skip to main content
10.1145/3230543.3230574acmconferencesArticle/Chapter ViewAbstractPublication PagescommConference Proceedingsconference-collections
research-article
Free access

Chameleon: scalable adaptation of video analytics

Published: 07 August 2018 Publication History

Abstract

Applying deep convolutional neural networks (NN) to video data at scale poses a substantial systems challenge, as improving inference accuracy often requires a prohibitive cost in computational resources. While it is promising to balance resource and accuracy by selecting a suitable NN configuration (e.g., the resolution and frame rate of the input video), one must also address the significant dynamics of the NN configuration's impact on video analytics accuracy. We present Chameleon, a controller that dynamically picks the best configurations for existing NN-based video analytics pipelines. The key challenge in Chameleon is that in theory, adapting configurations frequently can reduce resource consumption with little degradation in accuracy, but searching a large space of configurations periodically incurs an overwhelming resource overhead that negates the gains of adaptation. The insight behind Chameleon is that the underlying characteristics (e.g., the velocity and sizes of objects) that affect the best configuration have enough temporal and spatial correlation to allow the search cost to be amortized over time and across multiple video feeds. For example, using the video feeds of five traffic cameras, we demonstrate that compared to a baseline that picks a single optimal configuration offline, Chameleon can achieve 20-50% higher accuracy with the same amount of resources, or achieve the same accuracy with only 30--50% of the resources (a 2-3X speedup).

References

[1]
Amazon aws deeplens. https://aws.amazon.com/deeplens/.
[2]
Artificial Intelligence Surveillance Cameras Security. https://www.theverge.com/2018/1/23/16907238/artificial-intelligence-surveillance-cameras-security.
[3]
AWS Lambda. https://aws.amazon.com/lambda/.
[4]
Azure Functions. https://azure.microsoft.com/en-us/services/functions/.
[5]
Google clips. https://store.google.com/us/product/google_clips?hl=en-US.
[6]
New Search Engine Revolutionizes Video Surveillance. https://i-hls.com/archives/80734.
[7]
Tensorflow detection model zoo. https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/detection_model_zoo.md.
[8]
Tensorflow-slim image classification model library. https://github.com/tensorflow/models/tree/master/research/slim.
[9]
Yolo. https://pjreddie.com/darknet/yolo/.
[10]
FFmpeg. http://ffmpeg.org/, 2000--2018.
[11]
S. Agrawal and N. Goyal. Analysis of thompson sampling for the multi-armed bandit problem. In 25th Conference on Learning Theory (COLT '12), pages 39.1--39.26, 2012.
[12]
O. Alipourfard, H. H. Liu, J. Chen, S. Venkataraman, M. Yu, and M. Zhang. Cherrypick: Adaptively unearthing the best cloud configurations for big data analytics. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI '17), pages 469--482, 2017.
[13]
G. Ananthanarayanan, V. Bahl, P. Bodik K. Chintalapudi, M. Philipose, and L. Ravindranath. Real-time video analytics - the killer app for edge computing. In IEEE Computer, 2017.
[14]
M. Everingham, L. Van Gool, C. K. Williams, J. Winn, and A. Zisserman. The pascal visual object classes (voc) challenge. International journal of computer vision, 88(2):303--338, 2010.
[15]
R. Girshick. Fast r-cnn. arXiv preprint arXiv:1504.08083, 2015.
[16]
S. Han, H. Shen, M. Philipose, S. Agarwal, A. Wolman, and A. Krishnamurthy. Mcdnn: An approximation-based execution framework for deep stream processing under resource constraints. In Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services, pages 123--136. ACM, 2016.
[17]
K. He, G. Gkioxari, P. Dollár, and R. Girshick. Mask r-cnn. In IEEE International Conference on Computer Vision (ICCV), 2017, pages 2980--2988. IEEE, 2017.
[18]
K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 770--778, 2016.
[19]
D. N. Hill, H. Nassif, Y. Liu, A. Iyer, and S. Vishwanathan. An efficient bandit algorithm for realtime multivariate optimization. In 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD '17), pages 1813--1821, 2017.
[20]
W. E. Hoover and M. Rockville. Algorithms for confidence circles and ellipses. Citeseer, 1984.
[21]
A. G. Howard, M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam. Mobilenets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861, 2017.
[22]
K. Hsieh, G. Ananthanarayanan, P. Bodik, P. Bahl, M. Philipose, P. B. Gibbons, and O. Mutlu. Focus: Querying large video datasets with low latency and low cost. arXiv preprint arXiv:1801.03493, 2018.
[23]
J. Huang, V. Rathod, C. Sun, M. Zhu, A. Korattikara, A. Fathi, I. Fischer, Z. Wojna, Y. Song, S. Guadarrama, and K. Murphy. Speed/accuracy trade-offs for modern convolutional object detectors. CoRR, abs/1611.10012, 2016.
[24]
D. Kang, J. Emmons, F. Abuzaid, P. Bailis, and M. Zaharia. Noscope: Optimizing neural network queries over video at scale. Proc. VLDB Endow., 10(11):1586--1597, Aug. 2017.
[25]
F. Loewenherz, V. Bahl, and Y. Wang. Video analytics towards vision zero. In ITE Journal, 2017.
[26]
H. Luo, A. Agarwal, and J. Langford. Efficient contextual bandits in non-stationary worlds. CoRR, abs/1708.01799, 2017.
[27]
J. Mockus. Bayesian approach to global optimization. Kluwer, Dordrecht, 1989.
[28]
F. Pukelsheim. Optimal Design of Experiments. John Wiley & Sons Inc., New York, 1993.
[29]
H. Shen, S. Han, M. Philipose, and A. Krishnamurthy. Fast video classification via adaptive cascading of deep models. In Proceedings of the IEEE conference on computer vision and pattern recognition, 2017.
[30]
C. Szegedy, S. Ioffe, V. Vanhoucke, and A. A. Alemi. Inception-v4, inception-resnet and the impact of residual connections on learning. In AAAI, volume 4, page 12, 2017.
[31]
S. Venkataraman, Z. Yang, M. Franklin, B. Recht, and I. Stoica. Ernest: Efficient performance prediction for large-scale advanced analytics. In 13th USENIX Symposium on Networked Systems Design and Implementation (NSDI '16), pages 363--378, 2016.
[32]
H. Zhang, G. Ananthanarayanan, P. Bodik, M. Philipose, P. Bahl, and M. J. Freedman. Live video analytics at scale with approximation and delay-tolerance. In NSDI, volume 9, page 1, 2017.
[33]
T. Zhang, A. Chowdhery, P. V. Bahl, K. Jamieson, and S. Banerjee. The design and implementation of a wireless video surveillance system. In Proceedings of the 21st Annual International Conference on Mobile Computing and Networking, pages 426--438. ACM, 2015.
[34]
Y. Zhu, J. Liu, M. Guo, Y. Bao, W. Ma, Z. Liu, K. Song, and Y. Yang. Bestconfig: tapping the performance potential of systems via automatic configuration tuning. In Proceedings of the 2017 Symposium on Cloud Computing, pages 338--350. ACM, 2017.

