Problem
Research questions and friction points this paper is trying to address.
Real-Time Object Detection
Latency
Input Resolution
Distribution Modeling
End-to-End Detection Time
Input Resolution Matters: Real-Time Object Detection Latency
🤖 AI Summary
研究通过基于图像分辨率的参数化分布模型，解决了实时目标检测中总延迟建模问题，实验表明该方法能有效改善延迟分布的近似。
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
resolution-dependent latency
parametric distribution
object detection
real-time processing
distributional approximation
🔎 Similar Papers
No similar papers found.
