VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAMEWORK FOR HIGH PERFORMANCE VIDEO ANALYTICS
0 likes266 views
The document presents a cloud-based video analytics framework for automated object detection and classification from large volumes of video stream data. The framework analyzes video streams uploaded to cloud storage and performs computationally intensive detection and classification using GPU servers. Testing on 21,600 video streams totaling 175GB showed the framework could analyze the data in 6.52 hours using a 15 node cloud, and analysis was twice as fast (3 hours) when using GPUs.
![CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
format. Whereas, the analysis of the same data on the 15 node cloud took a
maximum of 6.52 hours. The analysis of these video streams on 15 cloud
nodes with GPUs took 3 hours.
REFERENCES
[1] “The picture in not clear: How many surveillance cameras are there in the
UK?” Research Report, July 2013.
[2] K. Ball, D. Lyon, D. M. Wood, C. Norris, and C. Raab, “A report on the
surveillance society,” Report, September 2006.
[3] M. Gill and A. Spriggs, “Assessing the impact of CCTV,” London Home
Office Research, Development and Statistics Directorate, February 2005.
[4] S. J. McKenna and S. Gong, “Tracking colour objects using adaptive
mixture models,” Image Vision Computing, vol. 17, pp. 225–231, 1999.
[5] N. Ohta, “A statistical approach to background supression for surveillance
systems,” in International Conference on Computer Vision, 2001, pp. 481–
486.
[6] D. Koller, J. W. W. Haung, J. Malik, G. Ogasawara, B. Rao, and S. Russel,
“Towards robust automatic traffic scene analysis in real-time,” in
International conference on Pattern recognition, 1994, pp. 126–131.
[7] J. S. Bae and T. L. Song, “Image tracking algorithm using template
matching and PSNF-m,” International Journal of Control, Automation, and
Systems, vol. 6, no. 3, pp. 413–423, June 2008.](https://image.slidesharecdn.com/videostreamanalysisincloudsanobjectdetectionandclassificationframeworkforhighperformance-160722051804/85/VIDEO-STREAM-ANALYSIS-IN-CLOUDS-AN-OBJECT-DETECTION-AND-CLASSIFICATION-FRAMEWORK-FOR-HIGH-PERFORMANCE-VIDEO-ANALYTICS-3-320.jpg)
![CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249)
MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com
Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com
[8] J. Hsieh, W. Hu, C. Chang, and Y. Chen, “Shadow elimination for effective
moving object detection by gaussian shadow modeling,” Image and Vision
Computing, vol. 21, no. 3, pp. 505–516, 2003.
[9] S. Mantri and D. Bullock, “Analysis of feedforward-back propagation
neural networks used in vehicle detection,” Transportation Research Part C–
Emerging Technologies, vol. 3, no. 3, pp. 161–174, June 1995.
[10] T. Abdullah, A. Anjum, M. Tariq, Y. Baltaci, and N. Antonopoulos, “Traffic
monitoring using video analytics in clouds,” in 7th IEEE/ACM International
Conference on Utility and Cloud Computing (UCC), 2014, pp. 39–48.
[11] K. F. MacDorman, H. Nobuta, S. Koizumi, and H. Ishiguro,
“Memorybased attention control for activity recognition at a subway
station,” IEEE MultiMedia, vol. 14, no. 2, pp. 38–49, April 2007.](https://image.slidesharecdn.com/videostreamanalysisincloudsanobjectdetectionandclassificationframeworkforhighperformance-160722051804/85/VIDEO-STREAM-ANALYSIS-IN-CLOUDS-AN-OBJECT-DETECTION-AND-CLASSIFICATION-FRAMEWORK-FOR-HIGH-PERFORMANCE-VIDEO-ANALYTICS-4-320.jpg)
VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAMEWORK FOR HIGH PERFORMANCE VIDEO ANALYTICS
- 1. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com VIDEO STREAM ANALYSIS IN CLOUDS: AN OBJECT DETECTION AND CLASSIFICATION FRAMEWORK FOR HIGH PERFORMANCE VIDEO ANALYTICS ABSTRACT: Object detection and classification are the basic tasks in video analytics and become the starting point for other complex applications. Traditional video analytics approaches are manual and time consuming. These are subjective due to the very involvement of human factor. We present a cloud based video analytics framework for scalable and robust analysis of video streams. The framework empowers an operator by automating the object detection and classification process from recorded video streams. An operator only specifies an analysis criteria and duration of video streams to analyse. The streams are then fetched from a cloud storage, decoded and analysed on the cloud. The framework executes compute intensive parts of the analysis to GPU powered servers in the cloud. Vehicle and face detection are presented as two case studies for evaluating the framework, with one month of data and a 15 node cloud. The framework reliably performed object detection and classification on the data, comprising of 21,600 video streams and 175 GB in size, in 6.52 hours. The GPU enabled deployment of the framework took 3 hours to perform analysis on the same number of video streams, thus making it at least twice as fast than the cloud deployment without GPUs.
