research-article

Open access

DeepDish on a diet: low-latency, energy-efficient object-detection and tracking at the edge

Authors:

Matthew Danish,

Justas Brazauskas,

Richard MortierAuthors Info & Claims

EdgeSys '22: Proceedings of the 5th International Workshop on Edge Systems, Analytics and Networking

Pages 43 - 48

https://doi.org/10.1145/3517206.3526273

Published: 05 April 2022 Publication History

Abstract

Intelligent sensors using deep learning to comprehend video streams have become commonly used to track and analyse the movement of people and vehicles in public spaces. The models and hardware become more powerful at regular and frequent intervals. However, this computational marvel has come at the expense of heavy energy usage. If intelligent sensors are to become ubiquitous, such as being installed at every junction and frequently along every street in a city, then their power draw will become non-trivial, posing a severe downside to their usage. We explore Multi-Object Tracking (MOT) solutions based on our custom system that use less power while still maintaining reasonable accuracy.

References

[1]

2020. EfficientNet-Lite. https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet/lite

[2]

Kittipat Apicharttrisorn, Xukan Ran, Jiasi Chen, Srikanth V Krishnamurthy, and Amit K Roy-Chowdhury. 2019. Frugal following: power thrifty object detection and tracking for mobile augmented reality. In Proceedings of the 17th Conference on Embedded Networked Sensor Systems. 96--109.

Digital Library

[3]

Gioele Ciaparrone, Francisco Luque Sánchez, Siham Tabik, Luigi Troiano, Roberto Tagliaferri, and Francisco Herrera. 2019. Deep learning in video multi-object tracking: a survey. Neurocomputing (2019).

[4]

Matthew Danish, Justas Brazauskas, Rob Bricheno, Ian Lewis, and Richard Mortier. 2020. DeepDish: multi-object tracking with an off-the-shelf Raspberry Pi. In Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking. 37--42.

Digital Library

[5]

Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi, Qingming Huang, and Qi Tian. 2019. Centernet: Keypoint triplets for object detection. In Proceedings of the IEEE/CVF international conference on computer vision. 6569--6578.

[6]

Mauro Fernández-Sanjurjo, Manuel Mucientes, and Victor Manuel Brea. 2021. Real-time multiple object visual tracking for embedded GPU systems. IEEE Internet of Things Journal 8, 11 (2021), 9177--9188.

[7]

John Heidemann and Ramesh Govindan. 2004. An overview of embedded sensor networks. Handbook of Networked and Embedded Control Systems (2004), 1--20.

[8]

Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: efficient convolutional neural networks for mobile vision applications. CoRR abs/1704.04861 (2017). arXiv:1704.04861

[9]

Kirsten Lamb. 2019. Principle-based digital twins. (2019).

[10]

L. Leal-Taixé, A. Milan, I. Reid, S. Roth, and K. Schindler. 2015. MOTChallenge 2015: Towards a Benchmark for Multi-Target Tracking. arXiv:1504.01942 [cs] (April 2015). arXiv: 1504.01942.

[11]

Youngwan Lee, Joong-won Hwang, Sangrok Lee, Yuseok Bae, and Jongyoul Park. 2019. An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops.

[12]

Ivan Lujic, Vincenzo De Maio, Klaus Pollhammer, Ivan Bodrozic, Josip Lasic, and Ivona Brandic. 2021. Increasing traffic safety with real-time edge analytics and 5G. In Proceedings of the 4th International Workshop on Edge Systems, Analytics and Networking. 19--24.

Digital Library

[13]

Keely Portway. 2021. Smarter cities in sight: Keely Portway finds out how imaging is helping keep cyclists and pedestrians safe. Imaging and Machine Vision Europe 103 (2021), 16--20.

[14]

Springer 2016. MARS: a video benchmark for large-scale person re-identification. Springer.

[15]

Mingxing Tan and Quoc Le. 2019. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning. PMLR, 6105--6114.

[16]

Ultralytics. 2021. YOLOv5. https://github.com/ultralytics/yolov5

[17]

Nicolai Wojke and Alex Bewley. 2018. Deep cosine metric learning for person re-identification. In 2018 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, 748--756.

