The fetal electrocardiogram (f-ECG) beats analysis as well as the heart rate interpretation using the raw ECG signals captured by machine helps in providing the state of the fetus in pregnancy. For timely detection of the fetal arrhythmias, monitoring fetal ECGs constantly is important. In this paper, we are presenting the framework for detection of fetal from maternal ECG based on sparse binary matrix using Compressive Sensing. Additionally, we are presenting the preprocessing algorithm on raw fetus ECG data to remove the noises like impulsive artifacts along with notch filtering for baseline removal. The proposed method is on the basis of sparse representation of the components that are acquired using Independent Component Analysis (ICA) method, which is designed for direct application in the compressed domain. Detection of fetal ECG is performed on the basis of activated atoms in a specially designed Gaussian dictionary. The verification of the proposed framework has been carried out on ten samples of Challenge dataset A by determining QRS detection parameters such as sensitivity, S= 90.62% and positive predictivity, given by P+= 99.15%. © 2018 IEEE.