- 2. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com CONCLUSIONS The cloud based video analytics framework for automated object detection and classification is presented and evaluated in this paper. The framework automated the video stream analysis process by using a cascade classifier and laid the foundation for the experimentation of a wide variety of video analytics algorithms. The video analytics framework is robust and can cope with varying number of nodes or increased volumes of data. The time to analyse one month of video data depicted a decreasing trend with the increasing number of nodes in the cloud, as summarized in Figure 9. The analysis time of the recorded video streams decreased from 27.80 hours to 5.83 hours, when the number of nodes in the cloud varied from 3-15. The analysis time would further decrease when more nodes are added to the cloud. The larger volumes of video streams required more time to perform object detection and classification. The analysis time varied from 6.38 minutes to 5.83 hours, with the video stream data increasing from 5GB to 175GB. The time taken to analyse one month of recorded video stream data on a cloud with GPUs is shown in Figure 12. The speed up gain for the supported video formats varied according to the data transfer overheads. However, maximum speed up is observed for 4CIF video format. CIF and 4CIF video formats are mostly used for recording video streams from cameras. The analysis time for one month of recorded video stream data is summarized in Table IX. A cloud node with two GPUs mounted on it took 51 hours to analyse one month of the recorded video streams in the 4CIF
- 3. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com format. Whereas, the analysis of the same data on the 15 node cloud took a maximum of 6.52 hours. The analysis of these video streams on 15 cloud nodes with GPUs took 3 hours. REFERENCES [1] “The picture in not clear: How many surveillance cameras are there in the UK?” Research Report, July 2013. [2] K. Ball, D. Lyon, D. M. Wood, C. Norris, and C. Raab, “A report on the surveillance society,” Report, September 2006. [3] M. Gill and A. Spriggs, “Assessing the impact of CCTV,” London Home Office Research, Development and Statistics Directorate, February 2005. [4] S. J. McKenna and S. Gong, “Tracking colour objects using adaptive mixture models,” Image Vision Computing, vol. 17, pp. 225–231, 1999. [5] N. Ohta, “A statistical approach to background supression for surveillance systems,” in International Conference on Computer Vision, 2001, pp. 481– 486. [6] D. Koller, J. W. W. Haung, J. Malik, G. Ogasawara, B. Rao, and S. Russel, “Towards robust automatic traffic scene analysis in real-time,” in International conference on Pattern recognition, 1994, pp. 126–131. [7] J. S. Bae and T. L. Song, “Image tracking algorithm using template matching and PSNF-m,” International Journal of Control, Automation, and Systems, vol. 6, no. 3, pp. 413–423, June 2008.
- 4. CONTACT: PRAVEEN KUMAR. L (, +91 – 9791938249) MAIL ID: sunsid1989@gmail.com, praveen@nexgenproject.com Web: www.nexgenproject.com, www.finalyear-ieeeprojects.com [8] J. Hsieh, W. Hu, C. Chang, and Y. Chen, “Shadow elimination for effective moving object detection by gaussian shadow modeling,” Image and Vision Computing, vol. 21, no. 3, pp. 505–516, 2003. [9] S. Mantri and D. Bullock, “Analysis of feedforward-back propagation neural networks used in vehicle detection,” Transportation Research Part C– Emerging Technologies, vol. 3, no. 3, pp. 161–174, June 1995. [10] T. Abdullah, A. Anjum, M. Tariq, Y. Baltaci, and N. Antonopoulos, “Traffic monitoring using video analytics in clouds,” in 7th IEEE/ACM International Conference on Utility and Cloud Computing (UCC), 2014, pp. 39–48. [11] K. F. MacDorman, H. Nobuta, S. Koizumi, and H. Ishiguro, “Memorybased attention control for activity recognition at a subway station,” IEEE MultiMedia, vol. 14, no. 2, pp. 38–49, April 2007.