Objective: The fetal electrocardiogram (ECG) is an objective index that reflects a fetus’s health status. Non-invasive abdominal ECG (aECG) was obtained by placing silicone electrodes on pregnant women’s abdominal wall. However, fetal QRS (fQRS) extraction is very challenging due to maternal ECG interference, motion artifacts, and other noise. Approach: This paper introduces a new single-lead non-invasive fQRS extraction method based on compressive sensing and clustering analysis. This method can be applied to portable, low-power remote fetal ECG (fECG) acquisition equipment based on the Internet of Things (IoT). It is mainly divided into the following steps: (1) optimal component extraction of single-channel signal based on compressive sensing theory; (2) location of maternal QRS (mQRS) using the clustering method based on extreme value; (3) maternal ECG (mECG) elimination; (4) The preliminary location of fQRS based on double clustering and the correction of fQRS based on fetal RR interval. Main results: The new algorithm proposed in this paper is verified on two publicly available data sets. The averages of these indicators are Se=98.53%, PPV=98.28%, ACC=96.95%, F1=98.43% for the Silesia datasets and Se=97.59%, PPV=97.63%, ACC=95.44%, F1=97.62% for the Challenge datasets A. Significance: The results show that it is feasible and reliable to locate fQRS from a single-channel aECG signal under the condition of reducing power consumption. It lays a foundation for implementing the low-power wireless transmission of fECG signal and remote fetal heart rate (FHR) monitoring based on the IoT.