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...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:2021 58th ACM/IEEE Design Automation Conference (DAC) S. 421 - 426
Hauptverfasser: Liu, Ruoyang, Zhang, Lu, Wang, Jingyu, Yang, Huazhong, Liu, Yongpan
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 05.12.2021
Schlagworte:
Bandwidth
Collaboration
collaborative architecture
edge computing
Image edge detection
Object detection
Pipelines
Surveillance
Target tracking
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
DOI:10.1109/DAC18074.2021.9586088