Traffic congestion detection typically relies on loop detectors or centralized cloud processing, both of which have limitations. Edge-based multi-modal analytics enable real-time analysis close to data sources while reducing bandwidth consumption. The work addresses the challenge of selecting appropriate algorithms based on available resources and required accuracy.
This paper describes a multi-modal traffic analytics framework deployed at the edge for detecting and analyzing non-recurring congestion. The system integrates multiple object detection algorithms (YOLO, Faster-RCNN, SSD) with vehicle tracking to provide real-time traffic analysis with tradeoffs between accuracy and computational resource consumption.
The paper demonstrates a hierarchical traffic analytics workflow deployed on Raspberry Pi edge devices at intersections in Nashville. The system achieves different accuracy levels with various object detection algorithms and implements dynamic mode selection based on traffic conditions and available resources. Results show that edge-based analysis effectively detects non-recurring congestion.
@inproceedings{Pettet2019a,
author = {Pettet, Geoffrey and Sahoo, Saroj and Dubey, Abhishek},
booktitle = {IEEE} International Conference on Pervasive Computing and Communications Workshops, PerCom Workshops 2019, Kyoto, Japan, March 11-15, 2019},
title = {Towards an Adaptive Multi-Modal Traffic Analytics Framework at the Edge},
year = {2019},
pages = {511--516},
abstract = {The Internet of Things (IoT) requires distributed, large scale data collection via geographically distributed devices. While IoT devices typically send data to the cloud for processing, this is problematic for bandwidth constrained applications. Fog and edge computing (processing data near where it is gathered, and sending only results to the cloud) has become more popular, as it lowers network overhead and latency. Edge computing often uses devices with low computational capacity, therefore service frameworks and middleware are needed to efficiently compose services. While many frameworks use a top-down perspective, quality of service is an emergent property of the entire system and often requires a bottom up approach. We define services as multi-modal, allowing resource and performance tradeoffs. Different modes can be composed to meet an application's high level goal, which is modeled as a function. We examine a case study for counting vehicle traffic through intersections in Nashville. We apply object detection and tracking to video of the intersection, which must be performed at the edge due to privacy and bandwidth constraints. We explore the hardware and software architectures, and identify the various modes. This paper lays the foundation to formulate the online optimization problem presented by the system which makes tradeoffs between the quantity of services and their quality constrained by available resources.},
bibsource = {dblp computer science bibliography, https://dblp.org},
biburl = {https://dblp.org/rec/bib/conf/percom/PettetSD19},
category = {workshop},
contribution = {lead},
doi = {10.1109/PERCOMW.2019.8730577},
file = {:Pettet2019a-Towards_an_Adaptive_Multi-Modal_Traffic_Analytics_Framework_at_the_Edge.pdf:PDF},
keywords = {traffic analysis, edge computing, object detection, vehicle tracking, IoT, real-time processing},
project = {cps-middleware,smart-transit,smart-cities},
tag = {platform,incident,transit},
timestamp = {Wed, 16 Oct 2019 14:14:54 +0200},
url = {https://doi.org/10.1109/PERCOMW.2019.8730577}
}