Cited By

View all
  • (2025)SmartTBD: Smart Tracking for Resource-constrained Object DetectionACM Transactions on Embedded Computing Systems10.1145/370391224:2(1-19)Online publication date: 31-Mar-2025
  • (2025)A Resource-Efficient Multiple Recognition Services Framework for IoT DevicesIEEE Transactions on Services Computing10.1109/TSC.2024.3512949(1-14)Online publication date: 2025
  • (2025)Joint Configuration Optimization and GPU Allocation for Multi-Tenant Real-Time Video Analytics on Resource-Constrained EdgeIEEE Transactions on Mobile Computing10.1109/TMC.2024.346543424:2(794-811)Online publication date: Feb-2025
  • Show More Cited By

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences
SIGCOMM '18: Proceedings of the 2018 Conference of the ACM Special Interest Group on Data Communication
August 2018
604 pages
ISBN:9781450355674
DOI:10.1145/3230543
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 August 2018

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. deep neural networks
  2. object detection
  3. video analytics

Qualifiers

  • Research-article

Conference

SIGCOMM '18
Sponsor:
SIGCOMM '18: ACM SIGCOMM 2018 Conference
August 20 - 25, 2018
Budapest, Hungary

Acceptance Rates

Overall Acceptance Rate 462 of 3,389 submissions, 14%

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)1,076
  • Downloads (Last 6 weeks)91
Reflects downloads up to 15 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2025)SmartTBD: Smart Tracking for Resource-constrained Object DetectionACM Transactions on Embedded Computing Systems10.1145/370391224:2(1-19)Online publication date: 31-Mar-2025
  • (2025)A Resource-Efficient Multiple Recognition Services Framework for IoT DevicesIEEE Transactions on Services Computing10.1109/TSC.2024.3512949(1-14)Online publication date: 2025
  • (2025)Joint Configuration Optimization and GPU Allocation for Multi-Tenant Real-Time Video Analytics on Resource-Constrained EdgeIEEE Transactions on Mobile Computing10.1109/TMC.2024.346543424:2(794-811)Online publication date: Feb-2025
  • (2025)Scrava: Super Resolution-Based Bandwidth-Efficient Cross-Camera Video AnalyticsIEEE Transactions on Mobile Computing10.1109/TMC.2024.346187924:1(293-305)Online publication date: Jan-2025
  • (2025)Argus: Enabling Cross-Camera Collaboration for Video Analytics on Distributed Smart CamerasIEEE Transactions on Mobile Computing10.1109/TMC.2024.345940924:1(117-134)Online publication date: Jan-2025
  • (2024)TileClipperProceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference10.5555/3691992.3692051(967-984)Online publication date: 10-Jul-2024
  • (2024)VulcanProceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation10.5555/3691825.3691902(1385-1402)Online publication date: 16-Apr-2024
  • (2024)MadEyeProceedings of the 21st USENIX Symposium on Networked Systems Design and Implementation10.5555/3691825.3691856(549-568)Online publication date: 16-Apr-2024
  • (2024)Task Offloading Strategy for Unmanned Aerial Vehicle Power Inspection Based on Deep Reinforcement LearningSensors10.3390/s2407207024:7(2070)Online publication date: 24-Mar-2024
  • (2024)Modeling and Performance Analysis of a Notification-Based Method for Processing Video Queries on the FlyApplied Sciences10.3390/app1409356614:9(3566)Online publication date: 24-Apr-2024
  • Show More Cited By

View Options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

Login options

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media