Beyond Benchmarks: Continuous Edge Inference for Fine-Grained Roadside Perception
Quick Answer
Edge-TSR is a continuous edge inference system for roadside perception on NVIDIA Jetson Orin Nano, addressing performance degradation of 20-30% in real-world deployments compared to benchmarks.
Quick Take
It enhances classification accuracy by up to 10.16% while maintaining 16.18 FPS under thermal limits without cloud offload, highlighting the need for deployment-aware evaluation in systems.
Key Points
- Edge-TSR integrates detection, tracking, and classification with minimal computational overhead.
- Real-world deployment shows 20-30% performance drop compared to static-image benchmarks.
- Achieves up to 10.16% accuracy improvement over per-frame inference baselines.
- Sustains 16.18 FPS during a 55-minute vehicular deployment without cloud offload.
- Releases a sample annotated video dataset for reproducible evaluation.
Paper Resources
Source Excerpt
arXiv:2606. 17241v1 Announce Type: new Abstract: Continuous AI inference on resource-constrained edge hardware introduces deployment effects that are largely invisible to conventional benchmark evaluation, including temporal instability in streaming video, thermal throttling under sustained load, and workload-dependent performance variability. We present Edge-TSR, a deployment-oriented continuous edge inference system for sustained roadside perception on the NVIDIA Jetson Orin Nano. …
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.CV
See more →ProMoE-FL: Prototype-conditioned Mixture of Experts for Multimodal Federated Learning with Missing Modalities
ProMoE-FL introduces a Prototype-conditioned Mixture-of-Experts framework for multimodal federated learning, effectively addressing missing modalities. It outperforms existing methods on four chest X-ray datasets, demonstrating superior feature synthesis capabilities in both homogeneous and heterogeneous settings.
