Towards a Framework to Evaluate Cooperative Perception for Connected Vehicles

Hawlader, Faisal; Frank, Raphaël

doi:10.1109/vnc52810.2021.9644667

Cited by 8 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this context, the end-to-end delay heavily depends on where we perform the computation. If the car chooses to offload the data to an edge/cloud, it must exchange the raw data, which V2X technologies may not support due to bandwidth constraints [30].…”

Section: Methodsmentioning

confidence: 99%

“…However, their approach emphasises data communication to reduce transmission overhead without evaluating the impact on perception quality. In principle, offloading raw sensor data is excellent for perception accuracy [29], but could increase transmission costs [30]. However, offloading compressed data can save network resources, but it might degrade detection quality [31].…”

Section: Perception Using C-v2x Communicationmentioning

confidence: 99%

See 1 more Smart Citation

Vehicle-to-Infrastructure Communication for Real-Time Object Detection in Autonomous Driving

Hawlader

Robinet

Frank

2023

2023 18th Wireless on-Demand Network Systems and Services Conference (WONS)

Self Cite

View full text Add to dashboard Cite

Environmental perception is a key element of autonomous driving because the information received from the perception module influences core driving decisions. An outstanding challenge in real-time perception for autonomous driving lies in finding the best trade-off between detection quality and latency. Major constraints on both computation and power have to be taken into account for real-time perception in autonomous vehicles. Larger object detection models tend to produce the best results, but are also slower at runtime. Since the most accurate detectors cannot run in real-time locally, we investigate the possibility of offloading computation to edge and cloud platforms, which are less resource-constrained. We create a synthetic dataset to train object detection models and evaluate different offloading strategies. Using real hardware and network simulations, we compare different trade-offs between prediction quality and end-to-end delay. Since sending raw frames over the network implies additional transmission delays, we also explore the use of JPEG and H.265 compression at varying qualities and measure their impact on prediction metrics. We show that models with adequate compression can be run in real-time on the cloud while outperforming local detection performance.

show abstract

Section: Methodsmentioning

confidence: 99%