Metraipolis › archive › dc_ecdd94f4e043

Input Resolution Matters: Real-Time Object Detection Latency — arXiv:2609.12920

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.12920
License (as archived): CC0-1.0
Archived: 2026-10-16T03:08:46.297Z
SHA-256 of the archived text: 3ae3bd5a420d1ea2ba5663d9e4b3b6a234d12ffeb3142cfec4b17ef1a5779b3a
Stable URL of this page: https://metraipolis.com/documento/dc_ecdd94f4e043

How to cite

Input Resolution Matters: Real-Time Object Detection Latency — arXiv:2609.12920 — arXiv (en), https://arxiv.org/abs/2609.12920 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ecdd94f4e043 (Metraipolis archive dc_ecdd94f4e043, sha256 3ae3bd5a420d1ea2ba5663d9e4b3b6a234d12ffeb3142cfec4b17ef1a5779b3a)

BibTeX

@misc{dcecdd94f4e043,
  title = {Input Resolution Matters: Real-Time Object Detection Latency — arXiv:2609.12920},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.12920},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ecdd94f4e043; sha256 3ae3bd5a420d1ea2ba5663d9e4b3b6a234d12ffeb3142cfec4b17ef1a5779b3a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12920. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We model total latency as the convolution of preprocessing, inference, and postprocessing distributions under a simplifying independence approximation, with selected stage parameters expressed as functions of source-image resolution. Under this assumption, the probability density of the total latency is the convolution of the stage-wise densities, and its cumulative distribution function (CDF) provides the distribution of end-to-end detection time. Each stage is modeled by a parametric distribution (e.g., Exponential, Erlang, Normal, Gamma), with parameters expressed as functions of the source-image resolution. Experiments with YOLOv11n on NVIDIA Jetson Orin NX using COCO2017 images across multiple resolutions assess the proposed models against fixed-parameter baselines using Kolmogorov Smirnov, Anderson Darling, and Cramér von Mises statistics. The results indicate that resolution-aware parameterization can improve distributional approximation in the measured setting, particularly for the more flexible Normal and Gamma models, while the quality of fit remains distribution dependent. Our contribution is a theoretically grounded and lightweight formulation for studying resolution-dependent latency distributions in a measured object detection pipeline.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-14 in cs.PF).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Performance (cs.PF).
Pagina del lavoro: https://arxiv.org/abs/2609.12920 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-16T03:03:37.612Z dalla pagina https://arxiv.org/catchup/cs.PF/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).