High performance video processing in cloud data centres

Muhammad Usman Yaseen, Muhammad Sarim Zafar, Ashiq Anjum, Richard Hill

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Citations (Scopus)

Abstract

Mobile phones and affordable cameras are generating large amounts of video data. This data holds information regarding several activities and incidents. Video analytics systems have been introduced to extract valuable information from this data. However, most of these systems are expensive, require human supervision and are time consuming. The probability of extracting inaccurate information is also high due to human involvement. We have addressed these challenges by proposing a cloud based high performance video analytics platform. This platform attempts to minimize human intervention, reduce computation time and enables the processing of a large number of video streams. It achieves high performance by optimizing the occupancy of GPU resources in cloud and minimizing the data transfer by concurrently processing a large number of video streams. The proposed video processing platform is evaluated in three stages. The first evaluation was performed at the cloud level in order to evaluate the scalability of the platform. This evaluation includes fetching and distributing video streams and efficiently utilizing available resources within the cloud. The second valuation was performed at the individual cloud nodes. This evaluation includes measuring the occupancy level, effect of data transfer and the extent of concurrency achieved at each node. The third evaluation was performed at the frame level in order to determine the performance of object recognition algorithms. To measure this, compute intensive tasks of the Local Binary Pattern (LBP) algorithm have been ported on to the GPU resources. The platform proved to be very scalable with high throughput and performance when tested on a large number of video streams with increasing number of nodes.

Original languageEnglish
Title of host publicationProceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages180-189
Number of pages10
ISBN (Electronic)9781509022533
DOIs
Publication statusPublished - 18 May 2016
Externally publishedYes
Event10th International IEEE Symposium on Service-Oriented System Engineering: IEEE International Workshop - Oxford, United Kingdom
Duration: 29 Mar 20161 Apr 2016

Conference

Conference10th International IEEE Symposium on Service-Oriented System Engineering
Abbreviated titleSOSE 2016
CountryUnited Kingdom
CityOxford
Period29/03/161/04/16

Fingerprint

Data transfer
Processing
Object recognition
Mobile phones
Scalability
Cameras
Throughput
Graphics processing unit

Cite this

Yaseen, M. U., Zafar, M. S., Anjum, A., & Hill, R. (2016). High performance video processing in cloud data centres. In Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016 (pp. 180-189). [7473021] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SOSE.2016.56
Yaseen, Muhammad Usman ; Zafar, Muhammad Sarim ; Anjum, Ashiq ; Hill, Richard. / High performance video processing in cloud data centres. Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 180-189
@inproceedings{63fbc621b4eb4f3697720ef1b522c450,
title = "High performance video processing in cloud data centres",
abstract = "Mobile phones and affordable cameras are generating large amounts of video data. This data holds information regarding several activities and incidents. Video analytics systems have been introduced to extract valuable information from this data. However, most of these systems are expensive, require human supervision and are time consuming. The probability of extracting inaccurate information is also high due to human involvement. We have addressed these challenges by proposing a cloud based high performance video analytics platform. This platform attempts to minimize human intervention, reduce computation time and enables the processing of a large number of video streams. It achieves high performance by optimizing the occupancy of GPU resources in cloud and minimizing the data transfer by concurrently processing a large number of video streams. The proposed video processing platform is evaluated in three stages. The first evaluation was performed at the cloud level in order to evaluate the scalability of the platform. This evaluation includes fetching and distributing video streams and efficiently utilizing available resources within the cloud. The second valuation was performed at the individual cloud nodes. This evaluation includes measuring the occupancy level, effect of data transfer and the extent of concurrency achieved at each node. The third evaluation was performed at the frame level in order to determine the performance of object recognition algorithms. To measure this, compute intensive tasks of the Local Binary Pattern (LBP) algorithm have been ported on to the GPU resources. The platform proved to be very scalable with high throughput and performance when tested on a large number of video streams with increasing number of nodes.",
keywords = "Cloud Computing, High Performance and GPUs, Video analytics, Video Processing",
author = "Yaseen, {Muhammad Usman} and Zafar, {Muhammad Sarim} and Ashiq Anjum and Richard Hill",
year = "2016",
month = "5",
day = "18",
doi = "10.1109/SOSE.2016.56",
language = "English",
pages = "180--189",
booktitle = "Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Yaseen, MU, Zafar, MS, Anjum, A & Hill, R 2016, High performance video processing in cloud data centres. in Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016., 7473021, Institute of Electrical and Electronics Engineers Inc., pp. 180-189, 10th International IEEE Symposium on Service-Oriented System Engineering, Oxford, United Kingdom, 29/03/16. https://doi.org/10.1109/SOSE.2016.56