[18]

Nicolai Wojke, Alex Bewley, and Dietrich Paulus. 2017. Simple online and realtime tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP). IEEE, 3645--3649.

Digital Library

[19]

Xiaofan Zhang, Haoming Lu, Cong Hao, Jiachen Li, Bowen Cheng, Yuhong Li, Kyle Rupnow, Jinjun Xiong, Thomas Huang, Honghui Shi, et al. 2020. SkyNet: a hardware-efficient method for object detection and tracking on embedded systems. Proceedings of Machine Learning and Systems 2 (2020), 216--229.

Cited By

ElTobgui RZayer FIacoponi SDe Masi GRenda FDias J(2024)Towards Efficient Underwater Robotic Swarms: Edge-Based Comparative Analysis of Multi-Object TrackersOCEANS 2024 - Singapore10.1109/OCEANS51537.2024.10682269(1-7)Online publication date: 15-Apr-2024
https://doi.org/10.1109/OCEANS51537.2024.10682269
Pan WKolcun RMortier R(2023)Anonymising Video Data Collection at the Edge Using DeepDish2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)10.1109/HPSR57248.2023.10147953(7-13)Online publication date: 5-Jun-2023
https://doi.org/10.1109/HPSR57248.2023.10147953

Index Terms

DeepDish on a diet: low-latency, energy-efficient object-detection and tracking at the edge
1. Computer systems organization
  1. Embedded and cyber-physical systems
    1. Sensor networks
2. Computing methodologies
  1. Artificial intelligence
    1. Computer vision

Recommendations

Robust object tracking via multi-cue fusion

A long-term object tracking method based on calibrated binocular cameras by fusing information of the two channels and binocular geometry constraints is proposed.The stereo filter which is built based on the epipolar geometry of the binocular cameras is ...
Vision-based navigation of an unmanned surface vehicle with object detection and tracking abilities

The paper discusses autocalibration, object detection, and object tracking for unmanned surface vehicles. Input data are recorded with a wide-baseline stereo vision system providing accuracy for distance estimations. The paper reports about followed ...
Moving vehicle tracking based on improved tracking–learning–detection algorithm

This study addresses the tracking–learning–detection (TLD) algorithm for long‐term single‐target tracking of moving vehicle from video streams. The problems leading to tracking failures in existing TLD methods are discovered, and an improved TLD (ITLD) ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

EdgeSys '22: Proceedings of the 5th International Workshop on Edge Systems, Analytics and Networking

April 2022

67 pages

ISBN:9781450392532

DOI:10.1145/3517206

General Chairs:
Aaron Ding
TU Delft, Netherlands
,
Volker Hilt
Nokia Bell Labs, Germany

Copyright © 2022 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGOPS: ACM Special Interest Group on Operating Systems

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 05 April 2022

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

Innovate UK

Conference

EuroSys '22

Sponsor:

SIGOPS

EuroSys '22: Seventeenth European Conference on Computer Systems

April 5 - 8, 2022

Rennes, France

Acceptance Rates

Overall Acceptance Rate 10 of 23 submissions, 43%

Upcoming Conference

EuroSys '25

Sponsor:
sigops

Twentieth European Conference on Computer Systems

March 30 - April 3, 2025

Rotterdam , Netherlands

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

1
Total Citations
View Citations
530
Total Downloads

Downloads (Last 12 months)138
Downloads (Last 6 weeks)18

Reflects downloads up to 12 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

ElTobgui RZayer FIacoponi SDe Masi GRenda FDias J(2024)Towards Efficient Underwater Robotic Swarms: Edge-Based Comparative Analysis of Multi-Object TrackersOCEANS 2024 - Singapore10.1109/OCEANS51537.2024.10682269(1-7)Online publication date: 15-Apr-2024
https://doi.org/10.1109/OCEANS51537.2024.10682269
Pan WKolcun RMortier R(2023)Anonymising Video Data Collection at the Edge Using DeepDish2023 IEEE 24th International Conference on High Performance Switching and Routing (HPSR)10.1109/HPSR57248.2023.10147953(7-13)Online publication date: 5-Jun-2023
https://doi.org/10.1109/HPSR57248.2023.10147953

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents