输入分辨率至关重要：实时目标检测延迟
Input Resolution Matters: Real-Time Object Detection Latency
浏览论文内容
中文总结 AI 辅助
本文提出一种轻量级理论模型，将目标检测总延迟分解为各阶段分布的卷积，并引入分辨率感知参数化，实验表明可改善延迟分布拟合质量。
中文摘要 AI 辅助
我们将总延迟建模为预处理、推理和后处理分布在高斯独立近似下的卷积，其中选定的阶段参数表示为源图像分辨率的函数。在此假设下，总延迟的概率密度是各阶段密度的卷积，其累积分布函数（CDF）提供了端到端检测时间的分布。每个阶段由参数分布（例如，指数分布、厄兰分布、正态分布、伽马分布）建模，参数表示为源图像分辨率的函数。使用YOLOv11n在NVIDIA Jetson Orin NX上，采用COCO2017图像在多种分辨率下进行实验，评估所提出的模型与固定参数基线，使用Kolmogorov Smirnov、Anderson Darling和Cramér von Mises统计量进行比较。结果表明，在测量设置中，分辨率感知的参数化可以改善分布近似，特别是对于更灵活的正态和伽马模型，而拟合质量仍取决于分布。我们的贡献是为测量目标检测流水线中分辨率相关延迟分布提供了一种理论上有依据且轻量级的公式。
英文摘要
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.
发表机构
- University of Tsukuba（筑波大学）
- University of Florence（佛罗伦萨大学）
机构由 AI 辅助整理，请以论文原文为准。
