当前交通数据采集主要依赖深度目标检测器，再辅以基于检测的跟踪（tracking-by-detection）流程；该流程预设了一个实践中常缺失的前提：检测器已针对待计数的目标类别完成训练。我们重新审视了一种专为单板计算机（SBC）设计的纯几何交通感知流程，其中检测环节是类别无关的：运动目标通过背景减除与阈值化获得，计数则依据一条横跨道路的虚拟线（即软件定义的感应环路检测器）上的几何规则判定。该方法无需目标模型、训练集或逐目标轨迹，可在树莓派（Raspberry Pi）级别硬件上以超实时速度运行。文中描述了两种计数规则：其一为恒定平均速度规则，其理论精度在车速服从高斯分布时可解析推导为约86%；其二为自校准预标定规则，该规则从斑块（blob）统计中恢复车道几何结构，并通过检测车道占用边缘实现计数，同时零额外开销地输出每辆车的平均速度。在四段视频测试中，后一规则的计数精度达83.3%–100%；在实地部署中，其精度达91%，而相同计算资源下的斑块跟踪基线方法仅为37.5%。我们详细报告了该部署期间的若干关键观测结果：精度骤降的分辨率下限、车辆在计数线上发生混叠的帧率下限、短片段人工剪辑与长时段无控实拍之间的性能差距，以及Python（易于调优，CPU占用率100%）与C++（CPU占用率40%，热稳定性更佳）之间的权衡。这些特性源于采样几何结构本身，而非特定历史时期的硬件限制，至今仍制约着边缘端部署。最后，我们论证了基于运动、类别无关的检测方法仍适用的场景：开放集类别且缺乏标注数据、功耗预算极其紧张、隐私敏感等。

Traffic data collection is dominated today by deep object detectors followed by tracking-by-detection, a pipeline that presupposes what is often missing in practice: a detector already trained on the class one wants to count. We revisit a purely geometric traffic-sensing pipeline for Single Board Computers in which detection is class-agnostic: moving objects come from background subtraction and thresholding, and counting is decided by a geometric rule on an imaginary line across the road, a software inductive loop detector. With no object model, training set or per-object trajectory, it runs faster than real time on Raspberry Pi class hardware. Two counting rules are described: a constant average speed rule, whose expected accuracy is derived analytically as about 86% under a Gaussian speed distribution, and a self-calibrating pre-calibration rule that recovers the lane geometry from blob statistics and counts edges of lane occupancy, additionally yielding per-vehicle average speed at no extra cost. Over four videos the latter counts with 83.3%-100% accuracy; in a field deployment it reaches 91% against 37.5% for a blob-tracking baseline under the same compute budget. We report the observations of that period in detail: the resolution floor below which accuracy collapses, the frame rate floor at which vehicles alias past the counting line, the gap between short curated clips and long uncontrolled footage, and the trade-off between Python (easier to tune, 100% CPU) and C++ (40% CPU, thermally viable). These are properties of the sampling geometry, not of the hardware of the time, and still constrain edge deployments. We close by arguing where motion-based, class-agnostic detection remains the right tool: open-set classes with no annotated data, tight power budgets, privacy-constrained installations, and the cold start of mining training crops to bootstrap a learned detector.