High performance video processing in cloud data centres. / Yaseen, Muhammad Usman; Zafar, Muhammad Sarim; Anjum, Ashiq; Hill, Richard.

Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 180-189 7473021.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - High performance video processing in cloud data centres

AU - Yaseen, Muhammad Usman

AU - Zafar, Muhammad Sarim

AU - Anjum, Ashiq

AU - Hill, Richard

PY - 2016/5/18

Y1 - 2016/5/18

N2 - Mobile phones and affordable cameras are generating large amounts of video data. This data holds information regarding several activities and incidents. Video analytics systems have been introduced to extract valuable information from this data. However, most of these systems are expensive, require human supervision and are time consuming. The probability of extracting inaccurate information is also high due to human involvement. We have addressed these challenges by proposing a cloud based high performance video analytics platform. This platform attempts to minimize human intervention, reduce computation time and enables the processing of a large number of video streams. It achieves high performance by optimizing the occupancy of GPU resources in cloud and minimizing the data transfer by concurrently processing a large number of video streams. The proposed video processing platform is evaluated in three stages. The first evaluation was performed at the cloud level in order to evaluate the scalability of the platform. This evaluation includes fetching and distributing video streams and efficiently utilizing available resources within the cloud. The second valuation was performed at the individual cloud nodes. This evaluation includes measuring the occupancy level, effect of data transfer and the extent of concurrency achieved at each node. The third evaluation was performed at the frame level in order to determine the performance of object recognition algorithms. To measure this, compute intensive tasks of the Local Binary Pattern (LBP) algorithm have been ported on to the GPU resources. The platform proved to be very scalable with high throughput and performance when tested on a large number of video streams with increasing number of nodes.

AB - Mobile phones and affordable cameras are generating large amounts of video data. This data holds information regarding several activities and incidents. Video analytics systems have been introduced to extract valuable information from this data. However, most of these systems are expensive, require human supervision and are time consuming. The probability of extracting inaccurate information is also high due to human involvement. We have addressed these challenges by proposing a cloud based high performance video analytics platform. This platform attempts to minimize human intervention, reduce computation time and enables the processing of a large number of video streams. It achieves high performance by optimizing the occupancy of GPU resources in cloud and minimizing the data transfer by concurrently processing a large number of video streams. The proposed video processing platform is evaluated in three stages. The first evaluation was performed at the cloud level in order to evaluate the scalability of the platform. This evaluation includes fetching and distributing video streams and efficiently utilizing available resources within the cloud. The second valuation was performed at the individual cloud nodes. This evaluation includes measuring the occupancy level, effect of data transfer and the extent of concurrency achieved at each node. The third evaluation was performed at the frame level in order to determine the performance of object recognition algorithms. To measure this, compute intensive tasks of the Local Binary Pattern (LBP) algorithm have been ported on to the GPU resources. The platform proved to be very scalable with high throughput and performance when tested on a large number of video streams with increasing number of nodes.

KW - Cloud Computing

KW - High Performance and GPUs

KW - Video analytics

KW - Video Processing

UR - http://www.scopus.com/inward/record.url?scp=84979052882&partnerID=8YFLogxK

U2 - 10.1109/SOSE.2016.56

DO - 10.1109/SOSE.2016.56

M3 - Conference contribution

SP - 180

EP - 189

BT - Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Yaseen MU, Zafar MS, Anjum A, Hill R. High performance video processing in cloud data centres. In Proceedings - 2016 IEEE Symposium on Service-Oriented System Engineering, SOSE 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 180-189. 7473021 https://doi.org/10.1109/SOSE.2016.56