In model partitioning for real-time object detection, part of the model is deployed on a vehicle, and the remaining layers are processed in the cloud. Model partitioning requires transmitting intermediate features to the cloud, which can be problematic, given that the latency requirements are strict. This paper addresses this issue by demonstrating a lightweight feature-sharing strategy while investigating a trade-off between detection quality and latency. We report details on layer partitioning, such as which layers to split in order to achieve the desired accuracy.
Poster: Lightweight Features Sharing for Real-Time Object Detection in Cooperative Driving
26.04.2023
175359 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Poster: Edge-Assisted Unsafe Driving Detection
IEEE | 2023
|V2X sensor-sharing for cooperative and automated driving
TIBKAT | 2022
|