PETRI: Reducing Bandwidth Requirement in Smart Surveillance by Edge-Cloud Collaborative Adaptive Frame Clustering and Pipelined Bidirectional Tracking

Neural networks running on cloud servers have been widely used in smart surveillance, but they require high bandwidth to upload videos. Edge-cloud collaborative encoding based on ROI (Region-Of-Interest) can reduce bandwidth requirement, but it suffers from inaccurate ROI detection due to feedback l...

Full description

Saved in:
Bibliographic Details
Published in:2021 58th ACM/IEEE Design Automation Conference (DAC) pp. 421 - 426
Main Authors: Liu, Ruoyang, Zhang, Lu, Wang, Jingyu, Yang, Huazhong, Liu, Yongpan
Format: Conference Proceeding
Language:English
Published: IEEE 05.12.2021
Subjects:
Bandwidth
Collaboration
collaborative architecture
edge computing
Image edge detection
Object detection
Pipelines
Surveillance
Target tracking
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Neural networks running on cloud servers have been widely used in smart surveillance, but they require high bandwidth to upload videos. Edge-cloud collaborative encoding based on ROI (Region-Of-Interest) can reduce bandwidth requirement, but it suffers from inaccurate ROI detection due to feedback latency and undetected new targets. To address the above challenges, we propose an object detection system named PETRI. It adopts a latency-hiding pipeline workflow with adaptive keyframe interval selection for different input videos, and utilizes a retro-tracking method to find undetected targets. While achieving negligible impact on model accuracy, the proposed PETRI can save up to 66.44% and 30.25% bandwidth compared with the cloud only method and the previous state-of-art work respectively.
AbstractList Neural networks running on cloud servers have been widely used in smart surveillance, but they require high bandwidth to upload videos. Edge-cloud collaborative encoding based on ROI (Region-Of-Interest) can reduce bandwidth requirement, but it suffers from inaccurate ROI detection due to feedback latency and undetected new targets. To address the above challenges, we propose an object detection system named PETRI. It adopts a latency-hiding pipeline workflow with adaptive keyframe interval selection for different input videos, and utilizes a retro-tracking method to find undetected targets. While achieving negligible impact on model accuracy, the proposed PETRI can save up to 66.44% and 30.25% bandwidth compared with the cloud only method and the previous state-of-art work respectively.
Author Wang, Jingyu
Yang, Huazhong
Zhang, Lu
Liu, Yongpan
Liu, Ruoyang
Author_xml – sequence: 1
  givenname: Ruoyang
  surname: Liu
  fullname: Liu, Ruoyang
  email: ypliu@tsinghua.edu.cn
  organization: Tsinghua University,Department of Electronic Engineering,Beijing,China
– sequence: 2
  givenname: Lu
  surname: Zhang
  fullname: Zhang, Lu
  organization: Tsinghua University,Department of Electronic Engineering,Beijing,China
– sequence: 3
  givenname: Jingyu
  surname: Wang
  fullname: Wang, Jingyu
  organization: Tsinghua University,Department of Electronic Engineering,Beijing,China
– sequence: 4
  givenname: Huazhong
  surname: Yang
  fullname: Yang, Huazhong
  organization: Tsinghua University,Department of Electronic Engineering,Beijing,China
– sequence: 5
  givenname: Yongpan
  surname: Liu
  fullname: Liu, Yongpan
  organization: Tsinghua University,Department of Electronic Engineering,Beijing,China
