adaptive Gaussian mixture model for background subtraction , 2004, Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004..

[23]  Rita Cucchiara,et al.  Detecting objects, shadows and ghosts in video streams by exploiting color and motion information , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[24]  Alptekin Temizel,et al.  Abandoned object detection using thermal and visible band image fusion , 2010, 2010 IEEE 18th Signal Processing and Communications Applications Conference.

[25]  Alptekin Temizel,et al.  Adaptive mean-shift for automated multi object tracking , 2012 .

[26]  Hoai Bac Le,et al.  GPU Implementation of Extended Gaussian Mixture Model for Background Subtraction , 2010, 2010 IEEE RIVF International Conference on Computing & Communication Technologies, Research, Innovation, and Vision for the Future (RIVF).

[27]  Mubarak Shah,et al.  MinGPU: a minimum GPU library for computer vision , 2008, Journal of Real-Time Image Processing.