BookMark eNotkF1OwzAQhI0EElB6AoTkC6SsYyexeWtDC5UqUbXluXLsTbFIneIkRb0I5yX8vOysRqP9tHNNzn3tkZA7BiPGQN0_jnMmIROjGGI2UolMQcozMlSZZGmaCB5nAi7JsGlcASkkUvTzinwtp5vV_IGu0HbG-R2daG8_nW3feuujcwH36FvqPF3vdWjpugtHdFWlvUFanOjU7jDKq7qzNK97u6iDbt0R6djqw-8yC3qPNK-6psXwQ-gBdOkOWDmPlk6c7SGmdbXXFd0Ebd770A25KHXV4PBfB-R1Nt3kz9Hi5WmejxeRjmXWRjK2KQfDU5OpLIXYlLqUnCWqECoDIW0pk8JwgVYlDEAhSjDABdcysZoBH5Dbv7sOEbeH4PonT9v_9vg3azhphQ
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/DAC18074.2021.9586088
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9781665432740
1665432748
EndPage 426
ExternalDocumentID 9586088
Genre orig-research
GroupedDBID 6IE
6IH
ACM
ALMA_UNASSIGNED_HOLDINGS
CBEJK
RIE
RIO
ID FETCH-LOGICAL-a287t-82d630c36c797602cfaf83159b497048df85bc34ed951009ee80c0343a85da103
IEDL.DBID RIE
ISICitedReferencesCount 9
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000766079700071&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 02:28:29 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a287t-82d630c36c797602cfaf83159b497048df85bc34ed951009ee80c0343a85da103
PageCount 6
ParticipantIDs ieee_primary_9586088
PublicationCentury 2000
PublicationDate 2021-Dec.-5
PublicationDateYYYYMMDD 2021-12-05
PublicationDate_xml – month: 12
  year: 2021
  text: 2021-Dec.-5
  day: 05
PublicationDecade 2020
PublicationTitle 2021 58th ACM/IEEE Design Automation Conference (DAC)
PublicationTitleAbbrev DAC
PublicationYear 2021
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssib060584060
Score 2.232925
Snippet Neural networks running on cloud servers have been widely used in smart surveillance, but they require high bandwidth to upload videos. Edge-cloud...
SourceID ieee
SourceType Publisher
StartPage 421
SubjectTerms Bandwidth
Collaboration
collaborative architecture
edge computing
Image edge detection
Object detection
Pipelines
Surveillance
Target tracking
Title PETRI: Reducing Bandwidth Requirement in Smart Surveillance by Edge-Cloud Collaborative Adaptive Frame Clustering and Pipelined Bidirectional Tracking
URI https://ieeexplore.ieee.org/document/9586088
WOSCitedRecordID wos000766079700071&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1fS8MwEA_b8MEnFSf-Jw8-2i1d2qb1basbCjLKNmFvI01uWpjdmO3EL-LnNdfWDcEX38LR9CB34S5397sj5MZnOlBzqS2PgbQcrh0EK9uWtM3nto49UTZxfRLDoT-dBlGN3G6xMABQFJ9BC5dFLl8vVY6hsnbg-p65FXVSF0KUWK0f3cHsnrFNrALp2Cxo33dDG1u9mEdgx25Ve38NUSlsyODgf9wPSXMHxqPR1swckRqkx-Qr6k9Gj3d0hJ1XDZn2ZKo_Ep29GhIW9xZRP5qkdPxmlIOO8_UGcMAQ_i3-pH39Ala4WOaahjtN2ADtarkqFgOs2qLhIsdOCsjBMKBRskL8OmjaS0pjWEQSqbF4CmPuTfI86E_CB6sasWBJ81TKjFy0x5ninhLGL2EdI7a5z42LEzuBMJdbz303VtwBjZ4YCwB8phh3uPRdLW3GT0gjXaZwSmjgSI9Jl7syUA6TWnIhwI_BVZgKdPkZOcYzna3KLhqz6jjP_yZfkH0UW1E44l6SRrbO4YrsqU2WvK-vC9F_A9eAsc4
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LT8MwDI5gIMEJ0IZ4kwNHCumS9MENyqYhxlSNIXGb0sSDSqObxjrEH-H3EndlExIXbpHV1FLsyI7tzybkLGAm1ANlHI-BcgQ3AsHKrqNc-7lrEs-fN3Ft-51O8PwcxivkfIGFAYCi-AwucFnk8s1I5xgquwxl4NlbsUrWpBB1d47W-tEezO9Z68RKmI7Lwsvb68jFZi_2GVh3L8rdv8aoFFakufU__tuktoTj0XhhaHbICmRV8hU3et27K9rF3quWTG9UZj5SM321JCzvLeJ-NM3o45tVD_qYT2aAI4bwb8knbZgXcKLhKDc0WurCDOi1UeNi0cS6LRoNc-ylgBwsAxqnY0Swg6E36dwcFrFEam2exqh7jTw1G72o5ZRDFhxlH0tTKxnjcaa5p33rmbC6Fdwg4NbJSUTo2-ttBoFMNBdg0BdjIUDANOOCq0Aa5TK-SyrZKIM9QkOhPKYklyrUgimjuO9DkIDUmAyUfJ9U8Uz743kfjX55nAd_k0_JRqv30O637zr3h2QTRViUkcgjUplOcjgm63o2Td8nJ4UafANA77UV
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2021+58th+ACM%2FIEEE+Design+Automation+Conference+%28DAC%29&rft.atitle=PETRI%3A+Reducing+Bandwidth+Requirement+in+Smart+Surveillance+by+Edge-Cloud+Collaborative+Adaptive+Frame+Clustering+and+Pipelined+Bidirectional+Tracking&rft.au=Liu%2C+Ruoyang&rft.au=Zhang%2C+Lu&rft.au=Wang%2C+Jingyu&rft.au=Yang%2C+Huazhong&rft.date=2021-12-05&rft.pub=IEEE&rft.spage=421&rft.epage=426&rft_id=info:doi/10.1109%2FDAC18074.2021.9586088&rft.externalDocID=9586088